wufangtai commited on
Commit
a8782a2
·
1 Parent(s): 36af0f7

Adopt ten-component benchmark protocol

Browse files
blobs/columns.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Column guide
2
+
3
+ - **Overall-10** — Prompt-macro average across the ten applicable components, scaled from 0–3 to 0–100.
4
+ - **Checklist** — Satisfaction of prompt-specific verification checklist items.
5
+ - **Rubric Adaptive** — Satisfaction of prompt-specific weighted evaluation-rubric criteria.
6
+ - **Prompt Faithfulness** — How completely the image follows the user prompt.
7
+ - **Image Quality** — Visual fidelity, clarity, detail, and absence of rendering defects.
8
+ - **Text Rendering** — Correctness and legibility of text shown in the image.
9
+ - **AI Naturalness** — How natural and non-synthetic the image appears.
10
+ - **Composition & Aesthetics** — Layout, balance, coherence, and aesthetic quality.
11
+ - **Physical Plausibility** — Consistency with real-world geometry, anatomy, lighting, and physics.
12
+ - **Visual Reference** — Consistency with required visual-reference entities or attributes.
13
+ - **Text Reference** — Factual consistency with required text-derived knowledge.
14
+ - **Coverage** — Percentage and count of prompts with valid scored results. Missing-result handling follows the model-specific policy described in Metric Details.
15
+
16
+ All score columns use the 0–100 public scale. **N/A** means a component is not applicable, not a score of zero.
blobs/intro.md CHANGED
@@ -1,5 +1,7 @@
1
- **SearchGen-Bench** evaluates image generators on 751 prompts spanning 22 domains and 12 failure modes. It separates prompts that generators can answer without retrieval from visually and textually search-intensive prompts.
2
 
3
- The primary leaderboard metric, **Overall-9**, is the prompt-macro average of nine physical-plausibility judge components. The paper-compatible **Overall-10** additionally includes Text Reference. Use the scoreboard selector to inspect component, domain, and failure-mode rankings.
 
 
4
 
5
  All scores are generated from versioned prompt-level records. Counts and coverage are shown because domains and failure modes are multi-label and some commercial generators have incomplete evaluations.
 
1
+ ## Where visual generators know—and where they need search
2
 
3
+ **SearchGen-Bench** compares image generators across 751 evaluation prompts, knowledge-boundary strata, 22 domains, and 12 recurring failure modes. The benchmark separates 100 **NoSearch** prompts that strong generators can answer from parametric knowledge from 651 **SearchIntensive** prompts whose visual or textual requirements expose gaps that retrieval can address.
4
+
5
+ The primary metric is **Overall-10**: a prompt-macro average over the canonical ten applicable FF-judge+PP components, reported on a 0–100 scale. Use the scoreboard selector to inspect results by component, domain, or failure mode.
6
 
7
  All scores are generated from versioned prompt-level records. Counts and coverage are shown because domains and failure modes are multi-label and some commercial generators have incomplete evaluations.
blobs/metrics.md CHANGED
@@ -1,8 +1,6 @@
1
  ## Metric details
2
 
3
- **Overall-9** is the mean of all applicable public components for each prompt, followed by a macro average over prompts and conversion from the raw 0–3 scale to 0–100. Its components are Checklist, Rubric Adaptive, Prompt Faithfulness, Image Quality, Text Rendering, AI Naturalness, Composition and Aesthetics, Physical Plausibility, and Visual Reference.
4
-
5
- **Overall-10 (Paper)** uses the same procedure but additionally includes Text Reference. It is retained so results can be reconciled with the paper's canonical tables.
6
 
7
  An inapplicable component is excluded from its prompt-level mean. Missing model results are zero-filled by default, matching the canonical paper convention. Missing Grok-Imagine-Image and Qwen-Image-2-Pro results are excluded from their denominators. Coverage always reports valid scored prompts over prompts in the selected group.
8
 
 
1
  ## Metric details
2
 
3
+ **Overall-10** is the primary benchmark metric. For each prompt, it averages all applicable values across Checklist, Rubric Adaptive, Prompt Faithfulness, Image Quality, Text Rendering, AI Naturalness, Composition and Aesthetics, Physical Plausibility, Visual Reference, and Text Reference. Prompt-level means are then macro-averaged and converted from the raw 0–3 scale to 0–100.
 
 
4
 
5
  An inapplicable component is excluded from its prompt-level mean. Missing model results are zero-filled by default, matching the canonical paper convention. Missing Grok-Imagine-Image and Qwen-Image-2-Pro results are excluded from their denominators. Coverage always reports valid scored prompts over prompts in the selected group.
6
 
data/leaderboard_by_domain.json CHANGED
The diff for this file is too large to render. See raw diff
 
data/leaderboard_by_failure_mode.json CHANGED
@@ -9,6 +9,7 @@
9
  "physical_plausibility": 415,
10
  "prompt_faithfulness": 534,
11
  "rubric_adaptive": 534,
 
12
  "text_rendering": 376,
13
  "visual_reference_evaluation": 439
14
  },
@@ -20,6 +21,7 @@
20
  "physical_plausibility": 73.8,
21
  "prompt_faithfulness": 68.5,
22
  "rubric_adaptive": 69.7,
 
23
  "text_rendering": 73.2,
24
  "visual_reference_evaluation": 66.6
25
  },
@@ -43,6 +45,7 @@
43
  "physical_plausibility": 455,
44
  "prompt_faithfulness": 534,
45
  "rubric_adaptive": 534,
 
46
  "text_rendering": 344,
47
  "visual_reference_evaluation": 437
48
  },
@@ -54,6 +57,7 @@
54
  "physical_plausibility": 76.2,
55
  "prompt_faithfulness": 62.2,
56
  "rubric_adaptive": 65.8,
 
57
  "text_rendering": 66.4,
58
  "visual_reference_evaluation": 61.6
59
  },
@@ -77,6 +81,7 @@
77
  "physical_plausibility": 389,
78
  "prompt_faithfulness": 504,
79
  "rubric_adaptive": 504,
 
80
  "text_rendering": 355,
81
  "visual_reference_evaluation": 417
82
  },
@@ -88,6 +93,7 @@
88
  "physical_plausibility": 69.9,
89
  "prompt_faithfulness": 61.3,
90
  "rubric_adaptive": 63.8,
 
91
  "text_rendering": 61.7,
92
  "visual_reference_evaluation": 60.7
93
  },
@@ -111,6 +117,7 @@
111
  "physical_plausibility": 410,
112
  "prompt_faithfulness": 526,
113
  "rubric_adaptive": 526,
 
114
  "text_rendering": 321,
115
  "visual_reference_evaluation": 439
116
  },
@@ -122,6 +129,7 @@
122
  "physical_plausibility": 70.2,
123
  "prompt_faithfulness": 50.8,
124
  "rubric_adaptive": 54.7,
 
125
  "text_rendering": 56.9,
126
  "visual_reference_evaluation": 47.0
127
  },
@@ -145,6 +153,7 @@
145
  "physical_plausibility": 422,
146
  "prompt_faithfulness": 534,
147
  "rubric_adaptive": 534,
 
148
  "text_rendering": 319,
149
  "visual_reference_evaluation": 448
150
  },
@@ -156,6 +165,7 @@
156
  "physical_plausibility": 65.3,
157
  "prompt_faithfulness": 47.5,
158
  "rubric_adaptive": 51.6,
 
159
  "text_rendering": 52.0,
160
  "visual_reference_evaluation": 44.0
161
  },
@@ -179,6 +189,7 @@
179
  "physical_plausibility": 441,
180
  "prompt_faithfulness": 534,
181
  "rubric_adaptive": 534,
 
182
  "text_rendering": 353,
183
  "visual_reference_evaluation": 446
184
  },
@@ -190,6 +201,7 @@
190
  "physical_plausibility": 62.1,
191
  "prompt_faithfulness": 46.1,
192
  "rubric_adaptive": 50.8,
 
193
  "text_rendering": 48.6,
194
  "visual_reference_evaluation": 41.3
195
  },
@@ -213,6 +225,7 @@
213
  "physical_plausibility": 445,
214
  "prompt_faithfulness": 534,
215
  "rubric_adaptive": 534,
 
216
  "text_rendering": 333,
217
  "visual_reference_evaluation": 436
218
  },
@@ -224,6 +237,7 @@
224
  "physical_plausibility": 64.5,
225
  "prompt_faithfulness": 41.4,
226
  "rubric_adaptive": 47.1,
 
227
  "text_rendering": 37.8,
228
  "visual_reference_evaluation": 39.6
229
  },
@@ -247,6 +261,7 @@
247
  "physical_plausibility": 427,
248
  "prompt_faithfulness": 534,
249
  "rubric_adaptive": 534,
 
250
  "text_rendering": 346,
251
  "visual_reference_evaluation": 437
252
  },
@@ -258,6 +273,7 @@
258
  "physical_plausibility": 63.3,
259
  "prompt_faithfulness": 39.6,
260
  "rubric_adaptive": 44.3,
 
261
  "text_rendering": 29.3,
262
  "visual_reference_evaluation": 38.4
263
  },
@@ -281,6 +297,7 @@
281
  "physical_plausibility": 486,
282
  "prompt_faithfulness": 534,
283
  "rubric_adaptive": 534,
 
284
  "text_rendering": 328,
285
  "visual_reference_evaluation": 435
286
  },
@@ -292,6 +309,7 @@
292
  "physical_plausibility": 48.5,
293
  "prompt_faithfulness": 25.9,
294
  "rubric_adaptive": 32.0,
 
295
  "text_rendering": 11.4,
296
  "visual_reference_evaluation": 25.4
297
  },
@@ -315,6 +333,7 @@
315
  "physical_plausibility": 440,
316
  "prompt_faithfulness": 534,
317
  "rubric_adaptive": 534,
 
318
  "text_rendering": 345,
319
  "visual_reference_evaluation": 436
320
  },
@@ -326,6 +345,7 @@
326
  "physical_plausibility": 51.2,
327
  "prompt_faithfulness": 23.0,
328
  "rubric_adaptive": 29.1,
 
329
  "text_rendering": 8.7,
330
  "visual_reference_evaluation": 23.0
331
  },
@@ -349,6 +369,7 @@
349
  "physical_plausibility": 442,
350
  "prompt_faithfulness": 533,
351
  "rubric_adaptive": 534,
 
352
  "text_rendering": 327,
353
  "visual_reference_evaluation": 434
354
  },
@@ -360,6 +381,7 @@
360
  "physical_plausibility": 48.1,
361
  "prompt_faithfulness": 17.0,
362
  "rubric_adaptive": 23.4,
 
363
  "text_rendering": 4.5,
364
  "visual_reference_evaluation": 16.3
365
  },
@@ -383,6 +405,7 @@
383
  "physical_plausibility": 460,
384
  "prompt_faithfulness": 534,
385
  "rubric_adaptive": 534,
 
386
  "text_rendering": 313,
387
  "visual_reference_evaluation": 435
388
  },
@@ -394,6 +417,7 @@
394
  "physical_plausibility": 41.4,
395
  "prompt_faithfulness": 18.4,
396
  "rubric_adaptive": 23.2,
 
397
  "text_rendering": 4.1,
398
  "visual_reference_evaluation": 19.0
399
  },
@@ -417,6 +441,7 @@
417
  "physical_plausibility": 473,
418
  "prompt_faithfulness": 534,
419
  "rubric_adaptive": 534,
 
420
  "text_rendering": 430,
421
  "visual_reference_evaluation": 506
422
  },
@@ -428,6 +453,7 @@
428
  "physical_plausibility": 17.3,
429
  "prompt_faithfulness": 6.0,
430
  "rubric_adaptive": 8.1,
 
431
  "text_rendering": 0.9,
432
  "visual_reference_evaluation": 5.9
433
  },
@@ -453,6 +479,7 @@
453
  "physical_plausibility": 144,
454
  "prompt_faithfulness": 159,
455
  "rubric_adaptive": 159,
 
456
  "text_rendering": 95,
457
  "visual_reference_evaluation": 121
458
  },
@@ -464,6 +491,7 @@
464
  "physical_plausibility": 75.3,
465
  "prompt_faithfulness": 68.3,
466
  "rubric_adaptive": 71.3,
 
467
  "text_rendering": 70.9,
468
  "visual_reference_evaluation": 62.4
469
  },
@@ -487,6 +515,7 @@
487
  "physical_plausibility": 149,
488
  "prompt_faithfulness": 159,
489
  "rubric_adaptive": 159,
 
490
  "text_rendering": 78,
491
  "visual_reference_evaluation": 121
492
  },
@@ -498,6 +527,7 @@
498
  "physical_plausibility": 77.9,
499
  "prompt_faithfulness": 63.1,
500
  "rubric_adaptive": 68.7,
 
501
  "text_rendering": 61.3,
502
  "visual_reference_evaluation": 59.5
503
  },
@@ -521,6 +551,7 @@
521
  "physical_plausibility": 136,
522
  "prompt_faithfulness": 153,
523
  "rubric_adaptive": 153,
 
524
  "text_rendering": 92,
525
  "visual_reference_evaluation": 121
526
  },
@@ -532,6 +563,7 @@
532
  "physical_plausibility": 71.3,
533
  "prompt_faithfulness": 63.8,
534
  "rubric_adaptive": 68.1,
 
535
  "text_rendering": 64.7,
536
  "visual_reference_evaluation": 61.0
537
  },
@@ -555,6 +587,7 @@
555
  "physical_plausibility": 139,
556
  "prompt_faithfulness": 158,
557
  "rubric_adaptive": 158,
 
558
  "text_rendering": 70,
559
  "visual_reference_evaluation": 124
560
  },
@@ -566,6 +599,7 @@
566
  "physical_plausibility": 71.0,
567
  "prompt_faithfulness": 54.7,
568
  "rubric_adaptive": 62.6,
 
569
  "text_rendering": 65.5,
570
  "visual_reference_evaluation": 53.2
571
  },
@@ -589,6 +623,7 @@
589
  "physical_plausibility": 139,
590
  "prompt_faithfulness": 159,
591
  "rubric_adaptive": 159,
 
592
  "text_rendering": 73,
593
  "visual_reference_evaluation": 126
594
  },
@@ -600,6 +635,7 @@
600
  "physical_plausibility": 69.3,
601
  "prompt_faithfulness": 54.8,
602
  "rubric_adaptive": 61.9,
 
603
  "text_rendering": 60.7,
604
  "visual_reference_evaluation": 53.8
605
  },
@@ -623,6 +659,7 @@
623
  "physical_plausibility": 141,
624
  "prompt_faithfulness": 159,
625
  "rubric_adaptive": 159,
 
626
  "text_rendering": 75,
627
  "visual_reference_evaluation": 121
628
  },
@@ -634,6 +671,7 @@
634
  "physical_plausibility": 70.7,
635
  "prompt_faithfulness": 51.2,
636
  "rubric_adaptive": 57.5,
 
637
  "text_rendering": 49.6,
638
  "visual_reference_evaluation": 50.0
639
  },
@@ -657,6 +695,7 @@
657
  "physical_plausibility": 139,
658
  "prompt_faithfulness": 159,
659
  "rubric_adaptive": 159,
 
660
  "text_rendering": 86,
661
  "visual_reference_evaluation": 126
662
  },
@@ -668,6 +707,7 @@
668
  "physical_plausibility": 70.0,
669
  "prompt_faithfulness": 53.6,
670
  "rubric_adaptive": 58.6,
 
671
  "text_rendering": 54.5,
672
  "visual_reference_evaluation": 48.3
673
  },
@@ -691,6 +731,7 @@
691
  "physical_plausibility": 143,
692
  "prompt_faithfulness": 159,
693
  "rubric_adaptive": 159,
 
694
  "text_rendering": 79,
695
  "visual_reference_evaluation": 121
696
  },
@@ -702,6 +743,7 @@
702
  "physical_plausibility": 68.1,
703
  "prompt_faithfulness": 44.5,
704
  "rubric_adaptive": 52.5,
 
705
  "text_rendering": 20.8,
706
  "visual_reference_evaluation": 42.8
707
  },
@@ -725,6 +767,7 @@
725
  "physical_plausibility": 153,
726
  "prompt_faithfulness": 159,
727
  "rubric_adaptive": 159,
 
728
  "text_rendering": 74,
729
  "visual_reference_evaluation": 121
730
  },
@@ -736,6 +779,7 @@
736
  "physical_plausibility": 60.1,
737
  "prompt_faithfulness": 38.4,
738
  "rubric_adaptive": 44.8,
 
739
  "text_rendering": 21.2,
740
  "visual_reference_evaluation": 39.9
741
  },
@@ -759,6 +803,7 @@
759
  "physical_plausibility": 143,
760
  "prompt_faithfulness": 159,
761
  "rubric_adaptive": 159,
 
762
  "text_rendering": 81,
763
  "visual_reference_evaluation": 121
764
  },
@@ -770,6 +815,7 @@
770
  "physical_plausibility": 60.5,
771
  "prompt_faithfulness": 32.0,
772
  "rubric_adaptive": 39.4,
 
773
  "text_rendering": 6.8,
774
  "visual_reference_evaluation": 33.3
775
  },
@@ -793,6 +839,7 @@
793
  "physical_plausibility": 140,
794
  "prompt_faithfulness": 159,
795
  "rubric_adaptive": 159,
 
796
  "text_rendering": 79,
797
  "visual_reference_evaluation": 121
798
  },
@@ -804,6 +851,7 @@
804
  "physical_plausibility": 58.2,
805
  "prompt_faithfulness": 23.3,
806
  "rubric_adaptive": 31.3,
 
807
  "text_rendering": 4.2,
808
  "visual_reference_evaluation": 22.6
809
  },
@@ -827,6 +875,7 @@
827
  "physical_plausibility": 142,
828
  "prompt_faithfulness": 159,
829
  "rubric_adaptive": 159,
 
830
  "text_rendering": 70,
831
  "visual_reference_evaluation": 121
832
  },
@@ -838,6 +887,7 @@
838
  "physical_plausibility": 49.4,
839
  "prompt_faithfulness": 24.3,
840
  "rubric_adaptive": 30.4,
 
841
  "text_rendering": 2.6,
842
  "visual_reference_evaluation": 24.8
843
  },
@@ -861,6 +911,7 @@
861
  "physical_plausibility": 151,
862
  "prompt_faithfulness": 159,
863
  "rubric_adaptive": 159,
 
864
  "text_rendering": 124,
865
  "visual_reference_evaluation": 147
866
  },
@@ -872,6 +923,7 @@
872
  "physical_plausibility": 19.6,
873
  "prompt_faithfulness": 6.1,
874
  "rubric_adaptive": 8.3,
 
875
  "text_rendering": 0.7,
876
  "visual_reference_evaluation": 6.3
877
  },
@@ -897,6 +949,7 @@
897
  "physical_plausibility": 193,
898
  "prompt_faithfulness": 281,
899
  "rubric_adaptive": 281,
 
900
  "text_rendering": 226,
901
  "visual_reference_evaluation": 224
902
  },
@@ -908,6 +961,7 @@
908
  "physical_plausibility": 81.0,
909
  "prompt_faithfulness": 71.9,
910
  "rubric_adaptive": 72.6,
 
911
  "text_rendering": 78.8,
912
  "visual_reference_evaluation": 67.3
913
  },
@@ -931,6 +985,7 @@
931
  "physical_plausibility": 221,
932
  "prompt_faithfulness": 281,
933
  "rubric_adaptive": 281,
 
934
  "text_rendering": 210,
935
  "visual_reference_evaluation": 223
936
  },
@@ -942,6 +997,7 @@
942
  "physical_plausibility": 80.9,
943
  "prompt_faithfulness": 62.9,
944
  "rubric_adaptive": 64.5,
 
945
  "text_rendering": 67.1,
946
  "visual_reference_evaluation": 59.2
947
  },
@@ -965,6 +1021,7 @@
965
  "physical_plausibility": 181,
966
  "prompt_faithfulness": 269,
967
  "rubric_adaptive": 269,
 
968
  "text_rendering": 218,
969
  "visual_reference_evaluation": 221
970
  },
@@ -976,6 +1033,7 @@
976
  "physical_plausibility": 76.4,
977
  "prompt_faithfulness": 63.5,
978
  "rubric_adaptive": 63.6,
 
979
  "text_rendering": 62.9,
980
  "visual_reference_evaluation": 57.5
981
  },
@@ -999,6 +1057,7 @@
999
  "physical_plausibility": 190,
1000
  "prompt_faithfulness": 277,
1001
  "rubric_adaptive": 277,
 
1002
  "text_rendering": 208,
1003
  "visual_reference_evaluation": 229
1004
  },
@@ -1010,6 +1069,7 @@
1010
  "physical_plausibility": 72.5,
1011
  "prompt_faithfulness": 52.2,
1012
  "rubric_adaptive": 53.8,
 
1013
  "text_rendering": 58.7,
1014
  "visual_reference_evaluation": 44.8
1015
  },
@@ -1033,6 +1093,7 @@
1033
  "physical_plausibility": 199,
1034
  "prompt_faithfulness": 281,
1035
  "rubric_adaptive": 281,
 
1036
  "text_rendering": 203,
1037
  "visual_reference_evaluation": 234
1038
  },
@@ -1044,6 +1105,7 @@
1044
  "physical_plausibility": 66.3,
1045
  "prompt_faithfulness": 49.7,
1046
  "rubric_adaptive": 51.8,
 
1047
  "text_rendering": 56.2,
1048
  "visual_reference_evaluation": 41.3
1049
  },
@@ -1067,6 +1129,7 @@
1067
  "physical_plausibility": 212,
1068
  "prompt_faithfulness": 281,
1069
  "rubric_adaptive": 281,
 
1070
  "text_rendering": 220,
1071
  "visual_reference_evaluation": 233
1072
  },
@@ -1078,6 +1141,7 @@
1078
  "physical_plausibility": 62.6,
1079
  "prompt_faithfulness": 42.3,
1080
  "rubric_adaptive": 47.0,
 
1081
  "text_rendering": 47.3,
1082
  "visual_reference_evaluation": 35.6
1083
  },
@@ -1101,6 +1165,7 @@
1101
  "physical_plausibility": 217,
1102
  "prompt_faithfulness": 280,
1103
  "rubric_adaptive": 281,
 
1104
  "text_rendering": 208,
1105
  "visual_reference_evaluation": 223
1106
  },
@@ -1112,6 +1177,7 @@
1112
  "physical_plausibility": 61.5,
1113
  "prompt_faithfulness": 37.7,
1114
  "rubric_adaptive": 42.8,
 
1115
  "text_rendering": 35.8,
1116
  "visual_reference_evaluation": 33.5
1117
  },
@@ -1135,6 +1201,7 @@
1135
  "physical_plausibility": 205,
1136
  "prompt_faithfulness": 281,
1137
  "rubric_adaptive": 281,
 
1138
  "text_rendering": 216,
1139
  "visual_reference_evaluation": 223
1140
  },
@@ -1146,6 +1213,7 @@
1146
  "physical_plausibility": 66.7,
1147
  "prompt_faithfulness": 36.6,
1148
  "rubric_adaptive": 40.3,
 
1149
  "text_rendering": 26.9,
1150
  "visual_reference_evaluation": 32.2
1151
  },
@@ -1169,6 +1237,7 @@
1169
  "physical_plausibility": 250,
1170
  "prompt_faithfulness": 281,
1171
  "rubric_adaptive": 281,
 
1172
  "text_rendering": 206,
1173
  "visual_reference_evaluation": 223
1174
  },
@@ -1180,6 +1249,7 @@
1180
  "physical_plausibility": 44.9,
1181
  "prompt_faithfulness": 20.8,
1182
  "rubric_adaptive": 25.9,
 
1183
  "text_rendering": 11.2,
1184
  "visual_reference_evaluation": 18.4
1185
  },
@@ -1203,6 +1273,7 @@
1203
  "physical_plausibility": 211,
1204
  "prompt_faithfulness": 281,
1205
  "rubric_adaptive": 281,
 
1206
  "text_rendering": 219,
1207
  "visual_reference_evaluation": 223
1208
  },
@@ -1214,6 +1285,7 @@
1214
  "physical_plausibility": 48.6,
1215
  "prompt_faithfulness": 18.1,
1216
  "rubric_adaptive": 23.8,
 
1217
  "text_rendering": 7.4,
1218
  "visual_reference_evaluation": 15.7
1219
  },
@@ -1237,6 +1309,7 @@
1237
  "physical_plausibility": 211,
1238
  "prompt_faithfulness": 280,
1239
  "rubric_adaptive": 281,
 
1240
  "text_rendering": 203,
1241
  "visual_reference_evaluation": 222
1242
  },
@@ -1248,6 +1321,7 @@
1248
  "physical_plausibility": 44.9,
1249
  "prompt_faithfulness": 12.7,
1250
  "rubric_adaptive": 19.3,
 
1251
  "text_rendering": 4.1,
1252
  "visual_reference_evaluation": 12.1
1253
  },
@@ -1271,6 +1345,7 @@
1271
  "physical_plausibility": 226,
1272
  "prompt_faithfulness": 281,
1273
  "rubric_adaptive": 281,
 
1274
  "text_rendering": 204,
1275
  "visual_reference_evaluation": 223
1276
  },
@@ -1282,6 +1357,7 @@
1282
  "physical_plausibility": 34.5,
1283
  "prompt_faithfulness": 11.9,
1284
  "rubric_adaptive": 16.8,
 
1285
  "text_rendering": 3.6,
1286
  "visual_reference_evaluation": 11.4
1287
  },
@@ -1305,6 +1381,7 @@
1305
  "physical_plausibility": 234,
1306
  "prompt_faithfulness": 281,
1307
  "rubric_adaptive": 281,
 
1308
  "text_rendering": 229,
1309
  "visual_reference_evaluation": 256
1310
  },
@@ -1316,6 +1393,7 @@
1316
  "physical_plausibility": 21.2,
1317
  "prompt_faithfulness": 4.2,
1318
  "rubric_adaptive": 6.8,
 
1319
  "text_rendering": 0.6,
1320
  "visual_reference_evaluation": 4.8
1321
  },
@@ -1341,6 +1419,7 @@
1341
  "physical_plausibility": 23,
1342
  "prompt_faithfulness": 118,
1343
  "rubric_adaptive": 118,
 
1344
  "text_rendering": 110,
1345
  "visual_reference_evaluation": 95
1346
  },
@@ -1352,6 +1431,7 @@
1352
  "physical_plausibility": 91.3,
1353
  "prompt_faithfulness": 68.2,
1354
  "rubric_adaptive": 63.6,
 
1355
  "text_rendering": 74.1,
1356
  "visual_reference_evaluation": 66.1
1357
  },
@@ -1375,6 +1455,7 @@
1375
  "physical_plausibility": 72,
1376
  "prompt_faithfulness": 118,
1377
  "rubric_adaptive": 118,
 
1378
  "text_rendering": 110,
1379
  "visual_reference_evaluation": 95
1380
  },
@@ -1386,6 +1467,7 @@
1386
  "physical_plausibility": 85.6,
1387
  "prompt_faithfulness": 58.4,
1388
  "rubric_adaptive": 53.3,
 
1389
  "text_rendering": 63.5,
1390
  "visual_reference_evaluation": 53.6
1391
  },
@@ -1409,6 +1491,7 @@
1409
  "physical_plausibility": 39,
1410
  "prompt_faithfulness": 118,
1411
  "rubric_adaptive": 118,
 
1412
  "text_rendering": 113,
1413
  "visual_reference_evaluation": 96
1414
  },
@@ -1420,6 +1503,7 @@
1420
  "physical_plausibility": 90.2,
1421
  "prompt_faithfulness": 57.5,
1422
  "rubric_adaptive": 53.1,
 
1423
  "text_rendering": 55.6,
1424
  "visual_reference_evaluation": 53.3
1425
  },
@@ -1443,6 +1527,7 @@
1443
  "physical_plausibility": 20,
1444
  "prompt_faithfulness": 118,
1445
  "rubric_adaptive": 118,
 
1446
  "text_rendering": 115,
1447
  "visual_reference_evaluation": 96
1448
  },
@@ -1454,6 +1539,7 @@
1454
  "physical_plausibility": 69.2,
1455
  "prompt_faithfulness": 37.6,
1456
  "rubric_adaptive": 36.8,
 
1457
  "text_rendering": 41.3,
1458
  "visual_reference_evaluation": 28.3
1459
  },
@@ -1477,6 +1563,7 @@
1477
  "physical_plausibility": 23,
1478
  "prompt_faithfulness": 118,
1479
  "rubric_adaptive": 118,
 
1480
  "text_rendering": 113,
1481
  "visual_reference_evaluation": 96
1482
  },
@@ -1488,6 +1575,7 @@
1488
  "physical_plausibility": 74.6,
1489
  "prompt_faithfulness": 36.6,
1490
  "rubric_adaptive": 34.8,
 
1491
  "text_rendering": 41.6,
1492
  "visual_reference_evaluation": 28.6
1493
  },
@@ -1511,6 +1599,7 @@
1511
  "physical_plausibility": 45,
1512
  "prompt_faithfulness": 118,
1513
  "rubric_adaptive": 118,
 
1514
  "text_rendering": 113,
1515
  "visual_reference_evaluation": 96
1516
  },
@@ -1522,6 +1611,7 @@
1522
  "physical_plausibility": 65.2,
1523
  "prompt_faithfulness": 32.9,
1524
  "rubric_adaptive": 31.1,
 
1525
  "text_rendering": 37.2,
1526
  "visual_reference_evaluation": 20.1
1527
  },
@@ -1545,6 +1635,7 @@
1545
  "physical_plausibility": 55,
1546
  "prompt_faithfulness": 118,
1547
  "rubric_adaptive": 118,
 
1548
  "text_rendering": 112,
1549
  "visual_reference_evaluation": 95
1550
  },
@@ -1556,6 +1647,7 @@
1556
  "physical_plausibility": 65.8,
1557
  "prompt_faithfulness": 25.2,
1558
  "rubric_adaptive": 25.2,
 
1559
  "text_rendering": 20.2,
1560
  "visual_reference_evaluation": 17.7
1561
  },
@@ -1579,6 +1671,7 @@
1579
  "physical_plausibility": 55,
1580
  "prompt_faithfulness": 118,
1581
  "rubric_adaptive": 118,
 
1582
  "text_rendering": 114,
1583
  "visual_reference_evaluation": 95
1584
  },
@@ -1590,6 +1683,7 @@
1590
  "physical_plausibility": 59.7,
1591
  "prompt_faithfulness": 21.6,
1592
  "rubric_adaptive": 24.2,
 
1593
  "text_rendering": 22.1,
1594
  "visual_reference_evaluation": 17.4
1595
  },
@@ -1613,6 +1707,7 @@
1613
  "physical_plausibility": 83,
1614
  "prompt_faithfulness": 118,
1615
  "rubric_adaptive": 118,
 
1616
  "text_rendering": 114,
1617
  "visual_reference_evaluation": 95
1618
  },
@@ -1624,6 +1719,7 @@
1624
  "physical_plausibility": 16.1,
1625
  "prompt_faithfulness": 1.3,
1626
  "rubric_adaptive": 4.1,
 
1627
  "text_rendering": 0.3,
1628
  "visual_reference_evaluation": 2.3
1629
  },
@@ -1647,6 +1743,7 @@
1647
  "physical_plausibility": 59,
1648
  "prompt_faithfulness": 118,
1649
  "rubric_adaptive": 118,
 
1650
  "text_rendering": 117,
1651
  "visual_reference_evaluation": 95
1652
  },
@@ -1658,6 +1755,7 @@
1658
  "physical_plausibility": 12.1,
1659
  "prompt_faithfulness": 2.0,
1660
  "rubric_adaptive": 3.3,
 
1661
  "text_rendering": 1.1,
1662
  "visual_reference_evaluation": 1.8
1663
  },
@@ -1681,6 +1779,7 @@
1681
  "physical_plausibility": 80,
1682
  "prompt_faithfulness": 118,
1683
  "rubric_adaptive": 118,
 
1684
  "text_rendering": 112,
1685
  "visual_reference_evaluation": 96
1686
  },
@@ -1692,6 +1791,7 @@
1692
  "physical_plausibility": 11.2,
1693
  "prompt_faithfulness": 1.1,
1694
  "rubric_adaptive": 2.6,
 
1695
  "text_rendering": 0.3,
1696
  "visual_reference_evaluation": 1.4
1697
  },
@@ -1715,6 +1815,7 @@
1715
  "physical_plausibility": 64,
1716
  "prompt_faithfulness": 117,
1717
  "rubric_adaptive": 118,
 
1718
  "text_rendering": 115,
1719
  "visual_reference_evaluation": 94
1720
  },
@@ -1726,6 +1827,7 @@
1726
  "physical_plausibility": 9.4,
1727
  "prompt_faithfulness": 0.4,
1728
  "rubric_adaptive": 2.0,
 
1729
  "text_rendering": 0.1,
1730
  "visual_reference_evaluation": 0.9
1731
  },
@@ -1749,6 +1851,7 @@
1749
  "physical_plausibility": 69,
1750
  "prompt_faithfulness": 118,
1751
  "rubric_adaptive": 118,
 
1752
  "text_rendering": 112,
1753
  "visual_reference_evaluation": 95
1754
  },
@@ -1760,6 +1863,7 @@
1760
  "physical_plausibility": 5.1,
1761
  "prompt_faithfulness": 1.0,
1762
  "rubric_adaptive": 1.8,
 
1763
  "text_rendering": 0.0,
1764
  "visual_reference_evaluation": 1.2
1765
  },
@@ -1785,6 +1889,7 @@
1785
  "physical_plausibility": 352,
1786
  "prompt_faithfulness": 419,
1787
  "rubric_adaptive": 419,
 
1788
  "text_rendering": 264,
1789
  "visual_reference_evaluation": 352
1790
  },
@@ -1796,6 +1901,7 @@
1796
  "physical_plausibility": 70.5,
1797
  "prompt_faithfulness": 63.5,
1798
  "rubric_adaptive": 66.5,
 
1799
  "text_rendering": 69.8,
1800
  "visual_reference_evaluation": 60.4
1801
  },
@@ -1819,6 +1925,7 @@
1819
  "physical_plausibility": 371,
1820
  "prompt_faithfulness": 419,
1821
  "rubric_adaptive": 419,
 
1822
  "text_rendering": 237,
1823
  "visual_reference_evaluation": 351
1824
  },
@@ -1830,6 +1937,7 @@
1830
  "physical_plausibility": 73.2,
1831
  "prompt_faithfulness": 58.9,
1832
  "rubric_adaptive": 64.0,
 
1833
  "text_rendering": 62.0,
1834
  "visual_reference_evaluation": 57.1
1835
  },
@@ -1853,6 +1961,7 @@
1853
  "physical_plausibility": 323,
1854
  "prompt_faithfulness": 388,
1855
  "rubric_adaptive": 388,
 
1856
  "text_rendering": 237,
1857
  "visual_reference_evaluation": 326
1858
  },
@@ -1864,6 +1973,7 @@
1864
  "physical_plausibility": 68.2,
1865
  "prompt_faithfulness": 58.8,
1866
  "rubric_adaptive": 63.1,
 
1867
  "text_rendering": 62.1,
1868
  "visual_reference_evaluation": 55.9
1869
  },
@@ -1887,6 +1997,7 @@
1887
  "physical_plausibility": 344,
1888
  "prompt_faithfulness": 410,
1889
  "rubric_adaptive": 410,
 
1890
  "text_rendering": 203,
1891
  "visual_reference_evaluation": 347
1892
  },
@@ -1898,6 +2009,7 @@
1898
  "physical_plausibility": 65.9,
1899
  "prompt_faithfulness": 44.4,
1900
  "rubric_adaptive": 51.0,
 
1901
  "text_rendering": 52.5,
1902
  "visual_reference_evaluation": 40.5
1903
  },
@@ -1921,6 +2033,7 @@
1921
  "physical_plausibility": 354,
1922
  "prompt_faithfulness": 419,
1923
  "rubric_adaptive": 419,
 
1924
  "text_rendering": 205,
1925
  "visual_reference_evaluation": 358
1926
  },
@@ -1932,6 +2045,7 @@
1932
  "physical_plausibility": 62.5,
1933
  "prompt_faithfulness": 41.9,
1934
  "rubric_adaptive": 48.4,
 
1935
  "text_rendering": 48.1,
1936
  "visual_reference_evaluation": 37.3
1937
  },
@@ -1955,6 +2069,7 @@
1955
  "physical_plausibility": 366,
1956
  "prompt_faithfulness": 419,
1957
  "rubric_adaptive": 419,
 
1958
  "text_rendering": 241,
1959
  "visual_reference_evaluation": 356
1960
  },
@@ -1966,6 +2081,7 @@
1966
  "physical_plausibility": 59.9,
1967
  "prompt_faithfulness": 43.5,
1968
  "rubric_adaptive": 49.4,
 
1969
  "text_rendering": 45.3,
1970
  "visual_reference_evaluation": 37.2
1971
  },
@@ -1989,6 +2105,7 @@
1989
  "physical_plausibility": 369,
1990
  "prompt_faithfulness": 418,
1991
  "rubric_adaptive": 419,
 
1992
  "text_rendering": 219,
1993
  "visual_reference_evaluation": 348
1994
  },
@@ -2000,6 +2117,7 @@
2000
  "physical_plausibility": 63.0,
2001
  "prompt_faithfulness": 40.4,
2002
  "rubric_adaptive": 47.6,
 
2003
  "text_rendering": 35.8,
2004
  "visual_reference_evaluation": 36.3
2005
  },
@@ -2023,6 +2141,7 @@
2023
  "physical_plausibility": 367,
2024
  "prompt_faithfulness": 419,
2025
  "rubric_adaptive": 419,
 
2026
  "text_rendering": 236,
2027
  "visual_reference_evaluation": 349
2028
  },
@@ -2034,6 +2153,7 @@
2034
  "physical_plausibility": 62.0,
2035
  "prompt_faithfulness": 40.2,
2036
  "rubric_adaptive": 46.2,
 
2037
  "text_rendering": 29.8,
2038
  "visual_reference_evaluation": 36.4
2039
  },
@@ -2057,6 +2177,7 @@
2057
  "physical_plausibility": 388,
2058
  "prompt_faithfulness": 419,
2059
  "rubric_adaptive": 419,
 
2060
  "text_rendering": 212,
2061
  "visual_reference_evaluation": 348
2062
  },
@@ -2068,6 +2189,7 @@
2068
  "physical_plausibility": 52.0,
2069
  "prompt_faithfulness": 28.4,
2070
  "rubric_adaptive": 35.2,
 
2071
  "text_rendering": 14.9,
2072
  "visual_reference_evaluation": 25.9
2073
  },
@@ -2091,6 +2213,7 @@
2091
  "physical_plausibility": 365,
2092
  "prompt_faithfulness": 419,
2093
  "rubric_adaptive": 419,
 
2094
  "text_rendering": 230,
2095
  "visual_reference_evaluation": 348
2096
  },
@@ -2102,6 +2225,7 @@
2102
  "physical_plausibility": 53.1,
2103
  "prompt_faithfulness": 23.9,
2104
  "rubric_adaptive": 31.2,
 
2105
  "text_rendering": 9.9,
2106
  "visual_reference_evaluation": 21.3
2107
  },
@@ -2125,6 +2249,7 @@
2125
  "physical_plausibility": 355,
2126
  "prompt_faithfulness": 418,
2127
  "rubric_adaptive": 419,
 
2128
  "text_rendering": 223,
2129
  "visual_reference_evaluation": 347
2130
  },
@@ -2136,6 +2261,7 @@
2136
  "physical_plausibility": 49.9,
2137
  "prompt_faithfulness": 17.6,
2138
  "rubric_adaptive": 25.6,
 
2139
  "text_rendering": 5.0,
2140
  "visual_reference_evaluation": 14.6
2141
  },
@@ -2159,6 +2285,7 @@
2159
  "physical_plausibility": 373,
2160
  "prompt_faithfulness": 419,
2161
  "rubric_adaptive": 419,
 
2162
  "text_rendering": 213,
2163
  "visual_reference_evaluation": 348
2164
  },
@@ -2170,6 +2297,7 @@
2170
  "physical_plausibility": 41.1,
2171
  "prompt_faithfulness": 18.9,
2172
  "rubric_adaptive": 25.4,
 
2173
  "text_rendering": 4.5,
2174
  "visual_reference_evaluation": 18.8
2175
  },
@@ -2193,6 +2321,7 @@
2193
  "physical_plausibility": 388,
2194
  "prompt_faithfulness": 419,
2195
  "rubric_adaptive": 419,
 
2196
  "text_rendering": 305,
2197
  "visual_reference_evaluation": 402
2198
  },
@@ -2204,6 +2333,7 @@
2204
  "physical_plausibility": 21.5,
2205
  "prompt_faithfulness": 6.7,
2206
  "rubric_adaptive": 9.6,
 
2207
  "text_rendering": 0.2,
2208
  "visual_reference_evaluation": 6.1
2209
  },
@@ -2229,6 +2359,7 @@
2229
  "physical_plausibility": 176,
2230
  "prompt_faithfulness": 273,
2231
  "rubric_adaptive": 273,
 
2232
  "text_rendering": 217,
2233
  "visual_reference_evaluation": 222
2234
  },
@@ -2240,6 +2371,7 @@
2240
  "physical_plausibility": 80.2,
2241
  "prompt_faithfulness": 68.9,
2242
  "rubric_adaptive": 69.1,
 
2243
  "text_rendering": 73.8,
2244
  "visual_reference_evaluation": 67.1
2245
  },
@@ -2263,6 +2395,7 @@
2263
  "physical_plausibility": 215,
2264
  "prompt_faithfulness": 273,
2265
  "rubric_adaptive": 273,
 
2266
  "text_rendering": 208,
2267
  "visual_reference_evaluation": 223
2268
  },
@@ -2274,6 +2407,7 @@
2274
  "physical_plausibility": 80.2,
2275
  "prompt_faithfulness": 59.3,
2276
  "rubric_adaptive": 60.3,
 
2277
  "text_rendering": 62.4,
2278
  "visual_reference_evaluation": 56.9
2279
  },
@@ -2297,6 +2431,7 @@
2297
  "physical_plausibility": 184,
2298
  "prompt_faithfulness": 272,
2299
  "rubric_adaptive": 272,
 
2300
  "text_rendering": 213,
2301
  "visual_reference_evaluation": 226
2302
  },
@@ -2308,6 +2443,7 @@
2308
  "physical_plausibility": 74.8,
2309
  "prompt_faithfulness": 58.5,
2310
  "rubric_adaptive": 58.2,
 
2311
  "text_rendering": 56.3,
2312
  "visual_reference_evaluation": 56.2
2313
  },
@@ -2331,6 +2467,7 @@
2331
  "physical_plausibility": 173,
2332
  "prompt_faithfulness": 271,
2333
  "rubric_adaptive": 271,
 
2334
  "text_rendering": 197,
2335
  "visual_reference_evaluation": 224
2336
  },
@@ -2342,6 +2479,7 @@
2342
  "physical_plausibility": 73.4,
2343
  "prompt_faithfulness": 46.1,
2344
  "rubric_adaptive": 48.4,
 
2345
  "text_rendering": 48.8,
2346
  "visual_reference_evaluation": 41.5
2347
  },
@@ -2365,6 +2503,7 @@
2365
  "physical_plausibility": 179,
2366
  "prompt_faithfulness": 273,
2367
  "rubric_adaptive": 273,
 
2368
  "text_rendering": 194,
2369
  "visual_reference_evaluation": 227
2370
  },
@@ -2376,6 +2515,7 @@
2376
  "physical_plausibility": 67.9,
2377
  "prompt_faithfulness": 42.6,
2378
  "rubric_adaptive": 45.5,
 
2379
  "text_rendering": 44.5,
2380
  "visual_reference_evaluation": 39.2
2381
  },
@@ -2399,6 +2539,7 @@
2399
  "physical_plausibility": 206,
2400
  "prompt_faithfulness": 273,
2401
  "rubric_adaptive": 273,
 
2402
  "text_rendering": 214,
2403
  "visual_reference_evaluation": 227
2404
  },
@@ -2410,6 +2551,7 @@
2410
  "physical_plausibility": 60.2,
2411
  "prompt_faithfulness": 37.9,
2412
  "rubric_adaptive": 42.2,
 
2413
  "text_rendering": 39.6,
2414
  "visual_reference_evaluation": 32.5
2415
  },
@@ -2433,6 +2575,7 @@
2433
  "physical_plausibility": 211,
2434
  "prompt_faithfulness": 273,
2435
  "rubric_adaptive": 273,
 
2436
  "text_rendering": 208,
2437
  "visual_reference_evaluation": 222
2438
  },
@@ -2444,6 +2587,7 @@
2444
  "physical_plausibility": 63.7,
2445
  "prompt_faithfulness": 35.2,
2446
  "rubric_adaptive": 38.4,
 
2447
  "text_rendering": 28.5,
2448
  "visual_reference_evaluation": 30.7
2449
  },
@@ -2467,6 +2611,7 @@
2467
  "physical_plausibility": 202,
2468
  "prompt_faithfulness": 273,
2469
  "rubric_adaptive": 273,
 
2470
  "text_rendering": 212,
2471
  "visual_reference_evaluation": 222
2472
  },
@@ -2478,6 +2623,7 @@
2478
  "physical_plausibility": 64.5,
2479
  "prompt_faithfulness": 34.8,
2480
  "rubric_adaptive": 37.4,
 
2481
  "text_rendering": 24.5,
2482
  "visual_reference_evaluation": 31.3
2483
  },
@@ -2501,6 +2647,7 @@
2501
  "physical_plausibility": 240,
2502
  "prompt_faithfulness": 273,
2503
  "rubric_adaptive": 273,
 
2504
  "text_rendering": 198,
2505
  "visual_reference_evaluation": 222
2506
  },
@@ -2512,6 +2659,7 @@
2512
  "physical_plausibility": 39.8,
2513
  "prompt_faithfulness": 16.3,
2514
  "rubric_adaptive": 20.3,
 
2515
  "text_rendering": 2.8,
2516
  "visual_reference_evaluation": 16.9
2517
  },
@@ -2535,6 +2683,7 @@
2535
  "physical_plausibility": 212,
2536
  "prompt_faithfulness": 273,
2537
  "rubric_adaptive": 273,
 
2538
  "text_rendering": 209,
2539
  "visual_reference_evaluation": 222
2540
  },
@@ -2546,6 +2695,7 @@
2546
  "physical_plausibility": 43.9,
2547
  "prompt_faithfulness": 15.8,
2548
  "rubric_adaptive": 19.9,
 
2549
  "text_rendering": 2.5,
2550
  "visual_reference_evaluation": 15.7
2551
  },
@@ -2569,6 +2719,7 @@
2569
  "physical_plausibility": 215,
2570
  "prompt_faithfulness": 272,
2571
  "rubric_adaptive": 273,
 
2572
  "text_rendering": 202,
2573
  "visual_reference_evaluation": 221
2574
  },
@@ -2580,6 +2731,7 @@
2580
  "physical_plausibility": 39.5,
2581
  "prompt_faithfulness": 10.0,
2582
  "rubric_adaptive": 15.1,
 
2583
  "text_rendering": 1.6,
2584
  "visual_reference_evaluation": 9.5
2585
  },
@@ -2603,6 +2755,7 @@
2603
  "physical_plausibility": 216,
2604
  "prompt_faithfulness": 273,
2605
  "rubric_adaptive": 273,
 
2606
  "text_rendering": 193,
2607
  "visual_reference_evaluation": 222
2608
  },
@@ -2614,6 +2767,7 @@
2614
  "physical_plausibility": 34.9,
2615
  "prompt_faithfulness": 12.8,
2616
  "rubric_adaptive": 14.8,
 
2617
  "text_rendering": 1.9,
2618
  "visual_reference_evaluation": 12.8
2619
  },
@@ -2637,6 +2791,7 @@
2637
  "physical_plausibility": 227,
2638
  "prompt_faithfulness": 273,
2639
  "rubric_adaptive": 273,
 
2640
  "text_rendering": 225,
2641
  "visual_reference_evaluation": 252
2642
  },
@@ -2648,6 +2803,7 @@
2648
  "physical_plausibility": 17.6,
2649
  "prompt_faithfulness": 5.1,
2650
  "rubric_adaptive": 6.7,
 
2651
  "text_rendering": 1.0,
2652
  "visual_reference_evaluation": 5.1
2653
  },
@@ -2673,6 +2829,7 @@
2673
  "physical_plausibility": 23,
2674
  "prompt_faithfulness": 30,
2675
  "rubric_adaptive": 30,
 
2676
  "text_rendering": 23,
2677
  "visual_reference_evaluation": 22
2678
  },
@@ -2684,6 +2841,7 @@
2684
  "physical_plausibility": 78.3,
2685
  "prompt_faithfulness": 66.1,
2686
  "rubric_adaptive": 69.0,
 
2687
  "text_rendering": 76.1,
2688
  "visual_reference_evaluation": 65.9
2689
  },
@@ -2707,6 +2865,7 @@
2707
  "physical_plausibility": 25,
2708
  "prompt_faithfulness": 30,
2709
  "rubric_adaptive": 30,
 
2710
  "text_rendering": 20,
2711
  "visual_reference_evaluation": 21
2712
  },
@@ -2718,6 +2877,7 @@
2718
  "physical_plausibility": 78.0,
2719
  "prompt_faithfulness": 52.2,
2720
  "rubric_adaptive": 55.4,
 
2721
  "text_rendering": 60.8,
2722
  "visual_reference_evaluation": 51.6
2723
  },
@@ -2741,6 +2901,7 @@
2741
  "physical_plausibility": 23,
2742
  "prompt_faithfulness": 30,
2743
  "rubric_adaptive": 30,
 
2744
  "text_rendering": 20,
2745
  "visual_reference_evaluation": 24
2746
  },
@@ -2752,6 +2913,7 @@
2752
  "physical_plausibility": 63.8,
2753
  "prompt_faithfulness": 54.4,
2754
  "rubric_adaptive": 56.2,
 
2755
  "text_rendering": 66.7,
2756
  "visual_reference_evaluation": 50.7
2757
  },
@@ -2775,6 +2937,7 @@
2775
  "physical_plausibility": 23,
2776
  "prompt_faithfulness": 30,
2777
  "rubric_adaptive": 30,
 
2778
  "text_rendering": 19,
2779
  "visual_reference_evaluation": 24
2780
  },
@@ -2786,6 +2949,7 @@
2786
  "physical_plausibility": 58.0,
2787
  "prompt_faithfulness": 46.7,
2788
  "rubric_adaptive": 54.6,
 
2789
  "text_rendering": 66.7,
2790
  "visual_reference_evaluation": 50.0
2791
  },
@@ -2809,6 +2973,7 @@
2809
  "physical_plausibility": 21,
2810
  "prompt_faithfulness": 30,
2811
  "rubric_adaptive": 30,
 
2812
  "text_rendering": 21,
2813
  "visual_reference_evaluation": 24
2814
  },
@@ -2820,6 +2985,7 @@
2820
  "physical_plausibility": 60.3,
2821
  "prompt_faithfulness": 45.6,
2822
  "rubric_adaptive": 47.7,
 
2823
  "text_rendering": 68.3,
2824
  "visual_reference_evaluation": 40.3
2825
  },
@@ -2843,6 +3009,7 @@
2843
  "physical_plausibility": 23,
2844
  "prompt_faithfulness": 30,
2845
  "rubric_adaptive": 30,
 
2846
  "text_rendering": 19,
2847
  "visual_reference_evaluation": 24
2848
  },
@@ -2854,6 +3021,7 @@
2854
  "physical_plausibility": 62.3,
2855
  "prompt_faithfulness": 41.1,
2856
  "rubric_adaptive": 46.3,
 
2857
  "text_rendering": 57.0,
2858
  "visual_reference_evaluation": 43.1
2859
  },
@@ -2877,6 +3045,7 @@
2877
  "physical_plausibility": 22,
2878
  "prompt_faithfulness": 30,
2879
  "rubric_adaptive": 30,
 
2880
  "text_rendering": 20,
2881
  "visual_reference_evaluation": 21
2882
  },
@@ -2888,6 +3057,7 @@
2888
  "physical_plausibility": 68.2,
2889
  "prompt_faithfulness": 37.8,
2890
  "rubric_adaptive": 42.2,
 
2891
  "text_rendering": 35.0,
2892
  "visual_reference_evaluation": 32.5
2893
  },
@@ -2911,6 +3081,7 @@
2911
  "physical_plausibility": 24,
2912
  "prompt_faithfulness": 29,
2913
  "rubric_adaptive": 30,
 
2914
  "text_rendering": 17,
2915
  "visual_reference_evaluation": 21
2916
  },
@@ -2922,6 +3093,7 @@
2922
  "physical_plausibility": 64.6,
2923
  "prompt_faithfulness": 40.8,
2924
  "rubric_adaptive": 41.6,
 
2925
  "text_rendering": 47.1,
2926
  "visual_reference_evaluation": 37.3
2927
  },
@@ -2945,6 +3117,7 @@
2945
  "physical_plausibility": 29,
2946
  "prompt_faithfulness": 30,
2947
  "rubric_adaptive": 30,
 
2948
  "text_rendering": 16,
2949
  "visual_reference_evaluation": 21
2950
  },
@@ -2956,6 +3129,7 @@
2956
  "physical_plausibility": 37.9,
2957
  "prompt_faithfulness": 15.6,
2958
  "rubric_adaptive": 22.8,
 
2959
  "text_rendering": 8.3,
2960
  "visual_reference_evaluation": 18.3
2961
  },
@@ -2979,6 +3153,7 @@
2979
  "physical_plausibility": 23,
2980
  "prompt_faithfulness": 30,
2981
  "rubric_adaptive": 30,
 
2982
  "text_rendering": 19,
2983
  "visual_reference_evaluation": 21
2984
  },
@@ -2990,6 +3165,7 @@
2990
  "physical_plausibility": 44.9,
2991
  "prompt_faithfulness": 12.8,
2992
  "rubric_adaptive": 19.0,
 
2993
  "text_rendering": 7.0,
2994
  "visual_reference_evaluation": 7.9
2995
  },
@@ -3013,6 +3189,7 @@
3013
  "physical_plausibility": 23,
3014
  "prompt_faithfulness": 30,
3015
  "rubric_adaptive": 30,
 
3016
  "text_rendering": 21,
3017
  "visual_reference_evaluation": 21
3018
  },
@@ -3024,6 +3201,7 @@
3024
  "physical_plausibility": 34.1,
3025
  "prompt_faithfulness": 14.4,
3026
  "rubric_adaptive": 22.0,
 
3027
  "text_rendering": 2.4,
3028
  "visual_reference_evaluation": 15.1
3029
  },
@@ -3047,6 +3225,7 @@
3047
  "physical_plausibility": 27,
3048
  "prompt_faithfulness": 30,
3049
  "rubric_adaptive": 30,
 
3050
  "text_rendering": 18,
3051
  "visual_reference_evaluation": 21
3052
  },
@@ -3058,6 +3237,7 @@
3058
  "physical_plausibility": 31.5,
3059
  "prompt_faithfulness": 7.8,
3060
  "rubric_adaptive": 10.2,
 
3061
  "text_rendering": 5.6,
3062
  "visual_reference_evaluation": 9.5
3063
  },
@@ -3081,6 +3261,7 @@
3081
  "physical_plausibility": 28,
3082
  "prompt_faithfulness": 30,
3083
  "rubric_adaptive": 30,
 
3084
  "text_rendering": 20,
3085
  "visual_reference_evaluation": 24
3086
  },
@@ -3092,6 +3273,7 @@
3092
  "physical_plausibility": 31.5,
3093
  "prompt_faithfulness": 3.9,
3094
  "rubric_adaptive": 7.9,
 
3095
  "text_rendering": 8.3,
3096
  "visual_reference_evaluation": 0.7
3097
  },
@@ -3117,6 +3299,7 @@
3117
  "physical_plausibility": 259,
3118
  "prompt_faithfulness": 411,
3119
  "rubric_adaptive": 411,
 
3120
  "text_rendering": 393,
3121
  "visual_reference_evaluation": 299
3122
  },
@@ -3128,6 +3311,7 @@
3128
  "physical_plausibility": 86.5,
3129
  "prompt_faithfulness": 73.7,
3130
  "rubric_adaptive": 73.5,
 
3131
  "text_rendering": 76.3,
3132
  "visual_reference_evaluation": 70.7
3133
  },
@@ -3151,6 +3335,7 @@
3151
  "physical_plausibility": 320,
3152
  "prompt_faithfulness": 411,
3153
  "rubric_adaptive": 411,
 
3154
  "text_rendering": 385,
3155
  "visual_reference_evaluation": 299
3156
  },
@@ -3162,6 +3347,7 @@
3162
  "physical_plausibility": 85.3,
3163
  "prompt_faithfulness": 64.7,
3164
  "rubric_adaptive": 65.4,
 
3165
  "text_rendering": 65.2,
3166
  "visual_reference_evaluation": 62.5
3167
  },
@@ -3185,6 +3371,7 @@
3185
  "physical_plausibility": 270,
3186
  "prompt_faithfulness": 404,
3187
  "rubric_adaptive": 404,
 
3188
  "text_rendering": 388,
3189
  "visual_reference_evaluation": 299
3190
  },
@@ -3196,6 +3383,7 @@
3196
  "physical_plausibility": 82.8,
3197
  "prompt_faithfulness": 64.4,
3198
  "rubric_adaptive": 64.2,
 
3199
  "text_rendering": 61.0,
3200
  "visual_reference_evaluation": 61.2
3201
  },
@@ -3219,6 +3407,7 @@
3219
  "physical_plausibility": 251,
3220
  "prompt_faithfulness": 408,
3221
  "rubric_adaptive": 408,
 
3222
  "text_rendering": 391,
3223
  "visual_reference_evaluation": 303
3224
  },
@@ -3230,6 +3419,7 @@
3230
  "physical_plausibility": 80.9,
3231
  "prompt_faithfulness": 51.7,
3232
  "rubric_adaptive": 54.0,
 
3233
  "text_rendering": 54.9,
3234
  "visual_reference_evaluation": 46.3
3235
  },
@@ -3253,6 +3443,7 @@
3253
  "physical_plausibility": 253,
3254
  "prompt_faithfulness": 411,
3255
  "rubric_adaptive": 411,
 
3256
  "text_rendering": 394,
3257
  "visual_reference_evaluation": 307
3258
  },
@@ -3264,6 +3455,7 @@
3264
  "physical_plausibility": 78.2,
3265
  "prompt_faithfulness": 49.2,
3266
  "rubric_adaptive": 51.5,
 
3267
  "text_rendering": 53.2,
3268
  "visual_reference_evaluation": 43.4
3269
  },
@@ -3287,6 +3479,7 @@
3287
  "physical_plausibility": 291,
3288
  "prompt_faithfulness": 411,
3289
  "rubric_adaptive": 411,
 
3290
  "text_rendering": 399,
3291
  "visual_reference_evaluation": 306
3292
  },
@@ -3298,6 +3491,7 @@
3298
  "physical_plausibility": 69.6,
3299
  "prompt_faithfulness": 45.6,
3300
  "rubric_adaptive": 48.5,
 
3301
  "text_rendering": 49.1,
3302
  "visual_reference_evaluation": 37.5
3303
  },
@@ -3321,6 +3515,7 @@
3321
  "physical_plausibility": 297,
3322
  "prompt_faithfulness": 411,
3323
  "rubric_adaptive": 411,
 
3324
  "text_rendering": 396,
3325
  "visual_reference_evaluation": 298
3326
  },
@@ -3332,6 +3527,7 @@
3332
  "physical_plausibility": 70.9,
3333
  "prompt_faithfulness": 38.2,
3334
  "rubric_adaptive": 42.4,
 
3335
  "text_rendering": 36.3,
3336
  "visual_reference_evaluation": 33.9
3337
  },
@@ -3355,6 +3551,7 @@
3355
  "physical_plausibility": 293,
3356
  "prompt_faithfulness": 411,
3357
  "rubric_adaptive": 411,
 
3358
  "text_rendering": 392,
3359
  "visual_reference_evaluation": 299
3360
  },
@@ -3366,6 +3563,7 @@
3366
  "physical_plausibility": 72.9,
3367
  "prompt_faithfulness": 34.3,
3368
  "rubric_adaptive": 37.4,
 
3369
  "text_rendering": 26.0,
3370
  "visual_reference_evaluation": 30.5
3371
  },
@@ -3389,6 +3587,7 @@
3389
  "physical_plausibility": 354,
3390
  "prompt_faithfulness": 411,
3391
  "rubric_adaptive": 411,
 
3392
  "text_rendering": 402,
3393
  "visual_reference_evaluation": 298
3394
  },
@@ -3400,6 +3599,7 @@
3400
  "physical_plausibility": 44.4,
3401
  "prompt_faithfulness": 16.7,
3402
  "rubric_adaptive": 20.9,
 
3403
  "text_rendering": 10.9,
3404
  "visual_reference_evaluation": 15.8
3405
  },
@@ -3423,6 +3623,7 @@
3423
  "physical_plausibility": 297,
3424
  "prompt_faithfulness": 411,
3425
  "rubric_adaptive": 411,
 
3426
  "text_rendering": 400,
3427
  "visual_reference_evaluation": 298
3428
  },
@@ -3434,6 +3635,7 @@
3434
  "physical_plausibility": 49.6,
3435
  "prompt_faithfulness": 14.1,
3436
  "rubric_adaptive": 18.8,
 
3437
  "text_rendering": 7.2,
3438
  "visual_reference_evaluation": 12.8
3439
  },
@@ -3457,6 +3659,7 @@
3457
  "physical_plausibility": 289,
3458
  "prompt_faithfulness": 410,
3459
  "rubric_adaptive": 411,
 
3460
  "text_rendering": 391,
3461
  "visual_reference_evaluation": 297
3462
  },
@@ -3468,6 +3671,7 @@
3468
  "physical_plausibility": 45.8,
3469
  "prompt_faithfulness": 10.1,
3470
  "rubric_adaptive": 15.3,
 
3471
  "text_rendering": 3.9,
3472
  "visual_reference_evaluation": 9.3
3473
  },
@@ -3491,6 +3695,7 @@
3491
  "physical_plausibility": 319,
3492
  "prompt_faithfulness": 411,
3493
  "rubric_adaptive": 411,
 
3494
  "text_rendering": 390,
3495
  "visual_reference_evaluation": 298
3496
  },
@@ -3502,6 +3707,7 @@
3502
  "physical_plausibility": 35.9,
3503
  "prompt_faithfulness": 10.3,
3504
  "rubric_adaptive": 13.7,
 
3505
  "text_rendering": 3.4,
3506
  "visual_reference_evaluation": 9.7
3507
  },
@@ -3525,6 +3731,7 @@
3525
  "physical_plausibility": 337,
3526
  "prompt_faithfulness": 411,
3527
  "rubric_adaptive": 411,
 
3528
  "text_rendering": 397,
3529
  "visual_reference_evaluation": 369
3530
  },
@@ -3536,6 +3743,7 @@
3536
  "physical_plausibility": 14.3,
3537
  "prompt_faithfulness": 2.8,
3538
  "rubric_adaptive": 4.7,
 
3539
  "text_rendering": 1.0,
3540
  "visual_reference_evaluation": 3.3
3541
  },
@@ -3561,6 +3769,7 @@
3561
  "physical_plausibility": 10,
3562
  "prompt_faithfulness": 38,
3563
  "rubric_adaptive": 38,
 
3564
  "text_rendering": 35,
3565
  "visual_reference_evaluation": 25
3566
  },
@@ -3572,6 +3781,7 @@
3572
  "physical_plausibility": 85.0,
3573
  "prompt_faithfulness": 63.2,
3574
  "rubric_adaptive": 57.9,
 
3575
  "text_rendering": 68.1,
3576
  "visual_reference_evaluation": 56.7
3577
  },
@@ -3595,6 +3805,7 @@
3595
  "physical_plausibility": 29,
3596
  "prompt_faithfulness": 38,
3597
  "rubric_adaptive": 38,
 
3598
  "text_rendering": 36,
3599
  "visual_reference_evaluation": 25
3600
  },
@@ -3606,6 +3817,7 @@
3606
  "physical_plausibility": 86.8,
3607
  "prompt_faithfulness": 53.9,
3608
  "rubric_adaptive": 48.5,
 
3609
  "text_rendering": 60.6,
3610
  "visual_reference_evaluation": 45.3
3611
  },
@@ -3629,6 +3841,7 @@
3629
  "physical_plausibility": 16,
3630
  "prompt_faithfulness": 38,
3631
  "rubric_adaptive": 38,
 
3632
  "text_rendering": 37,
3633
  "visual_reference_evaluation": 27
3634
  },
@@ -3640,6 +3853,7 @@
3640
  "physical_plausibility": 89.6,
3641
  "prompt_faithfulness": 56.1,
3642
  "rubric_adaptive": 53.6,
 
3643
  "text_rendering": 58.1,
3644
  "visual_reference_evaluation": 46.9
3645
  },
@@ -3663,6 +3877,7 @@
3663
  "physical_plausibility": 8,
3664
  "prompt_faithfulness": 38,
3665
  "rubric_adaptive": 38,
 
3666
  "text_rendering": 38,
3667
  "visual_reference_evaluation": 27
3668
  },
@@ -3674,6 +3889,7 @@
3674
  "physical_plausibility": 56.2,
3675
  "prompt_faithfulness": 36.0,
3676
  "rubric_adaptive": 32.7,
 
3677
  "text_rendering": 40.4,
3678
  "visual_reference_evaluation": 20.4
3679
  },
@@ -3697,6 +3913,7 @@
3697
  "physical_plausibility": 11,
3698
  "prompt_faithfulness": 38,
3699
  "rubric_adaptive": 38,
 
3700
  "text_rendering": 35,
3701
  "visual_reference_evaluation": 27
3702
  },
@@ -3708,6 +3925,7 @@
3708
  "physical_plausibility": 77.3,
3709
  "prompt_faithfulness": 32.5,
3710
  "rubric_adaptive": 29.2,
 
3711
  "text_rendering": 35.2,
3712
  "visual_reference_evaluation": 19.1
3713
  },
@@ -3731,6 +3949,7 @@
3731
  "physical_plausibility": 16,
3732
  "prompt_faithfulness": 38,
3733
  "rubric_adaptive": 38,
 
3734
  "text_rendering": 37,
3735
  "visual_reference_evaluation": 27
3736
  },
@@ -3742,6 +3961,7 @@
3742
  "physical_plausibility": 55.2,
3743
  "prompt_faithfulness": 35.1,
3744
  "rubric_adaptive": 27.5,
 
3745
  "text_rendering": 39.6,
3746
  "visual_reference_evaluation": 9.3
3747
  },
@@ -3765,6 +3985,7 @@
3765
  "physical_plausibility": 23,
3766
  "prompt_faithfulness": 38,
3767
  "rubric_adaptive": 38,
 
3768
  "text_rendering": 35,
3769
  "visual_reference_evaluation": 25
3770
  },
@@ -3776,6 +3997,7 @@
3776
  "physical_plausibility": 75.4,
3777
  "prompt_faithfulness": 22.4,
3778
  "rubric_adaptive": 21.2,
 
3779
  "text_rendering": 19.0,
3780
  "visual_reference_evaluation": 16.7
3781
  },
@@ -3799,6 +4021,7 @@
3799
  "physical_plausibility": 20,
3800
  "prompt_faithfulness": 38,
3801
  "rubric_adaptive": 38,
 
3802
  "text_rendering": 38,
3803
  "visual_reference_evaluation": 25
3804
  },
@@ -3810,6 +4033,7 @@
3810
  "physical_plausibility": 55.8,
3811
  "prompt_faithfulness": 22.4,
3812
  "rubric_adaptive": 22.0,
 
3813
  "text_rendering": 23.2,
3814
  "visual_reference_evaluation": 9.3
3815
  },
@@ -3833,6 +4057,7 @@
3833
  "physical_plausibility": 28,
3834
  "prompt_faithfulness": 38,
3835
  "rubric_adaptive": 38,
 
3836
  "text_rendering": 38,
3837
  "visual_reference_evaluation": 25
3838
  },
@@ -3844,6 +4069,7 @@
3844
  "physical_plausibility": 28.0,
3845
  "prompt_faithfulness": 3.5,
3846
  "rubric_adaptive": 5.7,
 
3847
  "text_rendering": 3.1,
3848
  "visual_reference_evaluation": 4.0
3849
  },
@@ -3867,6 +4093,7 @@
3867
  "physical_plausibility": 23,
3868
  "prompt_faithfulness": 38,
3869
  "rubric_adaptive": 38,
 
3870
  "text_rendering": 38,
3871
  "visual_reference_evaluation": 25
3872
  },
@@ -3878,6 +4105,7 @@
3878
  "physical_plausibility": 15.2,
3879
  "prompt_faithfulness": 2.6,
3880
  "rubric_adaptive": 3.3,
 
3881
  "text_rendering": 1.3,
3882
  "visual_reference_evaluation": 1.3
3883
  },
@@ -3901,6 +4129,7 @@
3901
  "physical_plausibility": 20,
3902
  "prompt_faithfulness": 38,
3903
  "rubric_adaptive": 38,
 
3904
  "text_rendering": 38,
3905
  "visual_reference_evaluation": 25
3906
  },
@@ -3912,6 +4141,7 @@
3912
  "physical_plausibility": 28.3,
3913
  "prompt_faithfulness": 1.8,
3914
  "rubric_adaptive": 3.8,
 
3915
  "text_rendering": 0.9,
3916
  "visual_reference_evaluation": 4.0
3917
  },
@@ -3935,6 +4165,7 @@
3935
  "physical_plausibility": 26,
3936
  "prompt_faithfulness": 38,
3937
  "rubric_adaptive": 38,
 
3938
  "text_rendering": 34,
3939
  "visual_reference_evaluation": 25
3940
  },
@@ -3946,6 +4177,7 @@
3946
  "physical_plausibility": 18.6,
3947
  "prompt_faithfulness": 0.4,
3948
  "rubric_adaptive": 2.2,
 
3949
  "text_rendering": 0.0,
3950
  "visual_reference_evaluation": 0.0
3951
  },
@@ -3969,6 +4201,7 @@
3969
  "physical_plausibility": 26,
3970
  "prompt_faithfulness": 38,
3971
  "rubric_adaptive": 38,
 
3972
  "text_rendering": 36,
3973
  "visual_reference_evaluation": 25
3974
  },
@@ -3980,6 +4213,7 @@
3980
  "physical_plausibility": 6.4,
3981
  "prompt_faithfulness": 0.4,
3982
  "rubric_adaptive": 1.2,
 
3983
  "text_rendering": 0.0,
3984
  "visual_reference_evaluation": 0.7
3985
  },
@@ -4005,6 +4239,7 @@
4005
  "physical_plausibility": 24,
4006
  "prompt_faithfulness": 56,
4007
  "rubric_adaptive": 56,
 
4008
  "text_rendering": 53,
4009
  "visual_reference_evaluation": 46
4010
  },
@@ -4016,6 +4251,7 @@
4016
  "physical_plausibility": 86.8,
4017
  "prompt_faithfulness": 69.6,
4018
  "rubric_adaptive": 64.9,
 
4019
  "text_rendering": 77.0,
4020
  "visual_reference_evaluation": 64.9
4021
  },
@@ -4039,6 +4275,7 @@
4039
  "physical_plausibility": 33,
4040
  "prompt_faithfulness": 56,
4041
  "rubric_adaptive": 56,
 
4042
  "text_rendering": 53,
4043
  "visual_reference_evaluation": 46
4044
  },
@@ -4050,6 +4287,7 @@
4050
  "physical_plausibility": 81.8,
4051
  "prompt_faithfulness": 59.5,
4052
  "rubric_adaptive": 58.9,
 
4053
  "text_rendering": 60.1,
4054
  "visual_reference_evaluation": 51.1
4055
  },
@@ -4073,6 +4311,7 @@
4073
  "physical_plausibility": 50,
4074
  "prompt_faithfulness": 56,
4075
  "rubric_adaptive": 56,
 
4076
  "text_rendering": 50,
4077
  "visual_reference_evaluation": 46
4078
  },
@@ -4084,6 +4323,7 @@
4084
  "physical_plausibility": 79.7,
4085
  "prompt_faithfulness": 59.4,
4086
  "rubric_adaptive": 52.9,
 
4087
  "text_rendering": 59.0,
4088
  "visual_reference_evaluation": 49.6
4089
  },
@@ -4107,6 +4347,7 @@
4107
  "physical_plausibility": 25,
4108
  "prompt_faithfulness": 56,
4109
  "rubric_adaptive": 56,
 
4110
  "text_rendering": 53,
4111
  "visual_reference_evaluation": 46
4112
  },
@@ -4118,6 +4359,7 @@
4118
  "physical_plausibility": 75.3,
4119
  "prompt_faithfulness": 45.1,
4120
  "rubric_adaptive": 43.3,
 
4121
  "text_rendering": 51.9,
4122
  "visual_reference_evaluation": 34.1
4123
  },
@@ -4141,6 +4383,7 @@
4141
  "physical_plausibility": 19,
4142
  "prompt_faithfulness": 56,
4143
  "rubric_adaptive": 56,
 
4144
  "text_rendering": 55,
4145
  "visual_reference_evaluation": 46
4146
  },
@@ -4152,6 +4395,7 @@
4152
  "physical_plausibility": 71.1,
4153
  "prompt_faithfulness": 45.5,
4154
  "rubric_adaptive": 44.0,
 
4155
  "text_rendering": 51.2,
4156
  "visual_reference_evaluation": 35.9
4157
  },
@@ -4175,6 +4419,7 @@
4175
  "physical_plausibility": 31,
4176
  "prompt_faithfulness": 56,
4177
  "rubric_adaptive": 56,
 
4178
  "text_rendering": 53,
4179
  "visual_reference_evaluation": 46
4180
  },
@@ -4186,6 +4431,7 @@
4186
  "physical_plausibility": 66.7,
4187
  "prompt_faithfulness": 42.3,
4188
  "rubric_adaptive": 39.8,
 
4189
  "text_rendering": 49.1,
4190
  "visual_reference_evaluation": 25.7
4191
  },
@@ -4209,6 +4455,7 @@
4209
  "physical_plausibility": 34,
4210
  "prompt_faithfulness": 56,
4211
  "rubric_adaptive": 56,
 
4212
  "text_rendering": 55,
4213
  "visual_reference_evaluation": 46
4214
  },
@@ -4220,6 +4467,7 @@
4220
  "physical_plausibility": 68.6,
4221
  "prompt_faithfulness": 31.8,
4222
  "rubric_adaptive": 34.3,
 
4223
  "text_rendering": 31.5,
4224
  "visual_reference_evaluation": 24.6
4225
  },
@@ -4243,6 +4491,7 @@
4243
  "physical_plausibility": 38,
4244
  "prompt_faithfulness": 56,
4245
  "rubric_adaptive": 56,
 
4246
  "text_rendering": 54,
4247
  "visual_reference_evaluation": 46
4248
  },
@@ -4254,6 +4503,7 @@
4254
  "physical_plausibility": 64.9,
4255
  "prompt_faithfulness": 27.1,
4256
  "rubric_adaptive": 26.6,
 
4257
  "text_rendering": 19.1,
4258
  "visual_reference_evaluation": 21.7
4259
  },
@@ -4277,6 +4527,7 @@
4277
  "physical_plausibility": 46,
4278
  "prompt_faithfulness": 56,
4279
  "rubric_adaptive": 56,
 
4280
  "text_rendering": 55,
4281
  "visual_reference_evaluation": 46
4282
  },
@@ -4288,6 +4539,7 @@
4288
  "physical_plausibility": 35.5,
4289
  "prompt_faithfulness": 8.0,
4290
  "rubric_adaptive": 13.1,
 
4291
  "text_rendering": 5.5,
4292
  "visual_reference_evaluation": 9.4
4293
  },
@@ -4311,6 +4563,7 @@
4311
  "physical_plausibility": 39,
4312
  "prompt_faithfulness": 56,
4313
  "rubric_adaptive": 56,
 
4314
  "text_rendering": 52,
4315
  "visual_reference_evaluation": 46
4316
  },
@@ -4322,6 +4575,7 @@
4322
  "physical_plausibility": 32.1,
4323
  "prompt_faithfulness": 6.0,
4324
  "rubric_adaptive": 9.1,
 
4325
  "text_rendering": 3.8,
4326
  "visual_reference_evaluation": 6.2
4327
  },
@@ -4345,6 +4599,7 @@
4345
  "physical_plausibility": 33,
4346
  "prompt_faithfulness": 56,
4347
  "rubric_adaptive": 56,
 
4348
  "text_rendering": 55,
4349
  "visual_reference_evaluation": 46
4350
  },
@@ -4356,6 +4611,7 @@
4356
  "physical_plausibility": 29.3,
4357
  "prompt_faithfulness": 3.0,
4358
  "rubric_adaptive": 6.3,
 
4359
  "text_rendering": 1.5,
4360
  "visual_reference_evaluation": 4.3
4361
  },
@@ -4379,6 +4635,7 @@
4379
  "physical_plausibility": 41,
4380
  "prompt_faithfulness": 56,
4381
  "rubric_adaptive": 56,
 
4382
  "text_rendering": 51,
4383
  "visual_reference_evaluation": 46
4384
  },
@@ -4390,6 +4647,7 @@
4390
  "physical_plausibility": 14.6,
4391
  "prompt_faithfulness": 2.7,
4392
  "rubric_adaptive": 5.2,
 
4393
  "text_rendering": 0.3,
4394
  "visual_reference_evaluation": 3.6
4395
  },
@@ -4413,6 +4671,7 @@
4413
  "physical_plausibility": 46,
4414
  "prompt_faithfulness": 56,
4415
  "rubric_adaptive": 56,
 
4416
  "text_rendering": 53,
4417
  "visual_reference_evaluation": 47
4418
  },
@@ -4424,6 +4683,7 @@
4424
  "physical_plausibility": 14.5,
4425
  "prompt_faithfulness": 1.8,
4426
  "rubric_adaptive": 2.9,
 
4427
  "text_rendering": 0.0,
4428
  "visual_reference_evaluation": 2.1
4429
  },
@@ -4449,6 +4709,7 @@
4449
  "physical_plausibility": 27,
4450
  "prompt_faithfulness": 33,
4451
  "rubric_adaptive": 33,
 
4452
  "text_rendering": 21,
4453
  "visual_reference_evaluation": 25
4454
  },
@@ -4460,6 +4721,7 @@
4460
  "physical_plausibility": 78.4,
4461
  "prompt_faithfulness": 67.2,
4462
  "rubric_adaptive": 68.6,
 
4463
  "text_rendering": 78.6,
4464
  "visual_reference_evaluation": 66.0
4465
  },
@@ -4483,6 +4745,7 @@
4483
  "physical_plausibility": 28,
4484
  "prompt_faithfulness": 33,
4485
  "rubric_adaptive": 33,
 
4486
  "text_rendering": 14,
4487
  "visual_reference_evaluation": 25
4488
  },
@@ -4494,6 +4757,7 @@
4494
  "physical_plausibility": 84.5,
4495
  "prompt_faithfulness": 58.1,
4496
  "rubric_adaptive": 62.7,
 
4497
  "text_rendering": 63.1,
4498
  "visual_reference_evaluation": 51.3
4499
  },
@@ -4508,40 +4772,6 @@
4508
  "overall_9": 67.1,
4509
  "type": "Commercial"
4510
  },
4511
- {
4512
- "component_counts": {
4513
- "ai_naturalness": 33,
4514
- "checklist": 33,
4515
- "composition_and_aesthetics": 33,
4516
- "image_quality": 33,
4517
- "physical_plausibility": 28,
4518
- "prompt_faithfulness": 33,
4519
- "rubric_adaptive": 33,
4520
- "text_rendering": 15,
4521
- "visual_reference_evaluation": 30
4522
- },
4523
- "components": {
4524
- "ai_naturalness": 65.2,
4525
- "checklist": 59.8,
4526
- "composition_and_aesthetics": 75.8,
4527
- "image_quality": 75.8,
4528
- "physical_plausibility": 79.2,
4529
- "prompt_faithfulness": 51.5,
4530
- "rubric_adaptive": 58.2,
4531
- "text_rendering": 78.9,
4532
- "visual_reference_evaluation": 56.1
4533
- },
4534
- "coverage": 1.0,
4535
- "display_name": "Qwen-Image-2",
4536
- "missing_policy": "zero_fill",
4537
- "model_id": "qwen2",
4538
- "n_included": 33,
4539
- "n_scored": 33,
4540
- "n_total": 33,
4541
- "overall_10": 63.9,
4542
- "overall_9": 65.6,
4543
- "type": "Commercial"
4544
- },
4545
  {
4546
  "component_counts": {
4547
  "ai_naturalness": 33,
@@ -4551,6 +4781,7 @@
4551
  "physical_plausibility": 24,
4552
  "prompt_faithfulness": 33,
4553
  "rubric_adaptive": 33,
 
4554
  "text_rendering": 15,
4555
  "visual_reference_evaluation": 26
4556
  },
@@ -4562,6 +4793,7 @@
4562
  "physical_plausibility": 75.0,
4563
  "prompt_faithfulness": 60.6,
4564
  "rubric_adaptive": 64.4,
 
4565
  "text_rendering": 60.0,
4566
  "visual_reference_evaluation": 56.4
4567
  },
@@ -4585,6 +4817,7 @@
4585
  "physical_plausibility": 23,
4586
  "prompt_faithfulness": 31,
4587
  "rubric_adaptive": 31,
 
4588
  "text_rendering": 18,
4589
  "visual_reference_evaluation": 28
4590
  },
@@ -4596,6 +4829,7 @@
4596
  "physical_plausibility": 64.5,
4597
  "prompt_faithfulness": 59.7,
4598
  "rubric_adaptive": 62.2,
 
4599
  "text_rendering": 75.9,
4600
  "visual_reference_evaluation": 60.7
4601
  },
@@ -4610,6 +4844,42 @@
4610
  "overall_9": 65.2,
4611
  "type": "Commercial"
4612
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4613
  {
4614
  "component_counts": {
4615
  "ai_naturalness": 33,
@@ -4619,6 +4889,7 @@
4619
  "physical_plausibility": 26,
4620
  "prompt_faithfulness": 33,
4621
  "rubric_adaptive": 33,
 
4622
  "text_rendering": 15,
4623
  "visual_reference_evaluation": 30
4624
  },
@@ -4630,6 +4901,7 @@
4630
  "physical_plausibility": 75.0,
4631
  "prompt_faithfulness": 51.5,
4632
  "rubric_adaptive": 55.8,
 
4633
  "text_rendering": 75.6,
4634
  "visual_reference_evaluation": 54.4
4635
  },
@@ -4653,6 +4925,7 @@
4653
  "physical_plausibility": 24,
4654
  "prompt_faithfulness": 33,
4655
  "rubric_adaptive": 33,
 
4656
  "text_rendering": 19,
4657
  "visual_reference_evaluation": 30
4658
  },
@@ -4664,6 +4937,7 @@
4664
  "physical_plausibility": 72.2,
4665
  "prompt_faithfulness": 52.5,
4666
  "rubric_adaptive": 58.6,
 
4667
  "text_rendering": 61.4,
4668
  "visual_reference_evaluation": 51.1
4669
  },
@@ -4687,6 +4961,7 @@
4687
  "physical_plausibility": 23,
4688
  "prompt_faithfulness": 33,
4689
  "rubric_adaptive": 33,
 
4690
  "text_rendering": 14,
4691
  "visual_reference_evaluation": 25
4692
  },
@@ -4698,6 +4973,7 @@
4698
  "physical_plausibility": 70.3,
4699
  "prompt_faithfulness": 43.4,
4700
  "rubric_adaptive": 49.2,
 
4701
  "text_rendering": 35.7,
4702
  "visual_reference_evaluation": 34.7
4703
  },
@@ -4721,6 +4997,7 @@
4721
  "physical_plausibility": 31,
4722
  "prompt_faithfulness": 33,
4723
  "rubric_adaptive": 33,
 
4724
  "text_rendering": 13,
4725
  "visual_reference_evaluation": 25
4726
  },
@@ -4732,6 +5009,7 @@
4732
  "physical_plausibility": 55.9,
4733
  "prompt_faithfulness": 22.0,
4734
  "rubric_adaptive": 29.3,
 
4735
  "text_rendering": 3.8,
4736
  "visual_reference_evaluation": 28.7
4737
  },
@@ -4755,6 +5033,7 @@
4755
  "physical_plausibility": 24,
4756
  "prompt_faithfulness": 33,
4757
  "rubric_adaptive": 33,
 
4758
  "text_rendering": 16,
4759
  "visual_reference_evaluation": 26
4760
  },
@@ -4766,6 +5045,7 @@
4766
  "physical_plausibility": 61.8,
4767
  "prompt_faithfulness": 20.7,
4768
  "rubric_adaptive": 29.2,
 
4769
  "text_rendering": 4.2,
4770
  "visual_reference_evaluation": 22.4
4771
  },
@@ -4789,6 +5069,7 @@
4789
  "physical_plausibility": 23,
4790
  "prompt_faithfulness": 33,
4791
  "rubric_adaptive": 33,
 
4792
  "text_rendering": 16,
4793
  "visual_reference_evaluation": 25
4794
  },
@@ -4800,6 +5081,7 @@
4800
  "physical_plausibility": 58.7,
4801
  "prompt_faithfulness": 13.1,
4802
  "rubric_adaptive": 23.1,
 
4803
  "text_rendering": 2.1,
4804
  "visual_reference_evaluation": 13.3
4805
  },
@@ -4823,6 +5105,7 @@
4823
  "physical_plausibility": 30,
4824
  "prompt_faithfulness": 33,
4825
  "rubric_adaptive": 33,
 
4826
  "text_rendering": 13,
4827
  "visual_reference_evaluation": 25
4828
  },
@@ -4834,6 +5117,7 @@
4834
  "physical_plausibility": 43.9,
4835
  "prompt_faithfulness": 17.7,
4836
  "rubric_adaptive": 22.6,
 
4837
  "text_rendering": 1.3,
4838
  "visual_reference_evaluation": 18.0
4839
  },
@@ -4857,6 +5141,7 @@
4857
  "physical_plausibility": 28,
4858
  "prompt_faithfulness": 33,
4859
  "rubric_adaptive": 33,
 
4860
  "text_rendering": 15,
4861
  "visual_reference_evaluation": 26
4862
  },
@@ -4868,6 +5153,7 @@
4868
  "physical_plausibility": 51.2,
4869
  "prompt_faithfulness": 14.6,
4870
  "rubric_adaptive": 21.6,
 
4871
  "text_rendering": 3.3,
4872
  "visual_reference_evaluation": 15.4
4873
  },
@@ -4893,6 +5179,7 @@
4893
  "physical_plausibility": 117,
4894
  "prompt_faithfulness": 185,
4895
  "rubric_adaptive": 185,
 
4896
  "text_rendering": 164,
4897
  "visual_reference_evaluation": 150
4898
  },
@@ -4904,6 +5191,7 @@
4904
  "physical_plausibility": 86.8,
4905
  "prompt_faithfulness": 76.1,
4906
  "rubric_adaptive": 75.5,
 
4907
  "text_rendering": 79.8,
4908
  "visual_reference_evaluation": 74.4
4909
  },
@@ -4927,6 +5215,7 @@
4927
  "physical_plausibility": 142,
4928
  "prompt_faithfulness": 185,
4929
  "rubric_adaptive": 185,
 
4930
  "text_rendering": 158,
4931
  "visual_reference_evaluation": 150
4932
  },
@@ -4938,6 +5227,7 @@
4938
  "physical_plausibility": 86.9,
4939
  "prompt_faithfulness": 66.1,
4940
  "rubric_adaptive": 67.7,
 
4941
  "text_rendering": 70.6,
4942
  "visual_reference_evaluation": 65.6
4943
  },
@@ -4961,6 +5251,7 @@
4961
  "physical_plausibility": 123,
4962
  "prompt_faithfulness": 180,
4963
  "rubric_adaptive": 180,
 
4964
  "text_rendering": 157,
4965
  "visual_reference_evaluation": 151
4966
  },
@@ -4972,6 +5263,7 @@
4972
  "physical_plausibility": 80.2,
4973
  "prompt_faithfulness": 63.4,
4974
  "rubric_adaptive": 64.8,
 
4975
  "text_rendering": 64.2,
4976
  "visual_reference_evaluation": 61.9
4977
  },
@@ -4995,6 +5287,7 @@
4995
  "physical_plausibility": 119,
4996
  "prompt_faithfulness": 183,
4997
  "rubric_adaptive": 183,
 
4998
  "text_rendering": 148,
4999
  "visual_reference_evaluation": 154
5000
  },
@@ -5006,6 +5299,7 @@
5006
  "physical_plausibility": 76.8,
5007
  "prompt_faithfulness": 51.4,
5008
  "rubric_adaptive": 54.2,
 
5009
  "text_rendering": 58.6,
5010
  "visual_reference_evaluation": 47.3
5011
  },
@@ -5029,6 +5323,7 @@
5029
  "physical_plausibility": 119,
5030
  "prompt_faithfulness": 185,
5031
  "rubric_adaptive": 185,
 
5032
  "text_rendering": 148,
5033
  "visual_reference_evaluation": 156
5034
  },
@@ -5040,6 +5335,7 @@
5040
  "physical_plausibility": 73.7,
5041
  "prompt_faithfulness": 49.0,
5042
  "rubric_adaptive": 52.4,
 
5043
  "text_rendering": 54.8,
5044
  "visual_reference_evaluation": 44.4
5045
  },
@@ -5063,6 +5359,7 @@
5063
  "physical_plausibility": 134,
5064
  "prompt_faithfulness": 185,
5065
  "rubric_adaptive": 185,
 
5066
  "text_rendering": 154,
5067
  "visual_reference_evaluation": 156
5068
  },
@@ -5074,6 +5371,7 @@
5074
  "physical_plausibility": 68.7,
5075
  "prompt_faithfulness": 45.5,
5076
  "rubric_adaptive": 49.4,
 
5077
  "text_rendering": 51.9,
5078
  "visual_reference_evaluation": 41.6
5079
  },
@@ -5097,6 +5395,7 @@
5097
  "physical_plausibility": 136,
5098
  "prompt_faithfulness": 185,
5099
  "rubric_adaptive": 185,
 
5100
  "text_rendering": 148,
5101
  "visual_reference_evaluation": 150
5102
  },
@@ -5108,6 +5407,7 @@
5108
  "physical_plausibility": 67.2,
5109
  "prompt_faithfulness": 37.8,
5110
  "rubric_adaptive": 43.8,
 
5111
  "text_rendering": 37.3,
5112
  "visual_reference_evaluation": 38.8
5113
  },
@@ -5131,6 +5431,7 @@
5131
  "physical_plausibility": 129,
5132
  "prompt_faithfulness": 185,
5133
  "rubric_adaptive": 185,
 
5134
  "text_rendering": 153,
5135
  "visual_reference_evaluation": 150
5136
  },
@@ -5142,6 +5443,7 @@
5142
  "physical_plausibility": 74.2,
5143
  "prompt_faithfulness": 36.8,
5144
  "rubric_adaptive": 41.1,
 
5145
  "text_rendering": 26.6,
5146
  "visual_reference_evaluation": 37.7
5147
  },
@@ -5165,6 +5467,7 @@
5165
  "physical_plausibility": 156,
5166
  "prompt_faithfulness": 185,
5167
  "rubric_adaptive": 185,
 
5168
  "text_rendering": 153,
5169
  "visual_reference_evaluation": 150
5170
  },
@@ -5176,6 +5479,7 @@
5176
  "physical_plausibility": 47.1,
5177
  "prompt_faithfulness": 18.9,
5178
  "rubric_adaptive": 24.3,
 
5179
  "text_rendering": 10.7,
5180
  "visual_reference_evaluation": 20.4
5181
  },
@@ -5199,6 +5503,7 @@
5199
  "physical_plausibility": 134,
5200
  "prompt_faithfulness": 185,
5201
  "rubric_adaptive": 185,
 
5202
  "text_rendering": 157,
5203
  "visual_reference_evaluation": 150
5204
  },
@@ -5210,6 +5515,7 @@
5210
  "physical_plausibility": 50.1,
5211
  "prompt_faithfulness": 17.2,
5212
  "rubric_adaptive": 22.6,
 
5213
  "text_rendering": 9.1,
5214
  "visual_reference_evaluation": 20.2
5215
  },
@@ -5233,6 +5539,7 @@
5233
  "physical_plausibility": 131,
5234
  "prompt_faithfulness": 184,
5235
  "rubric_adaptive": 185,
 
5236
  "text_rendering": 148,
5237
  "visual_reference_evaluation": 149
5238
  },
@@ -5244,6 +5551,7 @@
5244
  "physical_plausibility": 50.0,
5245
  "prompt_faithfulness": 12.1,
5246
  "rubric_adaptive": 18.1,
 
5247
  "text_rendering": 3.7,
5248
  "visual_reference_evaluation": 15.7
5249
  },
@@ -5267,6 +5575,7 @@
5267
  "physical_plausibility": 148,
5268
  "prompt_faithfulness": 185,
5269
  "rubric_adaptive": 185,
 
5270
  "text_rendering": 149,
5271
  "visual_reference_evaluation": 150
5272
  },
@@ -5278,6 +5587,7 @@
5278
  "physical_plausibility": 35.8,
5279
  "prompt_faithfulness": 10.7,
5280
  "rubric_adaptive": 14.6,
 
5281
  "text_rendering": 1.7,
5282
  "visual_reference_evaluation": 12.8
5283
  },
@@ -5301,6 +5611,7 @@
5301
  "physical_plausibility": 151,
5302
  "prompt_faithfulness": 185,
5303
  "rubric_adaptive": 185,
 
5304
  "text_rendering": 159,
5305
  "visual_reference_evaluation": 169
5306
  },
@@ -5312,6 +5623,7 @@
5312
  "physical_plausibility": 22.0,
5313
  "prompt_faithfulness": 6.3,
5314
  "rubric_adaptive": 9.5,
 
5315
  "text_rendering": 1.2,
5316
  "visual_reference_evaluation": 6.3
5317
  },
 
9
  "physical_plausibility": 415,
10
  "prompt_faithfulness": 534,
11
  "rubric_adaptive": 534,
12
+ "text_reference_evaluation": 336,
13
  "text_rendering": 376,
14
  "visual_reference_evaluation": 439
15
  },
 
21
  "physical_plausibility": 73.8,
22
  "prompt_faithfulness": 68.5,
23
  "rubric_adaptive": 69.7,
24
+ "text_reference_evaluation": 55.3,
25
  "text_rendering": 73.2,
26
  "visual_reference_evaluation": 66.6
27
  },
 
45
  "physical_plausibility": 455,
46
  "prompt_faithfulness": 534,
47
  "rubric_adaptive": 534,
48
+ "text_reference_evaluation": 327,
49
  "text_rendering": 344,
50
  "visual_reference_evaluation": 437
51
  },
 
57
  "physical_plausibility": 76.2,
58
  "prompt_faithfulness": 62.2,
59
  "rubric_adaptive": 65.8,
60
+ "text_reference_evaluation": 49.5,
61
  "text_rendering": 66.4,
62
  "visual_reference_evaluation": 61.6
63
  },
 
81
  "physical_plausibility": 389,
82
  "prompt_faithfulness": 504,
83
  "rubric_adaptive": 504,
84
+ "text_reference_evaluation": 331,
85
  "text_rendering": 355,
86
  "visual_reference_evaluation": 417
87
  },
 
93
  "physical_plausibility": 69.9,
94
  "prompt_faithfulness": 61.3,
95
  "rubric_adaptive": 63.8,
96
+ "text_reference_evaluation": 46.6,
97
  "text_rendering": 61.7,
98
  "visual_reference_evaluation": 60.7
99
  },
 
117
  "physical_plausibility": 410,
118
  "prompt_faithfulness": 526,
119
  "rubric_adaptive": 526,
120
+ "text_reference_evaluation": 320,
121
  "text_rendering": 321,
122
  "visual_reference_evaluation": 439
123
  },
 
129
  "physical_plausibility": 70.2,
130
  "prompt_faithfulness": 50.8,
131
  "rubric_adaptive": 54.7,
132
+ "text_reference_evaluation": 37.6,
133
  "text_rendering": 56.9,
134
  "visual_reference_evaluation": 47.0
135
  },
 
153
  "physical_plausibility": 422,
154
  "prompt_faithfulness": 534,
155
  "rubric_adaptive": 534,
156
+ "text_reference_evaluation": 335,
157
  "text_rendering": 319,
158
  "visual_reference_evaluation": 448
159
  },
 
165
  "physical_plausibility": 65.3,
166
  "prompt_faithfulness": 47.5,
167
  "rubric_adaptive": 51.6,
168
+ "text_reference_evaluation": 33.8,
169
  "text_rendering": 52.0,
170
  "visual_reference_evaluation": 44.0
171
  },
 
189
  "physical_plausibility": 441,
190
  "prompt_faithfulness": 534,
191
  "rubric_adaptive": 534,
192
+ "text_reference_evaluation": 336,
193
  "text_rendering": 353,
194
  "visual_reference_evaluation": 446
195
  },
 
201
  "physical_plausibility": 62.1,
202
  "prompt_faithfulness": 46.1,
203
  "rubric_adaptive": 50.8,
204
+ "text_reference_evaluation": 29.1,
205
  "text_rendering": 48.6,
206
  "visual_reference_evaluation": 41.3
207
  },
 
225
  "physical_plausibility": 445,
226
  "prompt_faithfulness": 534,
227
  "rubric_adaptive": 534,
228
+ "text_reference_evaluation": 343,
229
  "text_rendering": 333,
230
  "visual_reference_evaluation": 436
231
  },
 
237
  "physical_plausibility": 64.5,
238
  "prompt_faithfulness": 41.4,
239
  "rubric_adaptive": 47.1,
240
+ "text_reference_evaluation": 23.7,
241
  "text_rendering": 37.8,
242
  "visual_reference_evaluation": 39.6
243
  },
 
261
  "physical_plausibility": 427,
262
  "prompt_faithfulness": 534,
263
  "rubric_adaptive": 534,
264
+ "text_reference_evaluation": 358,
265
  "text_rendering": 346,
266
  "visual_reference_evaluation": 437
267
  },
 
273
  "physical_plausibility": 63.3,
274
  "prompt_faithfulness": 39.6,
275
  "rubric_adaptive": 44.3,
276
+ "text_reference_evaluation": 18.3,
277
  "text_rendering": 29.3,
278
  "visual_reference_evaluation": 38.4
279
  },
 
297
  "physical_plausibility": 486,
298
  "prompt_faithfulness": 534,
299
  "rubric_adaptive": 534,
300
+ "text_reference_evaluation": 355,
301
  "text_rendering": 328,
302
  "visual_reference_evaluation": 435
303
  },
 
309
  "physical_plausibility": 48.5,
310
  "prompt_faithfulness": 25.9,
311
  "rubric_adaptive": 32.0,
312
+ "text_reference_evaluation": 7.9,
313
  "text_rendering": 11.4,
314
  "visual_reference_evaluation": 25.4
315
  },
 
333
  "physical_plausibility": 440,
334
  "prompt_faithfulness": 534,
335
  "rubric_adaptive": 534,
336
+ "text_reference_evaluation": 365,
337
  "text_rendering": 345,
338
  "visual_reference_evaluation": 436
339
  },
 
345
  "physical_plausibility": 51.2,
346
  "prompt_faithfulness": 23.0,
347
  "rubric_adaptive": 29.1,
348
+ "text_reference_evaluation": 6.6,
349
  "text_rendering": 8.7,
350
  "visual_reference_evaluation": 23.0
351
  },
 
369
  "physical_plausibility": 442,
370
  "prompt_faithfulness": 533,
371
  "rubric_adaptive": 534,
372
+ "text_reference_evaluation": 366,
373
  "text_rendering": 327,
374
  "visual_reference_evaluation": 434
375
  },
 
381
  "physical_plausibility": 48.1,
382
  "prompt_faithfulness": 17.0,
383
  "rubric_adaptive": 23.4,
384
+ "text_reference_evaluation": 3.4,
385
  "text_rendering": 4.5,
386
  "visual_reference_evaluation": 16.3
387
  },
 
405
  "physical_plausibility": 460,
406
  "prompt_faithfulness": 534,
407
  "rubric_adaptive": 534,
408
+ "text_reference_evaluation": 353,
409
  "text_rendering": 313,
410
  "visual_reference_evaluation": 435
411
  },
 
417
  "physical_plausibility": 41.4,
418
  "prompt_faithfulness": 18.4,
419
  "rubric_adaptive": 23.2,
420
+ "text_reference_evaluation": 3.4,
421
  "text_rendering": 4.1,
422
  "visual_reference_evaluation": 19.0
423
  },
 
441
  "physical_plausibility": 473,
442
  "prompt_faithfulness": 534,
443
  "rubric_adaptive": 534,
444
+ "text_reference_evaluation": 449,
445
  "text_rendering": 430,
446
  "visual_reference_evaluation": 506
447
  },
 
453
  "physical_plausibility": 17.3,
454
  "prompt_faithfulness": 6.0,
455
  "rubric_adaptive": 8.1,
456
+ "text_reference_evaluation": 0.9,
457
  "text_rendering": 0.9,
458
  "visual_reference_evaluation": 5.9
459
  },
 
479
  "physical_plausibility": 144,
480
  "prompt_faithfulness": 159,
481
  "rubric_adaptive": 159,
482
+ "text_reference_evaluation": 91,
483
  "text_rendering": 95,
484
  "visual_reference_evaluation": 121
485
  },
 
491
  "physical_plausibility": 75.3,
492
  "prompt_faithfulness": 68.3,
493
  "rubric_adaptive": 71.3,
494
+ "text_reference_evaluation": 50.4,
495
  "text_rendering": 70.9,
496
  "visual_reference_evaluation": 62.4
497
  },
 
515
  "physical_plausibility": 149,
516
  "prompt_faithfulness": 159,
517
  "rubric_adaptive": 159,
518
+ "text_reference_evaluation": 86,
519
  "text_rendering": 78,
520
  "visual_reference_evaluation": 121
521
  },
 
527
  "physical_plausibility": 77.9,
528
  "prompt_faithfulness": 63.1,
529
  "rubric_adaptive": 68.7,
530
+ "text_reference_evaluation": 47.1,
531
  "text_rendering": 61.3,
532
  "visual_reference_evaluation": 59.5
533
  },
 
551
  "physical_plausibility": 136,
552
  "prompt_faithfulness": 153,
553
  "rubric_adaptive": 153,
554
+ "text_reference_evaluation": 90,
555
  "text_rendering": 92,
556
  "visual_reference_evaluation": 121
557
  },
 
563
  "physical_plausibility": 71.3,
564
  "prompt_faithfulness": 63.8,
565
  "rubric_adaptive": 68.1,
566
+ "text_reference_evaluation": 48.0,
567
  "text_rendering": 64.7,
568
  "visual_reference_evaluation": 61.0
569
  },
 
587
  "physical_plausibility": 139,
588
  "prompt_faithfulness": 158,
589
  "rubric_adaptive": 158,
590
+ "text_reference_evaluation": 85,
591
  "text_rendering": 70,
592
  "visual_reference_evaluation": 124
593
  },
 
599
  "physical_plausibility": 71.0,
600
  "prompt_faithfulness": 54.7,
601
  "rubric_adaptive": 62.6,
602
+ "text_reference_evaluation": 45.7,
603
  "text_rendering": 65.5,
604
  "visual_reference_evaluation": 53.2
605
  },
 
623
  "physical_plausibility": 139,
624
  "prompt_faithfulness": 159,
625
  "rubric_adaptive": 159,
626
+ "text_reference_evaluation": 86,
627
  "text_rendering": 73,
628
  "visual_reference_evaluation": 126
629
  },
 
635
  "physical_plausibility": 69.3,
636
  "prompt_faithfulness": 54.8,
637
  "rubric_adaptive": 61.9,
638
+ "text_reference_evaluation": 41.3,
639
  "text_rendering": 60.7,
640
  "visual_reference_evaluation": 53.8
641
  },
 
659
  "physical_plausibility": 141,
660
  "prompt_faithfulness": 159,
661
  "rubric_adaptive": 159,
662
+ "text_reference_evaluation": 88,
663
  "text_rendering": 75,
664
  "visual_reference_evaluation": 121
665
  },
 
671
  "physical_plausibility": 70.7,
672
  "prompt_faithfulness": 51.2,
673
  "rubric_adaptive": 57.5,
674
+ "text_reference_evaluation": 32.0,
675
  "text_rendering": 49.6,
676
  "visual_reference_evaluation": 50.0
677
  },
 
695
  "physical_plausibility": 139,
696
  "prompt_faithfulness": 159,
697
  "rubric_adaptive": 159,
698
+ "text_reference_evaluation": 90,
699
  "text_rendering": 86,
700
  "visual_reference_evaluation": 126
701
  },
 
707
  "physical_plausibility": 70.0,
708
  "prompt_faithfulness": 53.6,
709
  "rubric_adaptive": 58.6,
710
+ "text_reference_evaluation": 35.4,
711
  "text_rendering": 54.5,
712
  "visual_reference_evaluation": 48.3
713
  },
 
731
  "physical_plausibility": 143,
732
  "prompt_faithfulness": 159,
733
  "rubric_adaptive": 159,
734
+ "text_reference_evaluation": 97,
735
  "text_rendering": 79,
736
  "visual_reference_evaluation": 121
737
  },
 
743
  "physical_plausibility": 68.1,
744
  "prompt_faithfulness": 44.5,
745
  "rubric_adaptive": 52.5,
746
+ "text_reference_evaluation": 16.2,
747
  "text_rendering": 20.8,
748
  "visual_reference_evaluation": 42.8
749
  },
 
767
  "physical_plausibility": 153,
768
  "prompt_faithfulness": 159,
769
  "rubric_adaptive": 159,
770
+ "text_reference_evaluation": 92,
771
  "text_rendering": 74,
772
  "visual_reference_evaluation": 121
773
  },
 
779
  "physical_plausibility": 60.1,
780
  "prompt_faithfulness": 38.4,
781
  "rubric_adaptive": 44.8,
782
+ "text_reference_evaluation": 16.1,
783
  "text_rendering": 21.2,
784
  "visual_reference_evaluation": 39.9
785
  },
 
803
  "physical_plausibility": 143,
804
  "prompt_faithfulness": 159,
805
  "rubric_adaptive": 159,
806
+ "text_reference_evaluation": 98,
807
  "text_rendering": 81,
808
  "visual_reference_evaluation": 121
809
  },
 
815
  "physical_plausibility": 60.5,
816
  "prompt_faithfulness": 32.0,
817
  "rubric_adaptive": 39.4,
818
+ "text_reference_evaluation": 9.2,
819
  "text_rendering": 6.8,
820
  "visual_reference_evaluation": 33.3
821
  },
 
839
  "physical_plausibility": 140,
840
  "prompt_faithfulness": 159,
841
  "rubric_adaptive": 159,
842
+ "text_reference_evaluation": 101,
843
  "text_rendering": 79,
844
  "visual_reference_evaluation": 121
845
  },
 
851
  "physical_plausibility": 58.2,
852
  "prompt_faithfulness": 23.3,
853
  "rubric_adaptive": 31.3,
854
+ "text_reference_evaluation": 6.8,
855
  "text_rendering": 4.2,
856
  "visual_reference_evaluation": 22.6
857
  },
 
875
  "physical_plausibility": 142,
876
  "prompt_faithfulness": 159,
877
  "rubric_adaptive": 159,
878
+ "text_reference_evaluation": 98,
879
  "text_rendering": 70,
880
  "visual_reference_evaluation": 121
881
  },
 
887
  "physical_plausibility": 49.4,
888
  "prompt_faithfulness": 24.3,
889
  "rubric_adaptive": 30.4,
890
+ "text_reference_evaluation": 7.3,
891
  "text_rendering": 2.6,
892
  "visual_reference_evaluation": 24.8
893
  },
 
911
  "physical_plausibility": 151,
912
  "prompt_faithfulness": 159,
913
  "rubric_adaptive": 159,
914
+ "text_reference_evaluation": 136,
915
  "text_rendering": 124,
916
  "visual_reference_evaluation": 147
917
  },
 
923
  "physical_plausibility": 19.6,
924
  "prompt_faithfulness": 6.1,
925
  "rubric_adaptive": 8.3,
926
+ "text_reference_evaluation": 0.7,
927
  "text_rendering": 0.7,
928
  "visual_reference_evaluation": 6.3
929
  },
 
949
  "physical_plausibility": 193,
950
  "prompt_faithfulness": 281,
951
  "rubric_adaptive": 281,
952
+ "text_reference_evaluation": 197,
953
  "text_rendering": 226,
954
  "visual_reference_evaluation": 224
955
  },
 
961
  "physical_plausibility": 81.0,
962
  "prompt_faithfulness": 71.9,
963
  "rubric_adaptive": 72.6,
964
+ "text_reference_evaluation": 62.1,
965
  "text_rendering": 78.8,
966
  "visual_reference_evaluation": 67.3
967
  },
 
985
  "physical_plausibility": 221,
986
  "prompt_faithfulness": 281,
987
  "rubric_adaptive": 281,
988
+ "text_reference_evaluation": 202,
989
  "text_rendering": 210,
990
  "visual_reference_evaluation": 223
991
  },
 
997
  "physical_plausibility": 80.9,
998
  "prompt_faithfulness": 62.9,
999
  "rubric_adaptive": 64.5,
1000
+ "text_reference_evaluation": 51.7,
1001
  "text_rendering": 67.1,
1002
  "visual_reference_evaluation": 59.2
1003
  },
 
1021
  "physical_plausibility": 181,
1022
  "prompt_faithfulness": 269,
1023
  "rubric_adaptive": 269,
1024
+ "text_reference_evaluation": 202,
1025
  "text_rendering": 218,
1026
  "visual_reference_evaluation": 221
1027
  },
 
1033
  "physical_plausibility": 76.4,
1034
  "prompt_faithfulness": 63.5,
1035
  "rubric_adaptive": 63.6,
1036
+ "text_reference_evaluation": 47.4,
1037
  "text_rendering": 62.9,
1038
  "visual_reference_evaluation": 57.5
1039
  },
 
1057
  "physical_plausibility": 190,
1058
  "prompt_faithfulness": 277,
1059
  "rubric_adaptive": 277,
1060
+ "text_reference_evaluation": 196,
1061
  "text_rendering": 208,
1062
  "visual_reference_evaluation": 229
1063
  },
 
1069
  "physical_plausibility": 72.5,
1070
  "prompt_faithfulness": 52.2,
1071
  "rubric_adaptive": 53.8,
1072
+ "text_reference_evaluation": 38.4,
1073
  "text_rendering": 58.7,
1074
  "visual_reference_evaluation": 44.8
1075
  },
 
1093
  "physical_plausibility": 199,
1094
  "prompt_faithfulness": 281,
1095
  "rubric_adaptive": 281,
1096
+ "text_reference_evaluation": 203,
1097
  "text_rendering": 203,
1098
  "visual_reference_evaluation": 234
1099
  },
 
1105
  "physical_plausibility": 66.3,
1106
  "prompt_faithfulness": 49.7,
1107
  "rubric_adaptive": 51.8,
1108
+ "text_reference_evaluation": 35.5,
1109
  "text_rendering": 56.2,
1110
  "visual_reference_evaluation": 41.3
1111
  },
 
1129
  "physical_plausibility": 212,
1130
  "prompt_faithfulness": 281,
1131
  "rubric_adaptive": 281,
1132
+ "text_reference_evaluation": 204,
1133
  "text_rendering": 220,
1134
  "visual_reference_evaluation": 233
1135
  },
 
1141
  "physical_plausibility": 62.6,
1142
  "prompt_faithfulness": 42.3,
1143
  "rubric_adaptive": 47.0,
1144
+ "text_reference_evaluation": 27.7,
1145
  "text_rendering": 47.3,
1146
  "visual_reference_evaluation": 35.6
1147
  },
 
1165
  "physical_plausibility": 217,
1166
  "prompt_faithfulness": 280,
1167
  "rubric_adaptive": 281,
1168
+ "text_reference_evaluation": 215,
1169
  "text_rendering": 208,
1170
  "visual_reference_evaluation": 223
1171
  },
 
1177
  "physical_plausibility": 61.5,
1178
  "prompt_faithfulness": 37.7,
1179
  "rubric_adaptive": 42.8,
1180
+ "text_reference_evaluation": 24.1,
1181
  "text_rendering": 35.8,
1182
  "visual_reference_evaluation": 33.5
1183
  },
 
1201
  "physical_plausibility": 205,
1202
  "prompt_faithfulness": 281,
1203
  "rubric_adaptive": 281,
1204
+ "text_reference_evaluation": 220,
1205
  "text_rendering": 216,
1206
  "visual_reference_evaluation": 223
1207
  },
 
1213
  "physical_plausibility": 66.7,
1214
  "prompt_faithfulness": 36.6,
1215
  "rubric_adaptive": 40.3,
1216
+ "text_reference_evaluation": 17.6,
1217
  "text_rendering": 26.9,
1218
  "visual_reference_evaluation": 32.2
1219
  },
 
1237
  "physical_plausibility": 250,
1238
  "prompt_faithfulness": 281,
1239
  "rubric_adaptive": 281,
1240
+ "text_reference_evaluation": 217,
1241
  "text_rendering": 206,
1242
  "visual_reference_evaluation": 223
1243
  },
 
1249
  "physical_plausibility": 44.9,
1250
  "prompt_faithfulness": 20.8,
1251
  "rubric_adaptive": 25.9,
1252
+ "text_reference_evaluation": 8.0,
1253
  "text_rendering": 11.2,
1254
  "visual_reference_evaluation": 18.4
1255
  },
 
1273
  "physical_plausibility": 211,
1274
  "prompt_faithfulness": 281,
1275
  "rubric_adaptive": 281,
1276
+ "text_reference_evaluation": 230,
1277
  "text_rendering": 219,
1278
  "visual_reference_evaluation": 223
1279
  },
 
1285
  "physical_plausibility": 48.6,
1286
  "prompt_faithfulness": 18.1,
1287
  "rubric_adaptive": 23.8,
1288
+ "text_reference_evaluation": 6.9,
1289
  "text_rendering": 7.4,
1290
  "visual_reference_evaluation": 15.7
1291
  },
 
1309
  "physical_plausibility": 211,
1310
  "prompt_faithfulness": 280,
1311
  "rubric_adaptive": 281,
1312
+ "text_reference_evaluation": 230,
1313
  "text_rendering": 203,
1314
  "visual_reference_evaluation": 222
1315
  },
 
1321
  "physical_plausibility": 44.9,
1322
  "prompt_faithfulness": 12.7,
1323
  "rubric_adaptive": 19.3,
1324
+ "text_reference_evaluation": 4.4,
1325
  "text_rendering": 4.1,
1326
  "visual_reference_evaluation": 12.1
1327
  },
 
1345
  "physical_plausibility": 226,
1346
  "prompt_faithfulness": 281,
1347
  "rubric_adaptive": 281,
1348
+ "text_reference_evaluation": 223,
1349
  "text_rendering": 204,
1350
  "visual_reference_evaluation": 223
1351
  },
 
1357
  "physical_plausibility": 34.5,
1358
  "prompt_faithfulness": 11.9,
1359
  "rubric_adaptive": 16.8,
1360
+ "text_reference_evaluation": 3.4,
1361
  "text_rendering": 3.6,
1362
  "visual_reference_evaluation": 11.4
1363
  },
 
1381
  "physical_plausibility": 234,
1382
  "prompt_faithfulness": 281,
1383
  "rubric_adaptive": 281,
1384
+ "text_reference_evaluation": 244,
1385
  "text_rendering": 229,
1386
  "visual_reference_evaluation": 256
1387
  },
 
1393
  "physical_plausibility": 21.2,
1394
  "prompt_faithfulness": 4.2,
1395
  "rubric_adaptive": 6.8,
1396
+ "text_reference_evaluation": 0.5,
1397
  "text_rendering": 0.6,
1398
  "visual_reference_evaluation": 4.8
1399
  },
 
1419
  "physical_plausibility": 23,
1420
  "prompt_faithfulness": 118,
1421
  "rubric_adaptive": 118,
1422
+ "text_reference_evaluation": 114,
1423
  "text_rendering": 110,
1424
  "visual_reference_evaluation": 95
1425
  },
 
1431
  "physical_plausibility": 91.3,
1432
  "prompt_faithfulness": 68.2,
1433
  "rubric_adaptive": 63.6,
1434
+ "text_reference_evaluation": 38.9,
1435
  "text_rendering": 74.1,
1436
  "visual_reference_evaluation": 66.1
1437
  },
 
1455
  "physical_plausibility": 72,
1456
  "prompt_faithfulness": 118,
1457
  "rubric_adaptive": 118,
1458
+ "text_reference_evaluation": 115,
1459
  "text_rendering": 110,
1460
  "visual_reference_evaluation": 95
1461
  },
 
1467
  "physical_plausibility": 85.6,
1468
  "prompt_faithfulness": 58.4,
1469
  "rubric_adaptive": 53.3,
1470
+ "text_reference_evaluation": 30.1,
1471
  "text_rendering": 63.5,
1472
  "visual_reference_evaluation": 53.6
1473
  },
 
1491
  "physical_plausibility": 39,
1492
  "prompt_faithfulness": 118,
1493
  "rubric_adaptive": 118,
1494
+ "text_reference_evaluation": 116,
1495
  "text_rendering": 113,
1496
  "visual_reference_evaluation": 96
1497
  },
 
1503
  "physical_plausibility": 90.2,
1504
  "prompt_faithfulness": 57.5,
1505
  "rubric_adaptive": 53.1,
1506
+ "text_reference_evaluation": 30.3,
1507
  "text_rendering": 55.6,
1508
  "visual_reference_evaluation": 53.3
1509
  },
 
1527
  "physical_plausibility": 20,
1528
  "prompt_faithfulness": 118,
1529
  "rubric_adaptive": 118,
1530
+ "text_reference_evaluation": 116,
1531
  "text_rendering": 115,
1532
  "visual_reference_evaluation": 96
1533
  },
 
1539
  "physical_plausibility": 69.2,
1540
  "prompt_faithfulness": 37.6,
1541
  "rubric_adaptive": 36.8,
1542
+ "text_reference_evaluation": 18.7,
1543
  "text_rendering": 41.3,
1544
  "visual_reference_evaluation": 28.3
1545
  },
 
1563
  "physical_plausibility": 23,
1564
  "prompt_faithfulness": 118,
1565
  "rubric_adaptive": 118,
1566
+ "text_reference_evaluation": 117,
1567
  "text_rendering": 113,
1568
  "visual_reference_evaluation": 96
1569
  },
 
1575
  "physical_plausibility": 74.6,
1576
  "prompt_faithfulness": 36.6,
1577
  "rubric_adaptive": 34.8,
1578
+ "text_reference_evaluation": 18.4,
1579
  "text_rendering": 41.6,
1580
  "visual_reference_evaluation": 28.6
1581
  },
 
1599
  "physical_plausibility": 45,
1600
  "prompt_faithfulness": 118,
1601
  "rubric_adaptive": 118,
1602
+ "text_reference_evaluation": 115,
1603
  "text_rendering": 113,
1604
  "visual_reference_evaluation": 96
1605
  },
 
1611
  "physical_plausibility": 65.2,
1612
  "prompt_faithfulness": 32.9,
1613
  "rubric_adaptive": 31.1,
1614
+ "text_reference_evaluation": 14.1,
1615
  "text_rendering": 37.2,
1616
  "visual_reference_evaluation": 20.1
1617
  },
 
1635
  "physical_plausibility": 55,
1636
  "prompt_faithfulness": 118,
1637
  "rubric_adaptive": 118,
1638
+ "text_reference_evaluation": 116,
1639
  "text_rendering": 112,
1640
  "visual_reference_evaluation": 95
1641
  },
 
1647
  "physical_plausibility": 65.8,
1648
  "prompt_faithfulness": 25.2,
1649
  "rubric_adaptive": 25.2,
1650
+ "text_reference_evaluation": 7.2,
1651
  "text_rendering": 20.2,
1652
  "visual_reference_evaluation": 17.7
1653
  },
 
1671
  "physical_plausibility": 55,
1672
  "prompt_faithfulness": 118,
1673
  "rubric_adaptive": 118,
1674
+ "text_reference_evaluation": 115,
1675
  "text_rendering": 114,
1676
  "visual_reference_evaluation": 95
1677
  },
 
1683
  "physical_plausibility": 59.7,
1684
  "prompt_faithfulness": 21.6,
1685
  "rubric_adaptive": 24.2,
1686
+ "text_reference_evaluation": 8.6,
1687
  "text_rendering": 22.1,
1688
  "visual_reference_evaluation": 17.4
1689
  },
 
1707
  "physical_plausibility": 83,
1708
  "prompt_faithfulness": 118,
1709
  "rubric_adaptive": 118,
1710
+ "text_reference_evaluation": 118,
1711
  "text_rendering": 114,
1712
  "visual_reference_evaluation": 95
1713
  },
 
1719
  "physical_plausibility": 16.1,
1720
  "prompt_faithfulness": 1.3,
1721
  "rubric_adaptive": 4.1,
1722
+ "text_reference_evaluation": 0.3,
1723
  "text_rendering": 0.3,
1724
  "visual_reference_evaluation": 2.3
1725
  },
 
1743
  "physical_plausibility": 59,
1744
  "prompt_faithfulness": 118,
1745
  "rubric_adaptive": 118,
1746
+ "text_reference_evaluation": 118,
1747
  "text_rendering": 117,
1748
  "visual_reference_evaluation": 95
1749
  },
 
1755
  "physical_plausibility": 12.1,
1756
  "prompt_faithfulness": 2.0,
1757
  "rubric_adaptive": 3.3,
1758
+ "text_reference_evaluation": 0.7,
1759
  "text_rendering": 1.1,
1760
  "visual_reference_evaluation": 1.8
1761
  },
 
1779
  "physical_plausibility": 80,
1780
  "prompt_faithfulness": 118,
1781
  "rubric_adaptive": 118,
1782
+ "text_reference_evaluation": 118,
1783
  "text_rendering": 112,
1784
  "visual_reference_evaluation": 96
1785
  },
 
1791
  "physical_plausibility": 11.2,
1792
  "prompt_faithfulness": 1.1,
1793
  "rubric_adaptive": 2.6,
1794
+ "text_reference_evaluation": 0.3,
1795
  "text_rendering": 0.3,
1796
  "visual_reference_evaluation": 1.4
1797
  },
 
1815
  "physical_plausibility": 64,
1816
  "prompt_faithfulness": 117,
1817
  "rubric_adaptive": 118,
1818
+ "text_reference_evaluation": 117,
1819
  "text_rendering": 115,
1820
  "visual_reference_evaluation": 94
1821
  },
 
1827
  "physical_plausibility": 9.4,
1828
  "prompt_faithfulness": 0.4,
1829
  "rubric_adaptive": 2.0,
1830
+ "text_reference_evaluation": 0.0,
1831
  "text_rendering": 0.1,
1832
  "visual_reference_evaluation": 0.9
1833
  },
 
1851
  "physical_plausibility": 69,
1852
  "prompt_faithfulness": 118,
1853
  "rubric_adaptive": 118,
1854
+ "text_reference_evaluation": 117,
1855
  "text_rendering": 112,
1856
  "visual_reference_evaluation": 95
1857
  },
 
1863
  "physical_plausibility": 5.1,
1864
  "prompt_faithfulness": 1.0,
1865
  "rubric_adaptive": 1.8,
1866
+ "text_reference_evaluation": 0.0,
1867
  "text_rendering": 0.0,
1868
  "visual_reference_evaluation": 1.2
1869
  },
 
1889
  "physical_plausibility": 352,
1890
  "prompt_faithfulness": 419,
1891
  "rubric_adaptive": 419,
1892
+ "text_reference_evaluation": 235,
1893
  "text_rendering": 264,
1894
  "visual_reference_evaluation": 352
1895
  },
 
1901
  "physical_plausibility": 70.5,
1902
  "prompt_faithfulness": 63.5,
1903
  "rubric_adaptive": 66.5,
1904
+ "text_reference_evaluation": 47.5,
1905
  "text_rendering": 69.8,
1906
  "visual_reference_evaluation": 60.4
1907
  },
 
1925
  "physical_plausibility": 371,
1926
  "prompt_faithfulness": 419,
1927
  "rubric_adaptive": 419,
1928
+ "text_reference_evaluation": 227,
1929
  "text_rendering": 237,
1930
  "visual_reference_evaluation": 351
1931
  },
 
1937
  "physical_plausibility": 73.2,
1938
  "prompt_faithfulness": 58.9,
1939
  "rubric_adaptive": 64.0,
1940
+ "text_reference_evaluation": 43.5,
1941
  "text_rendering": 62.0,
1942
  "visual_reference_evaluation": 57.1
1943
  },
 
1961
  "physical_plausibility": 323,
1962
  "prompt_faithfulness": 388,
1963
  "rubric_adaptive": 388,
1964
+ "text_reference_evaluation": 224,
1965
  "text_rendering": 237,
1966
  "visual_reference_evaluation": 326
1967
  },
 
1973
  "physical_plausibility": 68.2,
1974
  "prompt_faithfulness": 58.8,
1975
  "rubric_adaptive": 63.1,
1976
+ "text_reference_evaluation": 42.8,
1977
  "text_rendering": 62.1,
1978
  "visual_reference_evaluation": 55.9
1979
  },
 
1997
  "physical_plausibility": 344,
1998
  "prompt_faithfulness": 410,
1999
  "rubric_adaptive": 410,
2000
+ "text_reference_evaluation": 216,
2001
  "text_rendering": 203,
2002
  "visual_reference_evaluation": 347
2003
  },
 
2009
  "physical_plausibility": 65.9,
2010
  "prompt_faithfulness": 44.4,
2011
  "rubric_adaptive": 51.0,
2012
+ "text_reference_evaluation": 30.9,
2013
  "text_rendering": 52.5,
2014
  "visual_reference_evaluation": 40.5
2015
  },
 
2033
  "physical_plausibility": 354,
2034
  "prompt_faithfulness": 419,
2035
  "rubric_adaptive": 419,
2036
+ "text_reference_evaluation": 230,
2037
  "text_rendering": 205,
2038
  "visual_reference_evaluation": 358
2039
  },
 
2045
  "physical_plausibility": 62.5,
2046
  "prompt_faithfulness": 41.9,
2047
  "rubric_adaptive": 48.4,
2048
+ "text_reference_evaluation": 28.1,
2049
  "text_rendering": 48.1,
2050
  "visual_reference_evaluation": 37.3
2051
  },
 
2069
  "physical_plausibility": 366,
2070
  "prompt_faithfulness": 419,
2071
  "rubric_adaptive": 419,
2072
+ "text_reference_evaluation": 224,
2073
  "text_rendering": 241,
2074
  "visual_reference_evaluation": 356
2075
  },
 
2081
  "physical_plausibility": 59.9,
2082
  "prompt_faithfulness": 43.5,
2083
  "rubric_adaptive": 49.4,
2084
+ "text_reference_evaluation": 24.9,
2085
  "text_rendering": 45.3,
2086
  "visual_reference_evaluation": 37.2
2087
  },
 
2105
  "physical_plausibility": 369,
2106
  "prompt_faithfulness": 418,
2107
  "rubric_adaptive": 419,
2108
+ "text_reference_evaluation": 237,
2109
  "text_rendering": 219,
2110
  "visual_reference_evaluation": 348
2111
  },
 
2117
  "physical_plausibility": 63.0,
2118
  "prompt_faithfulness": 40.4,
2119
  "rubric_adaptive": 47.6,
2120
+ "text_reference_evaluation": 21.0,
2121
  "text_rendering": 35.8,
2122
  "visual_reference_evaluation": 36.3
2123
  },
 
2141
  "physical_plausibility": 367,
2142
  "prompt_faithfulness": 419,
2143
  "rubric_adaptive": 419,
2144
+ "text_reference_evaluation": 245,
2145
  "text_rendering": 236,
2146
  "visual_reference_evaluation": 349
2147
  },
 
2153
  "physical_plausibility": 62.0,
2154
  "prompt_faithfulness": 40.2,
2155
  "rubric_adaptive": 46.2,
2156
+ "text_reference_evaluation": 18.5,
2157
  "text_rendering": 29.8,
2158
  "visual_reference_evaluation": 36.4
2159
  },
 
2177
  "physical_plausibility": 388,
2178
  "prompt_faithfulness": 419,
2179
  "rubric_adaptive": 419,
2180
+ "text_reference_evaluation": 244,
2181
  "text_rendering": 212,
2182
  "visual_reference_evaluation": 348
2183
  },
 
2189
  "physical_plausibility": 52.0,
2190
  "prompt_faithfulness": 28.4,
2191
  "rubric_adaptive": 35.2,
2192
+ "text_reference_evaluation": 9.4,
2193
  "text_rendering": 14.9,
2194
  "visual_reference_evaluation": 25.9
2195
  },
 
2213
  "physical_plausibility": 365,
2214
  "prompt_faithfulness": 419,
2215
  "rubric_adaptive": 419,
2216
+ "text_reference_evaluation": 254,
2217
  "text_rendering": 230,
2218
  "visual_reference_evaluation": 348
2219
  },
 
2225
  "physical_plausibility": 53.1,
2226
  "prompt_faithfulness": 23.9,
2227
  "rubric_adaptive": 31.2,
2228
+ "text_reference_evaluation": 6.4,
2229
  "text_rendering": 9.9,
2230
  "visual_reference_evaluation": 21.3
2231
  },
 
2249
  "physical_plausibility": 355,
2250
  "prompt_faithfulness": 418,
2251
  "rubric_adaptive": 419,
2252
+ "text_reference_evaluation": 255,
2253
  "text_rendering": 223,
2254
  "visual_reference_evaluation": 347
2255
  },
 
2261
  "physical_plausibility": 49.9,
2262
  "prompt_faithfulness": 17.6,
2263
  "rubric_adaptive": 25.6,
2264
+ "text_reference_evaluation": 3.8,
2265
  "text_rendering": 5.0,
2266
  "visual_reference_evaluation": 14.6
2267
  },
 
2285
  "physical_plausibility": 373,
2286
  "prompt_faithfulness": 419,
2287
  "rubric_adaptive": 419,
2288
+ "text_reference_evaluation": 245,
2289
  "text_rendering": 213,
2290
  "visual_reference_evaluation": 348
2291
  },
 
2297
  "physical_plausibility": 41.1,
2298
  "prompt_faithfulness": 18.9,
2299
  "rubric_adaptive": 25.4,
2300
+ "text_reference_evaluation": 4.6,
2301
  "text_rendering": 4.5,
2302
  "visual_reference_evaluation": 18.8
2303
  },
 
2321
  "physical_plausibility": 388,
2322
  "prompt_faithfulness": 419,
2323
  "rubric_adaptive": 419,
2324
+ "text_reference_evaluation": 328,
2325
  "text_rendering": 305,
2326
  "visual_reference_evaluation": 402
2327
  },
 
2333
  "physical_plausibility": 21.5,
2334
  "prompt_faithfulness": 6.7,
2335
  "rubric_adaptive": 9.6,
2336
+ "text_reference_evaluation": 0.6,
2337
  "text_rendering": 0.2,
2338
  "visual_reference_evaluation": 6.1
2339
  },
 
2359
  "physical_plausibility": 176,
2360
  "prompt_faithfulness": 273,
2361
  "rubric_adaptive": 273,
2362
+ "text_reference_evaluation": 209,
2363
  "text_rendering": 217,
2364
  "visual_reference_evaluation": 222
2365
  },
 
2371
  "physical_plausibility": 80.2,
2372
  "prompt_faithfulness": 68.9,
2373
  "rubric_adaptive": 69.1,
2374
+ "text_reference_evaluation": 53.5,
2375
  "text_rendering": 73.8,
2376
  "visual_reference_evaluation": 67.1
2377
  },
 
2395
  "physical_plausibility": 215,
2396
  "prompt_faithfulness": 273,
2397
  "rubric_adaptive": 273,
2398
+ "text_reference_evaluation": 207,
2399
  "text_rendering": 208,
2400
  "visual_reference_evaluation": 223
2401
  },
 
2407
  "physical_plausibility": 80.2,
2408
  "prompt_faithfulness": 59.3,
2409
  "rubric_adaptive": 60.3,
2410
+ "text_reference_evaluation": 41.7,
2411
  "text_rendering": 62.4,
2412
  "visual_reference_evaluation": 56.9
2413
  },
 
2431
  "physical_plausibility": 184,
2432
  "prompt_faithfulness": 272,
2433
  "rubric_adaptive": 272,
2434
+ "text_reference_evaluation": 212,
2435
  "text_rendering": 213,
2436
  "visual_reference_evaluation": 226
2437
  },
 
2443
  "physical_plausibility": 74.8,
2444
  "prompt_faithfulness": 58.5,
2445
  "rubric_adaptive": 58.2,
2446
+ "text_reference_evaluation": 39.8,
2447
  "text_rendering": 56.3,
2448
  "visual_reference_evaluation": 56.2
2449
  },
 
2467
  "physical_plausibility": 173,
2468
  "prompt_faithfulness": 271,
2469
  "rubric_adaptive": 271,
2470
+ "text_reference_evaluation": 203,
2471
  "text_rendering": 197,
2472
  "visual_reference_evaluation": 224
2473
  },
 
2479
  "physical_plausibility": 73.4,
2480
  "prompt_faithfulness": 46.1,
2481
  "rubric_adaptive": 48.4,
2482
+ "text_reference_evaluation": 30.8,
2483
  "text_rendering": 48.8,
2484
  "visual_reference_evaluation": 41.5
2485
  },
 
2503
  "physical_plausibility": 179,
2504
  "prompt_faithfulness": 273,
2505
  "rubric_adaptive": 273,
2506
+ "text_reference_evaluation": 206,
2507
  "text_rendering": 194,
2508
  "visual_reference_evaluation": 227
2509
  },
 
2515
  "physical_plausibility": 67.9,
2516
  "prompt_faithfulness": 42.6,
2517
  "rubric_adaptive": 45.5,
2518
+ "text_reference_evaluation": 25.8,
2519
  "text_rendering": 44.5,
2520
  "visual_reference_evaluation": 39.2
2521
  },
 
2539
  "physical_plausibility": 206,
2540
  "prompt_faithfulness": 273,
2541
  "rubric_adaptive": 273,
2542
+ "text_reference_evaluation": 209,
2543
  "text_rendering": 214,
2544
  "visual_reference_evaluation": 227
2545
  },
 
2551
  "physical_plausibility": 60.2,
2552
  "prompt_faithfulness": 37.9,
2553
  "rubric_adaptive": 42.2,
2554
+ "text_reference_evaluation": 20.1,
2555
  "text_rendering": 39.6,
2556
  "visual_reference_evaluation": 32.5
2557
  },
 
2575
  "physical_plausibility": 211,
2576
  "prompt_faithfulness": 273,
2577
  "rubric_adaptive": 273,
2578
+ "text_reference_evaluation": 216,
2579
  "text_rendering": 208,
2580
  "visual_reference_evaluation": 222
2581
  },
 
2587
  "physical_plausibility": 63.7,
2588
  "prompt_faithfulness": 35.2,
2589
  "rubric_adaptive": 38.4,
2590
+ "text_reference_evaluation": 15.6,
2591
  "text_rendering": 28.5,
2592
  "visual_reference_evaluation": 30.7
2593
  },
 
2611
  "physical_plausibility": 202,
2612
  "prompt_faithfulness": 273,
2613
  "rubric_adaptive": 273,
2614
+ "text_reference_evaluation": 217,
2615
  "text_rendering": 212,
2616
  "visual_reference_evaluation": 222
2617
  },
 
2623
  "physical_plausibility": 64.5,
2624
  "prompt_faithfulness": 34.8,
2625
  "rubric_adaptive": 37.4,
2626
+ "text_reference_evaluation": 13.9,
2627
  "text_rendering": 24.5,
2628
  "visual_reference_evaluation": 31.3
2629
  },
 
2647
  "physical_plausibility": 240,
2648
  "prompt_faithfulness": 273,
2649
  "rubric_adaptive": 273,
2650
+ "text_reference_evaluation": 216,
2651
  "text_rendering": 198,
2652
  "visual_reference_evaluation": 222
2653
  },
 
2659
  "physical_plausibility": 39.8,
2660
  "prompt_faithfulness": 16.3,
2661
  "rubric_adaptive": 20.3,
2662
+ "text_reference_evaluation": 1.9,
2663
  "text_rendering": 2.8,
2664
  "visual_reference_evaluation": 16.9
2665
  },
 
2683
  "physical_plausibility": 212,
2684
  "prompt_faithfulness": 273,
2685
  "rubric_adaptive": 273,
2686
+ "text_reference_evaluation": 221,
2687
  "text_rendering": 209,
2688
  "visual_reference_evaluation": 222
2689
  },
 
2695
  "physical_plausibility": 43.9,
2696
  "prompt_faithfulness": 15.8,
2697
  "rubric_adaptive": 19.9,
2698
+ "text_reference_evaluation": 2.9,
2699
  "text_rendering": 2.5,
2700
  "visual_reference_evaluation": 15.7
2701
  },
 
2719
  "physical_plausibility": 215,
2720
  "prompt_faithfulness": 272,
2721
  "rubric_adaptive": 273,
2722
+ "text_reference_evaluation": 222,
2723
  "text_rendering": 202,
2724
  "visual_reference_evaluation": 221
2725
  },
 
2731
  "physical_plausibility": 39.5,
2732
  "prompt_faithfulness": 10.0,
2733
  "rubric_adaptive": 15.1,
2734
+ "text_reference_evaluation": 0.8,
2735
  "text_rendering": 1.6,
2736
  "visual_reference_evaluation": 9.5
2737
  },
 
2755
  "physical_plausibility": 216,
2756
  "prompt_faithfulness": 273,
2757
  "rubric_adaptive": 273,
2758
+ "text_reference_evaluation": 213,
2759
  "text_rendering": 193,
2760
  "visual_reference_evaluation": 222
2761
  },
 
2767
  "physical_plausibility": 34.9,
2768
  "prompt_faithfulness": 12.8,
2769
  "rubric_adaptive": 14.8,
2770
+ "text_reference_evaluation": 0.9,
2771
  "text_rendering": 1.9,
2772
  "visual_reference_evaluation": 12.8
2773
  },
 
2791
  "physical_plausibility": 227,
2792
  "prompt_faithfulness": 273,
2793
  "rubric_adaptive": 273,
2794
+ "text_reference_evaluation": 244,
2795
  "text_rendering": 225,
2796
  "visual_reference_evaluation": 252
2797
  },
 
2803
  "physical_plausibility": 17.6,
2804
  "prompt_faithfulness": 5.1,
2805
  "rubric_adaptive": 6.7,
2806
+ "text_reference_evaluation": 0.5,
2807
  "text_rendering": 1.0,
2808
  "visual_reference_evaluation": 5.1
2809
  },
 
2829
  "physical_plausibility": 23,
2830
  "prompt_faithfulness": 30,
2831
  "rubric_adaptive": 30,
2832
+ "text_reference_evaluation": 21,
2833
  "text_rendering": 23,
2834
  "visual_reference_evaluation": 22
2835
  },
 
2841
  "physical_plausibility": 78.3,
2842
  "prompt_faithfulness": 66.1,
2843
  "rubric_adaptive": 69.0,
2844
+ "text_reference_evaluation": 60.3,
2845
  "text_rendering": 76.1,
2846
  "visual_reference_evaluation": 65.9
2847
  },
 
2865
  "physical_plausibility": 25,
2866
  "prompt_faithfulness": 30,
2867
  "rubric_adaptive": 30,
2868
+ "text_reference_evaluation": 20,
2869
  "text_rendering": 20,
2870
  "visual_reference_evaluation": 21
2871
  },
 
2877
  "physical_plausibility": 78.0,
2878
  "prompt_faithfulness": 52.2,
2879
  "rubric_adaptive": 55.4,
2880
+ "text_reference_evaluation": 46.7,
2881
  "text_rendering": 60.8,
2882
  "visual_reference_evaluation": 51.6
2883
  },
 
2901
  "physical_plausibility": 23,
2902
  "prompt_faithfulness": 30,
2903
  "rubric_adaptive": 30,
2904
+ "text_reference_evaluation": 21,
2905
  "text_rendering": 20,
2906
  "visual_reference_evaluation": 24
2907
  },
 
2913
  "physical_plausibility": 63.8,
2914
  "prompt_faithfulness": 54.4,
2915
  "rubric_adaptive": 56.2,
2916
+ "text_reference_evaluation": 39.7,
2917
  "text_rendering": 66.7,
2918
  "visual_reference_evaluation": 50.7
2919
  },
 
2937
  "physical_plausibility": 23,
2938
  "prompt_faithfulness": 30,
2939
  "rubric_adaptive": 30,
2940
+ "text_reference_evaluation": 22,
2941
  "text_rendering": 19,
2942
  "visual_reference_evaluation": 24
2943
  },
 
2949
  "physical_plausibility": 58.0,
2950
  "prompt_faithfulness": 46.7,
2951
  "rubric_adaptive": 54.6,
2952
+ "text_reference_evaluation": 36.4,
2953
  "text_rendering": 66.7,
2954
  "visual_reference_evaluation": 50.0
2955
  },
 
2973
  "physical_plausibility": 21,
2974
  "prompt_faithfulness": 30,
2975
  "rubric_adaptive": 30,
2976
+ "text_reference_evaluation": 21,
2977
  "text_rendering": 21,
2978
  "visual_reference_evaluation": 24
2979
  },
 
2985
  "physical_plausibility": 60.3,
2986
  "prompt_faithfulness": 45.6,
2987
  "rubric_adaptive": 47.7,
2988
+ "text_reference_evaluation": 38.1,
2989
  "text_rendering": 68.3,
2990
  "visual_reference_evaluation": 40.3
2991
  },
 
3009
  "physical_plausibility": 23,
3010
  "prompt_faithfulness": 30,
3011
  "rubric_adaptive": 30,
3012
+ "text_reference_evaluation": 20,
3013
  "text_rendering": 19,
3014
  "visual_reference_evaluation": 24
3015
  },
 
3021
  "physical_plausibility": 62.3,
3022
  "prompt_faithfulness": 41.1,
3023
  "rubric_adaptive": 46.3,
3024
+ "text_reference_evaluation": 26.7,
3025
  "text_rendering": 57.0,
3026
  "visual_reference_evaluation": 43.1
3027
  },
 
3045
  "physical_plausibility": 22,
3046
  "prompt_faithfulness": 30,
3047
  "rubric_adaptive": 30,
3048
+ "text_reference_evaluation": 22,
3049
  "text_rendering": 20,
3050
  "visual_reference_evaluation": 21
3051
  },
 
3057
  "physical_plausibility": 68.2,
3058
  "prompt_faithfulness": 37.8,
3059
  "rubric_adaptive": 42.2,
3060
+ "text_reference_evaluation": 27.3,
3061
  "text_rendering": 35.0,
3062
  "visual_reference_evaluation": 32.5
3063
  },
 
3081
  "physical_plausibility": 24,
3082
  "prompt_faithfulness": 29,
3083
  "rubric_adaptive": 30,
3084
+ "text_reference_evaluation": 21,
3085
  "text_rendering": 17,
3086
  "visual_reference_evaluation": 21
3087
  },
 
3093
  "physical_plausibility": 64.6,
3094
  "prompt_faithfulness": 40.8,
3095
  "rubric_adaptive": 41.6,
3096
+ "text_reference_evaluation": 28.6,
3097
  "text_rendering": 47.1,
3098
  "visual_reference_evaluation": 37.3
3099
  },
 
3117
  "physical_plausibility": 29,
3118
  "prompt_faithfulness": 30,
3119
  "rubric_adaptive": 30,
3120
+ "text_reference_evaluation": 22,
3121
  "text_rendering": 16,
3122
  "visual_reference_evaluation": 21
3123
  },
 
3129
  "physical_plausibility": 37.9,
3130
  "prompt_faithfulness": 15.6,
3131
  "rubric_adaptive": 22.8,
3132
+ "text_reference_evaluation": 2.3,
3133
  "text_rendering": 8.3,
3134
  "visual_reference_evaluation": 18.3
3135
  },
 
3153
  "physical_plausibility": 23,
3154
  "prompt_faithfulness": 30,
3155
  "rubric_adaptive": 30,
3156
+ "text_reference_evaluation": 23,
3157
  "text_rendering": 19,
3158
  "visual_reference_evaluation": 21
3159
  },
 
3165
  "physical_plausibility": 44.9,
3166
  "prompt_faithfulness": 12.8,
3167
  "rubric_adaptive": 19.0,
3168
+ "text_reference_evaluation": 1.4,
3169
  "text_rendering": 7.0,
3170
  "visual_reference_evaluation": 7.9
3171
  },
 
3189
  "physical_plausibility": 23,
3190
  "prompt_faithfulness": 30,
3191
  "rubric_adaptive": 30,
3192
+ "text_reference_evaluation": 23,
3193
  "text_rendering": 21,
3194
  "visual_reference_evaluation": 21
3195
  },
 
3201
  "physical_plausibility": 34.1,
3202
  "prompt_faithfulness": 14.4,
3203
  "rubric_adaptive": 22.0,
3204
+ "text_reference_evaluation": 2.9,
3205
  "text_rendering": 2.4,
3206
  "visual_reference_evaluation": 15.1
3207
  },
 
3225
  "physical_plausibility": 27,
3226
  "prompt_faithfulness": 30,
3227
  "rubric_adaptive": 30,
3228
+ "text_reference_evaluation": 22,
3229
  "text_rendering": 18,
3230
  "visual_reference_evaluation": 21
3231
  },
 
3237
  "physical_plausibility": 31.5,
3238
  "prompt_faithfulness": 7.8,
3239
  "rubric_adaptive": 10.2,
3240
+ "text_reference_evaluation": 0.8,
3241
  "text_rendering": 5.6,
3242
  "visual_reference_evaluation": 9.5
3243
  },
 
3261
  "physical_plausibility": 28,
3262
  "prompt_faithfulness": 30,
3263
  "rubric_adaptive": 30,
3264
+ "text_reference_evaluation": 24,
3265
  "text_rendering": 20,
3266
  "visual_reference_evaluation": 24
3267
  },
 
3273
  "physical_plausibility": 31.5,
3274
  "prompt_faithfulness": 3.9,
3275
  "rubric_adaptive": 7.9,
3276
+ "text_reference_evaluation": 2.8,
3277
  "text_rendering": 8.3,
3278
  "visual_reference_evaluation": 0.7
3279
  },
 
3299
  "physical_plausibility": 259,
3300
  "prompt_faithfulness": 411,
3301
  "rubric_adaptive": 411,
3302
+ "text_reference_evaluation": 363,
3303
  "text_rendering": 393,
3304
  "visual_reference_evaluation": 299
3305
  },
 
3311
  "physical_plausibility": 86.5,
3312
  "prompt_faithfulness": 73.7,
3313
  "rubric_adaptive": 73.5,
3314
+ "text_reference_evaluation": 58.1,
3315
  "text_rendering": 76.3,
3316
  "visual_reference_evaluation": 70.7
3317
  },
 
3335
  "physical_plausibility": 320,
3336
  "prompt_faithfulness": 411,
3337
  "rubric_adaptive": 411,
3338
+ "text_reference_evaluation": 370,
3339
  "text_rendering": 385,
3340
  "visual_reference_evaluation": 299
3341
  },
 
3347
  "physical_plausibility": 85.3,
3348
  "prompt_faithfulness": 64.7,
3349
  "rubric_adaptive": 65.4,
3350
+ "text_reference_evaluation": 49.1,
3351
  "text_rendering": 65.2,
3352
  "visual_reference_evaluation": 62.5
3353
  },
 
3371
  "physical_plausibility": 270,
3372
  "prompt_faithfulness": 404,
3373
  "rubric_adaptive": 404,
3374
+ "text_reference_evaluation": 373,
3375
  "text_rendering": 388,
3376
  "visual_reference_evaluation": 299
3377
  },
 
3383
  "physical_plausibility": 82.8,
3384
  "prompt_faithfulness": 64.4,
3385
  "rubric_adaptive": 64.2,
3386
+ "text_reference_evaluation": 47.9,
3387
  "text_rendering": 61.0,
3388
  "visual_reference_evaluation": 61.2
3389
  },
 
3407
  "physical_plausibility": 251,
3408
  "prompt_faithfulness": 408,
3409
  "rubric_adaptive": 408,
3410
+ "text_reference_evaluation": 370,
3411
  "text_rendering": 391,
3412
  "visual_reference_evaluation": 303
3413
  },
 
3419
  "physical_plausibility": 80.9,
3420
  "prompt_faithfulness": 51.7,
3421
  "rubric_adaptive": 54.0,
3422
+ "text_reference_evaluation": 35.7,
3423
  "text_rendering": 54.9,
3424
  "visual_reference_evaluation": 46.3
3425
  },
 
3443
  "physical_plausibility": 253,
3444
  "prompt_faithfulness": 411,
3445
  "rubric_adaptive": 411,
3446
+ "text_reference_evaluation": 380,
3447
  "text_rendering": 394,
3448
  "visual_reference_evaluation": 307
3449
  },
 
3455
  "physical_plausibility": 78.2,
3456
  "prompt_faithfulness": 49.2,
3457
  "rubric_adaptive": 51.5,
3458
+ "text_reference_evaluation": 33.8,
3459
  "text_rendering": 53.2,
3460
  "visual_reference_evaluation": 43.4
3461
  },
 
3479
  "physical_plausibility": 291,
3480
  "prompt_faithfulness": 411,
3481
  "rubric_adaptive": 411,
3482
+ "text_reference_evaluation": 376,
3483
  "text_rendering": 399,
3484
  "visual_reference_evaluation": 306
3485
  },
 
3491
  "physical_plausibility": 69.6,
3492
  "prompt_faithfulness": 45.6,
3493
  "rubric_adaptive": 48.5,
3494
+ "text_reference_evaluation": 29.3,
3495
  "text_rendering": 49.1,
3496
  "visual_reference_evaluation": 37.5
3497
  },
 
3515
  "physical_plausibility": 297,
3516
  "prompt_faithfulness": 411,
3517
  "rubric_adaptive": 411,
3518
+ "text_reference_evaluation": 387,
3519
  "text_rendering": 396,
3520
  "visual_reference_evaluation": 298
3521
  },
 
3527
  "physical_plausibility": 70.9,
3528
  "prompt_faithfulness": 38.2,
3529
  "rubric_adaptive": 42.4,
3530
+ "text_reference_evaluation": 23.4,
3531
  "text_rendering": 36.3,
3532
  "visual_reference_evaluation": 33.9
3533
  },
 
3551
  "physical_plausibility": 293,
3552
  "prompt_faithfulness": 411,
3553
  "rubric_adaptive": 411,
3554
+ "text_reference_evaluation": 395,
3555
  "text_rendering": 392,
3556
  "visual_reference_evaluation": 299
3557
  },
 
3563
  "physical_plausibility": 72.9,
3564
  "prompt_faithfulness": 34.3,
3565
  "rubric_adaptive": 37.4,
3566
+ "text_reference_evaluation": 15.5,
3567
  "text_rendering": 26.0,
3568
  "visual_reference_evaluation": 30.5
3569
  },
 
3587
  "physical_plausibility": 354,
3588
  "prompt_faithfulness": 411,
3589
  "rubric_adaptive": 411,
3590
+ "text_reference_evaluation": 398,
3591
  "text_rendering": 402,
3592
  "visual_reference_evaluation": 298
3593
  },
 
3599
  "physical_plausibility": 44.4,
3600
  "prompt_faithfulness": 16.7,
3601
  "rubric_adaptive": 20.9,
3602
+ "text_reference_evaluation": 6.9,
3603
  "text_rendering": 10.9,
3604
  "visual_reference_evaluation": 15.8
3605
  },
 
3623
  "physical_plausibility": 297,
3624
  "prompt_faithfulness": 411,
3625
  "rubric_adaptive": 411,
3626
+ "text_reference_evaluation": 406,
3627
  "text_rendering": 400,
3628
  "visual_reference_evaluation": 298
3629
  },
 
3635
  "physical_plausibility": 49.6,
3636
  "prompt_faithfulness": 14.1,
3637
  "rubric_adaptive": 18.8,
3638
+ "text_reference_evaluation": 5.3,
3639
  "text_rendering": 7.2,
3640
  "visual_reference_evaluation": 12.8
3641
  },
 
3659
  "physical_plausibility": 289,
3660
  "prompt_faithfulness": 410,
3661
  "rubric_adaptive": 411,
3662
+ "text_reference_evaluation": 403,
3663
  "text_rendering": 391,
3664
  "visual_reference_evaluation": 297
3665
  },
 
3671
  "physical_plausibility": 45.8,
3672
  "prompt_faithfulness": 10.1,
3673
  "rubric_adaptive": 15.3,
3674
+ "text_reference_evaluation": 2.7,
3675
  "text_rendering": 3.9,
3676
  "visual_reference_evaluation": 9.3
3677
  },
 
3695
  "physical_plausibility": 319,
3696
  "prompt_faithfulness": 411,
3697
  "rubric_adaptive": 411,
3698
+ "text_reference_evaluation": 406,
3699
  "text_rendering": 390,
3700
  "visual_reference_evaluation": 298
3701
  },
 
3707
  "physical_plausibility": 35.9,
3708
  "prompt_faithfulness": 10.3,
3709
  "rubric_adaptive": 13.7,
3710
+ "text_reference_evaluation": 2.0,
3711
  "text_rendering": 3.4,
3712
  "visual_reference_evaluation": 9.7
3713
  },
 
3731
  "physical_plausibility": 337,
3732
  "prompt_faithfulness": 411,
3733
  "rubric_adaptive": 411,
3734
+ "text_reference_evaluation": 406,
3735
  "text_rendering": 397,
3736
  "visual_reference_evaluation": 369
3737
  },
 
3743
  "physical_plausibility": 14.3,
3744
  "prompt_faithfulness": 2.8,
3745
  "rubric_adaptive": 4.7,
3746
+ "text_reference_evaluation": 0.7,
3747
  "text_rendering": 1.0,
3748
  "visual_reference_evaluation": 3.3
3749
  },
 
3769
  "physical_plausibility": 10,
3770
  "prompt_faithfulness": 38,
3771
  "rubric_adaptive": 38,
3772
+ "text_reference_evaluation": 35,
3773
  "text_rendering": 35,
3774
  "visual_reference_evaluation": 25
3775
  },
 
3781
  "physical_plausibility": 85.0,
3782
  "prompt_faithfulness": 63.2,
3783
  "rubric_adaptive": 57.9,
3784
+ "text_reference_evaluation": 23.3,
3785
  "text_rendering": 68.1,
3786
  "visual_reference_evaluation": 56.7
3787
  },
 
3805
  "physical_plausibility": 29,
3806
  "prompt_faithfulness": 38,
3807
  "rubric_adaptive": 38,
3808
+ "text_reference_evaluation": 36,
3809
  "text_rendering": 36,
3810
  "visual_reference_evaluation": 25
3811
  },
 
3817
  "physical_plausibility": 86.8,
3818
  "prompt_faithfulness": 53.9,
3819
  "rubric_adaptive": 48.5,
3820
+ "text_reference_evaluation": 23.6,
3821
  "text_rendering": 60.6,
3822
  "visual_reference_evaluation": 45.3
3823
  },
 
3841
  "physical_plausibility": 16,
3842
  "prompt_faithfulness": 38,
3843
  "rubric_adaptive": 38,
3844
+ "text_reference_evaluation": 35,
3845
  "text_rendering": 37,
3846
  "visual_reference_evaluation": 27
3847
  },
 
3853
  "physical_plausibility": 89.6,
3854
  "prompt_faithfulness": 56.1,
3855
  "rubric_adaptive": 53.6,
3856
+ "text_reference_evaluation": 24.3,
3857
  "text_rendering": 58.1,
3858
  "visual_reference_evaluation": 46.9
3859
  },
 
3877
  "physical_plausibility": 8,
3878
  "prompt_faithfulness": 38,
3879
  "rubric_adaptive": 38,
3880
+ "text_reference_evaluation": 38,
3881
  "text_rendering": 38,
3882
  "visual_reference_evaluation": 27
3883
  },
 
3889
  "physical_plausibility": 56.2,
3890
  "prompt_faithfulness": 36.0,
3891
  "rubric_adaptive": 32.7,
3892
+ "text_reference_evaluation": 11.0,
3893
  "text_rendering": 40.4,
3894
  "visual_reference_evaluation": 20.4
3895
  },
 
3913
  "physical_plausibility": 11,
3914
  "prompt_faithfulness": 38,
3915
  "rubric_adaptive": 38,
3916
+ "text_reference_evaluation": 38,
3917
  "text_rendering": 35,
3918
  "visual_reference_evaluation": 27
3919
  },
 
3925
  "physical_plausibility": 77.3,
3926
  "prompt_faithfulness": 32.5,
3927
  "rubric_adaptive": 29.2,
3928
+ "text_reference_evaluation": 8.3,
3929
  "text_rendering": 35.2,
3930
  "visual_reference_evaluation": 19.1
3931
  },
 
3949
  "physical_plausibility": 16,
3950
  "prompt_faithfulness": 38,
3951
  "rubric_adaptive": 38,
3952
+ "text_reference_evaluation": 36,
3953
  "text_rendering": 37,
3954
  "visual_reference_evaluation": 27
3955
  },
 
3961
  "physical_plausibility": 55.2,
3962
  "prompt_faithfulness": 35.1,
3963
  "rubric_adaptive": 27.5,
3964
+ "text_reference_evaluation": 9.3,
3965
  "text_rendering": 39.6,
3966
  "visual_reference_evaluation": 9.3
3967
  },
 
3985
  "physical_plausibility": 23,
3986
  "prompt_faithfulness": 38,
3987
  "rubric_adaptive": 38,
3988
+ "text_reference_evaluation": 37,
3989
  "text_rendering": 35,
3990
  "visual_reference_evaluation": 25
3991
  },
 
3997
  "physical_plausibility": 75.4,
3998
  "prompt_faithfulness": 22.4,
3999
  "rubric_adaptive": 21.2,
4000
+ "text_reference_evaluation": 5.4,
4001
  "text_rendering": 19.0,
4002
  "visual_reference_evaluation": 16.7
4003
  },
 
4021
  "physical_plausibility": 20,
4022
  "prompt_faithfulness": 38,
4023
  "rubric_adaptive": 38,
4024
+ "text_reference_evaluation": 36,
4025
  "text_rendering": 38,
4026
  "visual_reference_evaluation": 25
4027
  },
 
4033
  "physical_plausibility": 55.8,
4034
  "prompt_faithfulness": 22.4,
4035
  "rubric_adaptive": 22.0,
4036
+ "text_reference_evaluation": 5.1,
4037
  "text_rendering": 23.2,
4038
  "visual_reference_evaluation": 9.3
4039
  },
 
4057
  "physical_plausibility": 28,
4058
  "prompt_faithfulness": 38,
4059
  "rubric_adaptive": 38,
4060
+ "text_reference_evaluation": 38,
4061
  "text_rendering": 38,
4062
  "visual_reference_evaluation": 25
4063
  },
 
4069
  "physical_plausibility": 28.0,
4070
  "prompt_faithfulness": 3.5,
4071
  "rubric_adaptive": 5.7,
4072
+ "text_reference_evaluation": 1.8,
4073
  "text_rendering": 3.1,
4074
  "visual_reference_evaluation": 4.0
4075
  },
 
4093
  "physical_plausibility": 23,
4094
  "prompt_faithfulness": 38,
4095
  "rubric_adaptive": 38,
4096
+ "text_reference_evaluation": 38,
4097
  "text_rendering": 38,
4098
  "visual_reference_evaluation": 25
4099
  },
 
4105
  "physical_plausibility": 15.2,
4106
  "prompt_faithfulness": 2.6,
4107
  "rubric_adaptive": 3.3,
4108
+ "text_reference_evaluation": 1.3,
4109
  "text_rendering": 1.3,
4110
  "visual_reference_evaluation": 1.3
4111
  },
 
4129
  "physical_plausibility": 20,
4130
  "prompt_faithfulness": 38,
4131
  "rubric_adaptive": 38,
4132
+ "text_reference_evaluation": 38,
4133
  "text_rendering": 38,
4134
  "visual_reference_evaluation": 25
4135
  },
 
4141
  "physical_plausibility": 28.3,
4142
  "prompt_faithfulness": 1.8,
4143
  "rubric_adaptive": 3.8,
4144
+ "text_reference_evaluation": 0.9,
4145
  "text_rendering": 0.9,
4146
  "visual_reference_evaluation": 4.0
4147
  },
 
4165
  "physical_plausibility": 26,
4166
  "prompt_faithfulness": 38,
4167
  "rubric_adaptive": 38,
4168
+ "text_reference_evaluation": 37,
4169
  "text_rendering": 34,
4170
  "visual_reference_evaluation": 25
4171
  },
 
4177
  "physical_plausibility": 18.6,
4178
  "prompt_faithfulness": 0.4,
4179
  "rubric_adaptive": 2.2,
4180
+ "text_reference_evaluation": 0.0,
4181
  "text_rendering": 0.0,
4182
  "visual_reference_evaluation": 0.0
4183
  },
 
4201
  "physical_plausibility": 26,
4202
  "prompt_faithfulness": 38,
4203
  "rubric_adaptive": 38,
4204
+ "text_reference_evaluation": 37,
4205
  "text_rendering": 36,
4206
  "visual_reference_evaluation": 25
4207
  },
 
4213
  "physical_plausibility": 6.4,
4214
  "prompt_faithfulness": 0.4,
4215
  "rubric_adaptive": 1.2,
4216
+ "text_reference_evaluation": 0.0,
4217
  "text_rendering": 0.0,
4218
  "visual_reference_evaluation": 0.7
4219
  },
 
4239
  "physical_plausibility": 24,
4240
  "prompt_faithfulness": 56,
4241
  "rubric_adaptive": 56,
4242
+ "text_reference_evaluation": 51,
4243
  "text_rendering": 53,
4244
  "visual_reference_evaluation": 46
4245
  },
 
4251
  "physical_plausibility": 86.8,
4252
  "prompt_faithfulness": 69.6,
4253
  "rubric_adaptive": 64.9,
4254
+ "text_reference_evaluation": 37.3,
4255
  "text_rendering": 77.0,
4256
  "visual_reference_evaluation": 64.9
4257
  },
 
4275
  "physical_plausibility": 33,
4276
  "prompt_faithfulness": 56,
4277
  "rubric_adaptive": 56,
4278
+ "text_reference_evaluation": 52,
4279
  "text_rendering": 53,
4280
  "visual_reference_evaluation": 46
4281
  },
 
4287
  "physical_plausibility": 81.8,
4288
  "prompt_faithfulness": 59.5,
4289
  "rubric_adaptive": 58.9,
4290
+ "text_reference_evaluation": 32.4,
4291
  "text_rendering": 60.1,
4292
  "visual_reference_evaluation": 51.1
4293
  },
 
4311
  "physical_plausibility": 50,
4312
  "prompt_faithfulness": 56,
4313
  "rubric_adaptive": 56,
4314
+ "text_reference_evaluation": 52,
4315
  "text_rendering": 50,
4316
  "visual_reference_evaluation": 46
4317
  },
 
4323
  "physical_plausibility": 79.7,
4324
  "prompt_faithfulness": 59.4,
4325
  "rubric_adaptive": 52.9,
4326
+ "text_reference_evaluation": 30.4,
4327
  "text_rendering": 59.0,
4328
  "visual_reference_evaluation": 49.6
4329
  },
 
4347
  "physical_plausibility": 25,
4348
  "prompt_faithfulness": 56,
4349
  "rubric_adaptive": 56,
4350
+ "text_reference_evaluation": 54,
4351
  "text_rendering": 53,
4352
  "visual_reference_evaluation": 46
4353
  },
 
4359
  "physical_plausibility": 75.3,
4360
  "prompt_faithfulness": 45.1,
4361
  "rubric_adaptive": 43.3,
4362
+ "text_reference_evaluation": 24.1,
4363
  "text_rendering": 51.9,
4364
  "visual_reference_evaluation": 34.1
4365
  },
 
4383
  "physical_plausibility": 19,
4384
  "prompt_faithfulness": 56,
4385
  "rubric_adaptive": 56,
4386
+ "text_reference_evaluation": 52,
4387
  "text_rendering": 55,
4388
  "visual_reference_evaluation": 46
4389
  },
 
4395
  "physical_plausibility": 71.1,
4396
  "prompt_faithfulness": 45.5,
4397
  "rubric_adaptive": 44.0,
4398
+ "text_reference_evaluation": 24.0,
4399
  "text_rendering": 51.2,
4400
  "visual_reference_evaluation": 35.9
4401
  },
 
4419
  "physical_plausibility": 31,
4420
  "prompt_faithfulness": 56,
4421
  "rubric_adaptive": 56,
4422
+ "text_reference_evaluation": 52,
4423
  "text_rendering": 53,
4424
  "visual_reference_evaluation": 46
4425
  },
 
4431
  "physical_plausibility": 66.7,
4432
  "prompt_faithfulness": 42.3,
4433
  "rubric_adaptive": 39.8,
4434
+ "text_reference_evaluation": 19.6,
4435
  "text_rendering": 49.1,
4436
  "visual_reference_evaluation": 25.7
4437
  },
 
4455
  "physical_plausibility": 34,
4456
  "prompt_faithfulness": 56,
4457
  "rubric_adaptive": 56,
4458
+ "text_reference_evaluation": 52,
4459
  "text_rendering": 55,
4460
  "visual_reference_evaluation": 46
4461
  },
 
4467
  "physical_plausibility": 68.6,
4468
  "prompt_faithfulness": 31.8,
4469
  "rubric_adaptive": 34.3,
4470
+ "text_reference_evaluation": 15.7,
4471
  "text_rendering": 31.5,
4472
  "visual_reference_evaluation": 24.6
4473
  },
 
4491
  "physical_plausibility": 38,
4492
  "prompt_faithfulness": 56,
4493
  "rubric_adaptive": 56,
4494
+ "text_reference_evaluation": 53,
4495
  "text_rendering": 54,
4496
  "visual_reference_evaluation": 46
4497
  },
 
4503
  "physical_plausibility": 64.9,
4504
  "prompt_faithfulness": 27.1,
4505
  "rubric_adaptive": 26.6,
4506
+ "text_reference_evaluation": 7.5,
4507
  "text_rendering": 19.1,
4508
  "visual_reference_evaluation": 21.7
4509
  },
 
4527
  "physical_plausibility": 46,
4528
  "prompt_faithfulness": 56,
4529
  "rubric_adaptive": 56,
4530
+ "text_reference_evaluation": 55,
4531
  "text_rendering": 55,
4532
  "visual_reference_evaluation": 46
4533
  },
 
4539
  "physical_plausibility": 35.5,
4540
  "prompt_faithfulness": 8.0,
4541
  "rubric_adaptive": 13.1,
4542
+ "text_reference_evaluation": 4.8,
4543
  "text_rendering": 5.5,
4544
  "visual_reference_evaluation": 9.4
4545
  },
 
4563
  "physical_plausibility": 39,
4564
  "prompt_faithfulness": 56,
4565
  "rubric_adaptive": 56,
4566
+ "text_reference_evaluation": 55,
4567
  "text_rendering": 52,
4568
  "visual_reference_evaluation": 46
4569
  },
 
4575
  "physical_plausibility": 32.1,
4576
  "prompt_faithfulness": 6.0,
4577
  "rubric_adaptive": 9.1,
4578
+ "text_reference_evaluation": 2.1,
4579
  "text_rendering": 3.8,
4580
  "visual_reference_evaluation": 6.2
4581
  },
 
4599
  "physical_plausibility": 33,
4600
  "prompt_faithfulness": 56,
4601
  "rubric_adaptive": 56,
4602
+ "text_reference_evaluation": 56,
4603
  "text_rendering": 55,
4604
  "visual_reference_evaluation": 46
4605
  },
 
4611
  "physical_plausibility": 29.3,
4612
  "prompt_faithfulness": 3.0,
4613
  "rubric_adaptive": 6.3,
4614
+ "text_reference_evaluation": 1.2,
4615
  "text_rendering": 1.5,
4616
  "visual_reference_evaluation": 4.3
4617
  },
 
4635
  "physical_plausibility": 41,
4636
  "prompt_faithfulness": 56,
4637
  "rubric_adaptive": 56,
4638
+ "text_reference_evaluation": 54,
4639
  "text_rendering": 51,
4640
  "visual_reference_evaluation": 46
4641
  },
 
4647
  "physical_plausibility": 14.6,
4648
  "prompt_faithfulness": 2.7,
4649
  "rubric_adaptive": 5.2,
4650
+ "text_reference_evaluation": 0.3,
4651
  "text_rendering": 0.3,
4652
  "visual_reference_evaluation": 3.6
4653
  },
 
4671
  "physical_plausibility": 46,
4672
  "prompt_faithfulness": 56,
4673
  "rubric_adaptive": 56,
4674
+ "text_reference_evaluation": 54,
4675
  "text_rendering": 53,
4676
  "visual_reference_evaluation": 47
4677
  },
 
4683
  "physical_plausibility": 14.5,
4684
  "prompt_faithfulness": 1.8,
4685
  "rubric_adaptive": 2.9,
4686
+ "text_reference_evaluation": 0.0,
4687
  "text_rendering": 0.0,
4688
  "visual_reference_evaluation": 2.1
4689
  },
 
4709
  "physical_plausibility": 27,
4710
  "prompt_faithfulness": 33,
4711
  "rubric_adaptive": 33,
4712
+ "text_reference_evaluation": 18,
4713
  "text_rendering": 21,
4714
  "visual_reference_evaluation": 25
4715
  },
 
4721
  "physical_plausibility": 78.4,
4722
  "prompt_faithfulness": 67.2,
4723
  "rubric_adaptive": 68.6,
4724
+ "text_reference_evaluation": 44.4,
4725
  "text_rendering": 78.6,
4726
  "visual_reference_evaluation": 66.0
4727
  },
 
4745
  "physical_plausibility": 28,
4746
  "prompt_faithfulness": 33,
4747
  "rubric_adaptive": 33,
4748
+ "text_reference_evaluation": 16,
4749
  "text_rendering": 14,
4750
  "visual_reference_evaluation": 25
4751
  },
 
4757
  "physical_plausibility": 84.5,
4758
  "prompt_faithfulness": 58.1,
4759
  "rubric_adaptive": 62.7,
4760
+ "text_reference_evaluation": 46.9,
4761
  "text_rendering": 63.1,
4762
  "visual_reference_evaluation": 51.3
4763
  },
 
4772
  "overall_9": 67.1,
4773
  "type": "Commercial"
4774
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4775
  {
4776
  "component_counts": {
4777
  "ai_naturalness": 33,
 
4781
  "physical_plausibility": 24,
4782
  "prompt_faithfulness": 33,
4783
  "rubric_adaptive": 33,
4784
+ "text_reference_evaluation": 16,
4785
  "text_rendering": 15,
4786
  "visual_reference_evaluation": 26
4787
  },
 
4793
  "physical_plausibility": 75.0,
4794
  "prompt_faithfulness": 60.6,
4795
  "rubric_adaptive": 64.4,
4796
+ "text_reference_evaluation": 41.7,
4797
  "text_rendering": 60.0,
4798
  "visual_reference_evaluation": 56.4
4799
  },
 
4817
  "physical_plausibility": 23,
4818
  "prompt_faithfulness": 31,
4819
  "rubric_adaptive": 31,
4820
+ "text_reference_evaluation": 20,
4821
  "text_rendering": 18,
4822
  "visual_reference_evaluation": 28
4823
  },
 
4829
  "physical_plausibility": 64.5,
4830
  "prompt_faithfulness": 59.7,
4831
  "rubric_adaptive": 62.2,
4832
+ "text_reference_evaluation": 45.0,
4833
  "text_rendering": 75.9,
4834
  "visual_reference_evaluation": 60.7
4835
  },
 
4844
  "overall_9": 65.2,
4845
  "type": "Commercial"
4846
  },
4847
+ {
4848
+ "component_counts": {
4849
+ "ai_naturalness": 33,
4850
+ "checklist": 33,
4851
+ "composition_and_aesthetics": 33,
4852
+ "image_quality": 33,
4853
+ "physical_plausibility": 28,
4854
+ "prompt_faithfulness": 33,
4855
+ "rubric_adaptive": 33,
4856
+ "text_reference_evaluation": 20,
4857
+ "text_rendering": 15,
4858
+ "visual_reference_evaluation": 30
4859
+ },
4860
+ "components": {
4861
+ "ai_naturalness": 65.2,
4862
+ "checklist": 59.8,
4863
+ "composition_and_aesthetics": 75.8,
4864
+ "image_quality": 75.8,
4865
+ "physical_plausibility": 79.2,
4866
+ "prompt_faithfulness": 51.5,
4867
+ "rubric_adaptive": 58.2,
4868
+ "text_reference_evaluation": 40.8,
4869
+ "text_rendering": 78.9,
4870
+ "visual_reference_evaluation": 56.1
4871
+ },
4872
+ "coverage": 1.0,
4873
+ "display_name": "Qwen-Image-2",
4874
+ "missing_policy": "zero_fill",
4875
+ "model_id": "qwen2",
4876
+ "n_included": 33,
4877
+ "n_scored": 33,
4878
+ "n_total": 33,
4879
+ "overall_10": 63.9,
4880
+ "overall_9": 65.6,
4881
+ "type": "Commercial"
4882
+ },
4883
  {
4884
  "component_counts": {
4885
  "ai_naturalness": 33,
 
4889
  "physical_plausibility": 26,
4890
  "prompt_faithfulness": 33,
4891
  "rubric_adaptive": 33,
4892
+ "text_reference_evaluation": 18,
4893
  "text_rendering": 15,
4894
  "visual_reference_evaluation": 30
4895
  },
 
4901
  "physical_plausibility": 75.0,
4902
  "prompt_faithfulness": 51.5,
4903
  "rubric_adaptive": 55.8,
4904
+ "text_reference_evaluation": 41.7,
4905
  "text_rendering": 75.6,
4906
  "visual_reference_evaluation": 54.4
4907
  },
 
4925
  "physical_plausibility": 24,
4926
  "prompt_faithfulness": 33,
4927
  "rubric_adaptive": 33,
4928
+ "text_reference_evaluation": 16,
4929
  "text_rendering": 19,
4930
  "visual_reference_evaluation": 30
4931
  },
 
4937
  "physical_plausibility": 72.2,
4938
  "prompt_faithfulness": 52.5,
4939
  "rubric_adaptive": 58.6,
4940
+ "text_reference_evaluation": 38.5,
4941
  "text_rendering": 61.4,
4942
  "visual_reference_evaluation": 51.1
4943
  },
 
4961
  "physical_plausibility": 23,
4962
  "prompt_faithfulness": 33,
4963
  "rubric_adaptive": 33,
4964
+ "text_reference_evaluation": 22,
4965
  "text_rendering": 14,
4966
  "visual_reference_evaluation": 25
4967
  },
 
4973
  "physical_plausibility": 70.3,
4974
  "prompt_faithfulness": 43.4,
4975
  "rubric_adaptive": 49.2,
4976
+ "text_reference_evaluation": 26.5,
4977
  "text_rendering": 35.7,
4978
  "visual_reference_evaluation": 34.7
4979
  },
 
4997
  "physical_plausibility": 31,
4998
  "prompt_faithfulness": 33,
4999
  "rubric_adaptive": 33,
5000
+ "text_reference_evaluation": 21,
5001
  "text_rendering": 13,
5002
  "visual_reference_evaluation": 25
5003
  },
 
5009
  "physical_plausibility": 55.9,
5010
  "prompt_faithfulness": 22.0,
5011
  "rubric_adaptive": 29.3,
5012
+ "text_reference_evaluation": 7.1,
5013
  "text_rendering": 3.8,
5014
  "visual_reference_evaluation": 28.7
5015
  },
 
5033
  "physical_plausibility": 24,
5034
  "prompt_faithfulness": 33,
5035
  "rubric_adaptive": 33,
5036
+ "text_reference_evaluation": 21,
5037
  "text_rendering": 16,
5038
  "visual_reference_evaluation": 26
5039
  },
 
5045
  "physical_plausibility": 61.8,
5046
  "prompt_faithfulness": 20.7,
5047
  "rubric_adaptive": 29.2,
5048
+ "text_reference_evaluation": 7.1,
5049
  "text_rendering": 4.2,
5050
  "visual_reference_evaluation": 22.4
5051
  },
 
5069
  "physical_plausibility": 23,
5070
  "prompt_faithfulness": 33,
5071
  "rubric_adaptive": 33,
5072
+ "text_reference_evaluation": 22,
5073
  "text_rendering": 16,
5074
  "visual_reference_evaluation": 25
5075
  },
 
5081
  "physical_plausibility": 58.7,
5082
  "prompt_faithfulness": 13.1,
5083
  "rubric_adaptive": 23.1,
5084
+ "text_reference_evaluation": 2.3,
5085
  "text_rendering": 2.1,
5086
  "visual_reference_evaluation": 13.3
5087
  },
 
5105
  "physical_plausibility": 30,
5106
  "prompt_faithfulness": 33,
5107
  "rubric_adaptive": 33,
5108
+ "text_reference_evaluation": 20,
5109
  "text_rendering": 13,
5110
  "visual_reference_evaluation": 25
5111
  },
 
5117
  "physical_plausibility": 43.9,
5118
  "prompt_faithfulness": 17.7,
5119
  "rubric_adaptive": 22.6,
5120
+ "text_reference_evaluation": 6.7,
5121
  "text_rendering": 1.3,
5122
  "visual_reference_evaluation": 18.0
5123
  },
 
5141
  "physical_plausibility": 28,
5142
  "prompt_faithfulness": 33,
5143
  "rubric_adaptive": 33,
5144
+ "text_reference_evaluation": 22,
5145
  "text_rendering": 15,
5146
  "visual_reference_evaluation": 26
5147
  },
 
5153
  "physical_plausibility": 51.2,
5154
  "prompt_faithfulness": 14.6,
5155
  "rubric_adaptive": 21.6,
5156
+ "text_reference_evaluation": 6.1,
5157
  "text_rendering": 3.3,
5158
  "visual_reference_evaluation": 15.4
5159
  },
 
5179
  "physical_plausibility": 117,
5180
  "prompt_faithfulness": 185,
5181
  "rubric_adaptive": 185,
5182
+ "text_reference_evaluation": 133,
5183
  "text_rendering": 164,
5184
  "visual_reference_evaluation": 150
5185
  },
 
5191
  "physical_plausibility": 86.8,
5192
  "prompt_faithfulness": 76.1,
5193
  "rubric_adaptive": 75.5,
5194
+ "text_reference_evaluation": 59.3,
5195
  "text_rendering": 79.8,
5196
  "visual_reference_evaluation": 74.4
5197
  },
 
5215
  "physical_plausibility": 142,
5216
  "prompt_faithfulness": 185,
5217
  "rubric_adaptive": 185,
5218
+ "text_reference_evaluation": 139,
5219
  "text_rendering": 158,
5220
  "visual_reference_evaluation": 150
5221
  },
 
5227
  "physical_plausibility": 86.9,
5228
  "prompt_faithfulness": 66.1,
5229
  "rubric_adaptive": 67.7,
5230
+ "text_reference_evaluation": 52.5,
5231
  "text_rendering": 70.6,
5232
  "visual_reference_evaluation": 65.6
5233
  },
 
5251
  "physical_plausibility": 123,
5252
  "prompt_faithfulness": 180,
5253
  "rubric_adaptive": 180,
5254
+ "text_reference_evaluation": 140,
5255
  "text_rendering": 157,
5256
  "visual_reference_evaluation": 151
5257
  },
 
5263
  "physical_plausibility": 80.2,
5264
  "prompt_faithfulness": 63.4,
5265
  "rubric_adaptive": 64.8,
5266
+ "text_reference_evaluation": 50.0,
5267
  "text_rendering": 64.2,
5268
  "visual_reference_evaluation": 61.9
5269
  },
 
5287
  "physical_plausibility": 119,
5288
  "prompt_faithfulness": 183,
5289
  "rubric_adaptive": 183,
5290
+ "text_reference_evaluation": 137,
5291
  "text_rendering": 148,
5292
  "visual_reference_evaluation": 154
5293
  },
 
5299
  "physical_plausibility": 76.8,
5300
  "prompt_faithfulness": 51.4,
5301
  "rubric_adaptive": 54.2,
5302
+ "text_reference_evaluation": 39.2,
5303
  "text_rendering": 58.6,
5304
  "visual_reference_evaluation": 47.3
5305
  },
 
5323
  "physical_plausibility": 119,
5324
  "prompt_faithfulness": 185,
5325
  "rubric_adaptive": 185,
5326
+ "text_reference_evaluation": 147,
5327
  "text_rendering": 148,
5328
  "visual_reference_evaluation": 156
5329
  },
 
5335
  "physical_plausibility": 73.7,
5336
  "prompt_faithfulness": 49.0,
5337
  "rubric_adaptive": 52.4,
5338
+ "text_reference_evaluation": 37.6,
5339
  "text_rendering": 54.8,
5340
  "visual_reference_evaluation": 44.4
5341
  },
 
5359
  "physical_plausibility": 134,
5360
  "prompt_faithfulness": 185,
5361
  "rubric_adaptive": 185,
5362
+ "text_reference_evaluation": 142,
5363
  "text_rendering": 154,
5364
  "visual_reference_evaluation": 156
5365
  },
 
5371
  "physical_plausibility": 68.7,
5372
  "prompt_faithfulness": 45.5,
5373
  "rubric_adaptive": 49.4,
5374
+ "text_reference_evaluation": 32.0,
5375
  "text_rendering": 51.9,
5376
  "visual_reference_evaluation": 41.6
5377
  },
 
5395
  "physical_plausibility": 136,
5396
  "prompt_faithfulness": 185,
5397
  "rubric_adaptive": 185,
5398
+ "text_reference_evaluation": 149,
5399
  "text_rendering": 148,
5400
  "visual_reference_evaluation": 150
5401
  },
 
5407
  "physical_plausibility": 67.2,
5408
  "prompt_faithfulness": 37.8,
5409
  "rubric_adaptive": 43.8,
5410
+ "text_reference_evaluation": 24.8,
5411
  "text_rendering": 37.3,
5412
  "visual_reference_evaluation": 38.8
5413
  },
 
5431
  "physical_plausibility": 129,
5432
  "prompt_faithfulness": 185,
5433
  "rubric_adaptive": 185,
5434
+ "text_reference_evaluation": 153,
5435
  "text_rendering": 153,
5436
  "visual_reference_evaluation": 150
5437
  },
 
5443
  "physical_plausibility": 74.2,
5444
  "prompt_faithfulness": 36.8,
5445
  "rubric_adaptive": 41.1,
5446
+ "text_reference_evaluation": 18.8,
5447
  "text_rendering": 26.6,
5448
  "visual_reference_evaluation": 37.7
5449
  },
 
5467
  "physical_plausibility": 156,
5468
  "prompt_faithfulness": 185,
5469
  "rubric_adaptive": 185,
5470
+ "text_reference_evaluation": 150,
5471
  "text_rendering": 153,
5472
  "visual_reference_evaluation": 150
5473
  },
 
5479
  "physical_plausibility": 47.1,
5480
  "prompt_faithfulness": 18.9,
5481
  "rubric_adaptive": 24.3,
5482
+ "text_reference_evaluation": 8.4,
5483
  "text_rendering": 10.7,
5484
  "visual_reference_evaluation": 20.4
5485
  },
 
5503
  "physical_plausibility": 134,
5504
  "prompt_faithfulness": 185,
5505
  "rubric_adaptive": 185,
5506
+ "text_reference_evaluation": 159,
5507
  "text_rendering": 157,
5508
  "visual_reference_evaluation": 150
5509
  },
 
5515
  "physical_plausibility": 50.1,
5516
  "prompt_faithfulness": 17.2,
5517
  "rubric_adaptive": 22.6,
5518
+ "text_reference_evaluation": 5.8,
5519
  "text_rendering": 9.1,
5520
  "visual_reference_evaluation": 20.2
5521
  },
 
5539
  "physical_plausibility": 131,
5540
  "prompt_faithfulness": 184,
5541
  "rubric_adaptive": 185,
5542
+ "text_reference_evaluation": 157,
5543
  "text_rendering": 148,
5544
  "visual_reference_evaluation": 149
5545
  },
 
5551
  "physical_plausibility": 50.0,
5552
  "prompt_faithfulness": 12.1,
5553
  "rubric_adaptive": 18.1,
5554
+ "text_reference_evaluation": 3.5,
5555
  "text_rendering": 3.7,
5556
  "visual_reference_evaluation": 15.7
5557
  },
 
5575
  "physical_plausibility": 148,
5576
  "prompt_faithfulness": 185,
5577
  "rubric_adaptive": 185,
5578
+ "text_reference_evaluation": 153,
5579
  "text_rendering": 149,
5580
  "visual_reference_evaluation": 150
5581
  },
 
5587
  "physical_plausibility": 35.8,
5588
  "prompt_faithfulness": 10.7,
5589
  "rubric_adaptive": 14.6,
5590
+ "text_reference_evaluation": 1.5,
5591
  "text_rendering": 1.7,
5592
  "visual_reference_evaluation": 12.8
5593
  },
 
5611
  "physical_plausibility": 151,
5612
  "prompt_faithfulness": 185,
5613
  "rubric_adaptive": 185,
5614
+ "text_reference_evaluation": 161,
5615
  "text_rendering": 159,
5616
  "visual_reference_evaluation": 169
5617
  },
 
5623
  "physical_plausibility": 22.0,
5624
  "prompt_faithfulness": 6.3,
5625
  "rubric_adaptive": 9.5,
5626
+ "text_reference_evaluation": 1.3,
5627
  "text_rendering": 1.2,
5628
  "visual_reference_evaluation": 6.3
5629
  },
data/leaderboard_by_stratum.json CHANGED
@@ -9,6 +9,7 @@
9
  "physical_plausibility": 558,
10
  "prompt_faithfulness": 751,
11
  "rubric_adaptive": 751,
 
12
  "text_rendering": 544,
13
  "visual_reference_evaluation": 599
14
  },
@@ -20,6 +21,7 @@
20
  "physical_plausibility": 76.7,
21
  "prompt_faithfulness": 69.4,
22
  "rubric_adaptive": 70.8,
 
23
  "text_rendering": 75.4,
24
  "visual_reference_evaluation": 65.7
25
  },
@@ -43,6 +45,7 @@
43
  "physical_plausibility": 627,
44
  "prompt_faithfulness": 751,
45
  "rubric_adaptive": 751,
 
46
  "text_rendering": 500,
47
  "visual_reference_evaluation": 598
48
  },
@@ -54,6 +57,7 @@
54
  "physical_plausibility": 78.4,
55
  "prompt_faithfulness": 62.3,
56
  "rubric_adaptive": 65.1,
 
57
  "text_rendering": 66.3,
58
  "visual_reference_evaluation": 59.8
59
  },
@@ -77,6 +81,7 @@
77
  "physical_plausibility": 539,
78
  "prompt_faithfulness": 717,
79
  "rubric_adaptive": 717,
 
80
  "text_rendering": 517,
81
  "visual_reference_evaluation": 582
82
  },
@@ -88,6 +93,7 @@
88
  "physical_plausibility": 73.1,
89
  "prompt_faithfulness": 62.0,
90
  "rubric_adaptive": 64.1,
 
91
  "text_rendering": 63.4,
92
  "visual_reference_evaluation": 58.9
93
  },
@@ -111,6 +117,7 @@
111
  "physical_plausibility": 544,
112
  "prompt_faithfulness": 742,
113
  "rubric_adaptive": 742,
 
114
  "text_rendering": 471,
115
  "visual_reference_evaluation": 606
116
  },
@@ -122,6 +129,7 @@
122
  "physical_plausibility": 71.7,
123
  "prompt_faithfulness": 50.0,
124
  "rubric_adaptive": 54.2,
 
125
  "text_rendering": 56.7,
126
  "visual_reference_evaluation": 46.2
127
  },
@@ -145,6 +153,7 @@
145
  "physical_plausibility": 561,
146
  "prompt_faithfulness": 751,
147
  "rubric_adaptive": 751,
 
148
  "text_rendering": 467,
149
  "visual_reference_evaluation": 617
150
  },
@@ -156,6 +165,7 @@
156
  "physical_plausibility": 67.9,
157
  "prompt_faithfulness": 47.3,
158
  "rubric_adaptive": 51.9,
 
159
  "text_rendering": 54.0,
160
  "visual_reference_evaluation": 43.2
161
  },
@@ -179,6 +189,7 @@
179
  "physical_plausibility": 593,
180
  "prompt_faithfulness": 751,
181
  "rubric_adaptive": 751,
 
182
  "text_rendering": 518,
183
  "visual_reference_evaluation": 615
184
  },
@@ -190,6 +201,7 @@
190
  "physical_plausibility": 64.0,
191
  "prompt_faithfulness": 45.9,
192
  "rubric_adaptive": 50.2,
 
193
  "text_rendering": 48.9,
194
  "visual_reference_evaluation": 39.9
195
  },
@@ -213,6 +225,7 @@
213
  "physical_plausibility": 604,
214
  "prompt_faithfulness": 750,
215
  "rubric_adaptive": 751,
 
216
  "text_rendering": 483,
217
  "visual_reference_evaluation": 596
218
  },
@@ -224,6 +237,7 @@
224
  "physical_plausibility": 65.6,
225
  "prompt_faithfulness": 41.6,
226
  "rubric_adaptive": 47.2,
 
227
  "text_rendering": 38.1,
228
  "visual_reference_evaluation": 38.4
229
  },
@@ -247,6 +261,7 @@
247
  "physical_plausibility": 594,
248
  "prompt_faithfulness": 751,
249
  "rubric_adaptive": 751,
 
250
  "text_rendering": 498,
251
  "visual_reference_evaluation": 597
252
  },
@@ -258,6 +273,7 @@
258
  "physical_plausibility": 66.0,
259
  "prompt_faithfulness": 39.1,
260
  "rubric_adaptive": 44.0,
 
261
  "text_rendering": 28.9,
262
  "visual_reference_evaluation": 36.4
263
  },
@@ -281,6 +297,7 @@
281
  "physical_plausibility": 676,
282
  "prompt_faithfulness": 751,
283
  "rubric_adaptive": 751,
 
284
  "text_rendering": 475,
285
  "visual_reference_evaluation": 595
286
  },
@@ -292,6 +309,7 @@
292
  "physical_plausibility": 48.6,
293
  "prompt_faithfulness": 24.5,
294
  "rubric_adaptive": 30.5,
 
295
  "text_rendering": 11.3,
296
  "visual_reference_evaluation": 23.8
297
  },
@@ -315,6 +333,7 @@
315
  "physical_plausibility": 599,
316
  "prompt_faithfulness": 751,
317
  "rubric_adaptive": 751,
 
318
  "text_rendering": 501,
319
  "visual_reference_evaluation": 596
320
  },
@@ -326,6 +345,7 @@
326
  "physical_plausibility": 51.5,
327
  "prompt_faithfulness": 21.7,
328
  "rubric_adaptive": 27.9,
 
329
  "text_rendering": 8.4,
330
  "visual_reference_evaluation": 21.1
331
  },
@@ -349,6 +369,7 @@
349
  "physical_plausibility": 597,
350
  "prompt_faithfulness": 750,
351
  "rubric_adaptive": 751,
 
352
  "text_rendering": 483,
353
  "visual_reference_evaluation": 594
354
  },
@@ -360,6 +381,7 @@
360
  "physical_plausibility": 49.0,
361
  "prompt_faithfulness": 16.0,
362
  "rubric_adaptive": 22.9,
 
363
  "text_rendering": 4.7,
364
  "visual_reference_evaluation": 15.1
365
  },
@@ -383,6 +405,7 @@
383
  "physical_plausibility": 631,
384
  "prompt_faithfulness": 751,
385
  "rubric_adaptive": 751,
 
386
  "text_rendering": 465,
387
  "visual_reference_evaluation": 595
388
  },
@@ -394,6 +417,7 @@
394
  "physical_plausibility": 40.4,
395
  "prompt_faithfulness": 16.7,
396
  "rubric_adaptive": 21.8,
 
397
  "text_rendering": 3.5,
398
  "visual_reference_evaluation": 16.8
399
  },
@@ -417,6 +441,7 @@
417
  "physical_plausibility": 656,
418
  "prompt_faithfulness": 751,
419
  "rubric_adaptive": 751,
 
420
  "text_rendering": 596,
421
  "visual_reference_evaluation": 688
422
  },
@@ -428,6 +453,7 @@
428
  "physical_plausibility": 20.0,
429
  "prompt_faithfulness": 6.0,
430
  "rubric_adaptive": 8.7,
 
431
  "text_rendering": 1.2,
432
  "visual_reference_evaluation": 6.0
433
  },
@@ -453,6 +479,7 @@
453
  "physical_plausibility": 94,
454
  "prompt_faithfulness": 100,
455
  "rubric_adaptive": 100,
 
456
  "text_rendering": 33,
457
  "visual_reference_evaluation": 92
458
  },
@@ -464,6 +491,7 @@
464
  "physical_plausibility": 78.2,
465
  "prompt_faithfulness": 72.8,
466
  "rubric_adaptive": 78.1,
 
467
  "text_rendering": 85.9,
468
  "visual_reference_evaluation": 67.8
469
  },
@@ -487,6 +515,7 @@
487
  "physical_plausibility": 95,
488
  "prompt_faithfulness": 100,
489
  "rubric_adaptive": 100,
 
490
  "text_rendering": 32,
491
  "visual_reference_evaluation": 93
492
  },
@@ -498,6 +527,7 @@
498
  "physical_plausibility": 73.9,
499
  "prompt_faithfulness": 70.8,
500
  "rubric_adaptive": 75.6,
 
501
  "text_rendering": 67.7,
502
  "visual_reference_evaluation": 64.3
503
  },
@@ -521,6 +551,7 @@
521
  "physical_plausibility": 90,
522
  "prompt_faithfulness": 97,
523
  "rubric_adaptive": 97,
 
524
  "text_rendering": 33,
525
  "visual_reference_evaluation": 89
526
  },
@@ -532,6 +563,7 @@
532
  "physical_plausibility": 70.9,
533
  "prompt_faithfulness": 69.2,
534
  "rubric_adaptive": 74.2,
 
535
  "text_rendering": 71.2,
536
  "visual_reference_evaluation": 61.9
537
  },
@@ -555,6 +587,7 @@
555
  "physical_plausibility": 96,
556
  "prompt_faithfulness": 100,
557
  "rubric_adaptive": 100,
 
558
  "text_rendering": 23,
559
  "visual_reference_evaluation": 92
560
  },
@@ -566,6 +599,7 @@
566
  "physical_plausibility": 72.0,
567
  "prompt_faithfulness": 66.3,
568
  "rubric_adaptive": 73.2,
 
569
  "text_rendering": 76.1,
570
  "visual_reference_evaluation": 59.4
571
  },
@@ -589,6 +623,7 @@
589
  "physical_plausibility": 96,
590
  "prompt_faithfulness": 100,
591
  "rubric_adaptive": 100,
 
592
  "text_rendering": 26,
593
  "visual_reference_evaluation": 91
594
  },
@@ -600,6 +635,7 @@
600
  "physical_plausibility": 71.5,
601
  "prompt_faithfulness": 63.2,
602
  "rubric_adaptive": 69.9,
 
603
  "text_rendering": 76.9,
604
  "visual_reference_evaluation": 60.1
605
  },
@@ -623,6 +659,7 @@
623
  "physical_plausibility": 95,
624
  "prompt_faithfulness": 100,
625
  "rubric_adaptive": 100,
 
626
  "text_rendering": 30,
627
  "visual_reference_evaluation": 92
628
  },
@@ -634,6 +671,7 @@
634
  "physical_plausibility": 73.9,
635
  "prompt_faithfulness": 61.7,
636
  "rubric_adaptive": 70.6,
 
637
  "text_rendering": 71.1,
638
  "visual_reference_evaluation": 56.7
639
  },
@@ -657,6 +695,7 @@
657
  "physical_plausibility": 93,
658
  "prompt_faithfulness": 100,
659
  "rubric_adaptive": 100,
 
660
  "text_rendering": 23,
661
  "visual_reference_evaluation": 92
662
  },
@@ -668,6 +707,7 @@
668
  "physical_plausibility": 73.8,
669
  "prompt_faithfulness": 62.8,
670
  "rubric_adaptive": 70.8,
 
671
  "text_rendering": 63.0,
672
  "visual_reference_evaluation": 56.7
673
  },
@@ -691,6 +731,7 @@
691
  "physical_plausibility": 96,
692
  "prompt_faithfulness": 100,
693
  "rubric_adaptive": 100,
 
694
  "text_rendering": 37,
695
  "visual_reference_evaluation": 92
696
  },
@@ -702,6 +743,7 @@
702
  "physical_plausibility": 71.4,
703
  "prompt_faithfulness": 64.5,
704
  "rubric_adaptive": 71.0,
 
705
  "text_rendering": 68.0,
706
  "visual_reference_evaluation": 55.8
707
  },
@@ -725,6 +767,7 @@
725
  "physical_plausibility": 92,
726
  "prompt_faithfulness": 100,
727
  "rubric_adaptive": 100,
 
728
  "text_rendering": 30,
729
  "visual_reference_evaluation": 92
730
  },
@@ -736,6 +779,7 @@
736
  "physical_plausibility": 68.5,
737
  "prompt_faithfulness": 59.7,
738
  "rubric_adaptive": 67.5,
 
739
  "text_rendering": 42.8,
740
  "visual_reference_evaluation": 53.8
741
  },
@@ -759,6 +803,7 @@
759
  "physical_plausibility": 96,
760
  "prompt_faithfulness": 100,
761
  "rubric_adaptive": 100,
 
762
  "text_rendering": 25,
763
  "visual_reference_evaluation": 92
764
  },
@@ -770,6 +815,7 @@
770
  "physical_plausibility": 66.7,
771
  "prompt_faithfulness": 51.3,
772
  "rubric_adaptive": 59.8,
 
773
  "text_rendering": 31.3,
774
  "visual_reference_evaluation": 43.7
775
  },
@@ -793,6 +839,7 @@
793
  "physical_plausibility": 95,
794
  "prompt_faithfulness": 100,
795
  "rubric_adaptive": 100,
 
796
  "text_rendering": 24,
797
  "visual_reference_evaluation": 92
798
  },
@@ -804,6 +851,7 @@
804
  "physical_plausibility": 63.5,
805
  "prompt_faithfulness": 39.3,
806
  "rubric_adaptive": 51.8,
 
807
  "text_rendering": 13.2,
808
  "visual_reference_evaluation": 32.6
809
  },
@@ -827,6 +875,7 @@
827
  "physical_plausibility": 95,
828
  "prompt_faithfulness": 100,
829
  "rubric_adaptive": 100,
 
830
  "text_rendering": 29,
831
  "visual_reference_evaluation": 92
832
  },
@@ -838,6 +887,7 @@
838
  "physical_plausibility": 60.4,
839
  "prompt_faithfulness": 39.2,
840
  "rubric_adaptive": 49.1,
 
841
  "text_rendering": 18.4,
842
  "visual_reference_evaluation": 34.8
843
  },
@@ -861,6 +911,7 @@
861
  "physical_plausibility": 100,
862
  "prompt_faithfulness": 100,
863
  "rubric_adaptive": 100,
 
864
  "text_rendering": 100,
865
  "visual_reference_evaluation": 100
866
  },
@@ -872,6 +923,7 @@
872
  "physical_plausibility": 0.0,
873
  "prompt_faithfulness": 0.0,
874
  "rubric_adaptive": 0.0,
 
875
  "text_rendering": 0.0,
876
  "visual_reference_evaluation": 0.0
877
  },
@@ -897,6 +949,7 @@
897
  "physical_plausibility": 463,
898
  "prompt_faithfulness": 651,
899
  "rubric_adaptive": 651,
 
900
  "text_rendering": 512,
901
  "visual_reference_evaluation": 506
902
  },
@@ -908,6 +961,7 @@
908
  "physical_plausibility": 77.3,
909
  "prompt_faithfulness": 69.2,
910
  "rubric_adaptive": 70.1,
 
911
  "text_rendering": 75.9,
912
  "visual_reference_evaluation": 66.0
913
  },
@@ -931,6 +985,7 @@
931
  "physical_plausibility": 533,
932
  "prompt_faithfulness": 651,
933
  "rubric_adaptive": 651,
 
934
  "text_rendering": 467,
935
  "visual_reference_evaluation": 506
936
  },
@@ -942,6 +997,7 @@
942
  "physical_plausibility": 78.5,
943
  "prompt_faithfulness": 60.7,
944
  "rubric_adaptive": 63.1,
 
945
  "text_rendering": 65.0,
946
  "visual_reference_evaluation": 58.3
947
  },
@@ -965,6 +1021,7 @@
965
  "physical_plausibility": 449,
966
  "prompt_faithfulness": 620,
967
  "rubric_adaptive": 620,
 
968
  "text_rendering": 484,
969
  "visual_reference_evaluation": 493
970
  },
@@ -976,6 +1033,7 @@
976
  "physical_plausibility": 73.6,
977
  "prompt_faithfulness": 60.8,
978
  "rubric_adaptive": 62.5,
 
979
  "text_rendering": 62.8,
980
  "visual_reference_evaluation": 58.3
981
  },
@@ -999,6 +1057,7 @@
999
  "physical_plausibility": 448,
1000
  "prompt_faithfulness": 642,
1001
  "rubric_adaptive": 642,
 
1002
  "text_rendering": 445,
1003
  "visual_reference_evaluation": 515
1004
  },
@@ -1010,6 +1069,7 @@
1010
  "physical_plausibility": 71.8,
1011
  "prompt_faithfulness": 47.9,
1012
  "rubric_adaptive": 51.8,
 
1013
  "text_rendering": 55.5,
1014
  "visual_reference_evaluation": 43.8
1015
  },
@@ -1033,6 +1093,7 @@
1033
  "physical_plausibility": 465,
1034
  "prompt_faithfulness": 651,
1035
  "rubric_adaptive": 651,
 
1036
  "text_rendering": 444,
1037
  "visual_reference_evaluation": 525
1038
  },
@@ -1044,6 +1105,7 @@
1044
  "physical_plausibility": 67.1,
1045
  "prompt_faithfulness": 44.4,
1046
  "rubric_adaptive": 48.7,
 
1047
  "text_rendering": 52.9,
1048
  "visual_reference_evaluation": 40.3
1049
  },
@@ -1067,6 +1129,7 @@
1067
  "physical_plausibility": 497,
1068
  "prompt_faithfulness": 651,
1069
  "rubric_adaptive": 651,
 
1070
  "text_rendering": 481,
1071
  "visual_reference_evaluation": 523
1072
  },
@@ -1078,6 +1141,7 @@
1078
  "physical_plausibility": 62.6,
1079
  "prompt_faithfulness": 43.1,
1080
  "rubric_adaptive": 47.0,
 
1081
  "text_rendering": 47.5,
1082
  "visual_reference_evaluation": 37.1
1083
  },
@@ -1101,6 +1165,7 @@
1101
  "physical_plausibility": 509,
1102
  "prompt_faithfulness": 650,
1103
  "rubric_adaptive": 651,
 
1104
  "text_rendering": 453,
1105
  "visual_reference_evaluation": 504
1106
  },
@@ -1112,6 +1177,7 @@
1112
  "physical_plausibility": 64.0,
1113
  "prompt_faithfulness": 38.5,
1114
  "rubric_adaptive": 43.6,
 
1115
  "text_rendering": 35.9,
1116
  "visual_reference_evaluation": 35.1
1117
  },
@@ -1135,6 +1201,7 @@
1135
  "physical_plausibility": 502,
1136
  "prompt_faithfulness": 651,
1137
  "rubric_adaptive": 651,
 
1138
  "text_rendering": 468,
1139
  "visual_reference_evaluation": 505
1140
  },
@@ -1146,6 +1213,7 @@
1146
  "physical_plausibility": 65.5,
1147
  "prompt_faithfulness": 36.0,
1148
  "rubric_adaptive": 40.4,
 
1149
  "text_rendering": 28.0,
1150
  "visual_reference_evaluation": 33.2
1151
  },
@@ -1169,6 +1237,7 @@
1169
  "physical_plausibility": 583,
1170
  "prompt_faithfulness": 651,
1171
  "rubric_adaptive": 651,
 
1172
  "text_rendering": 452,
1173
  "visual_reference_evaluation": 503
1174
  },
@@ -1180,6 +1249,7 @@
1180
  "physical_plausibility": 44.6,
1181
  "prompt_faithfulness": 18.6,
1182
  "rubric_adaptive": 24.3,
 
1183
  "text_rendering": 8.7,
1184
  "visual_reference_evaluation": 17.7
1185
  },
@@ -1203,6 +1273,7 @@
1203
  "physical_plausibility": 503,
1204
  "prompt_faithfulness": 651,
1205
  "rubric_adaptive": 651,
 
1206
  "text_rendering": 476,
1207
  "visual_reference_evaluation": 504
1208
  },
@@ -1214,6 +1285,7 @@
1214
  "physical_plausibility": 48.6,
1215
  "prompt_faithfulness": 17.2,
1216
  "rubric_adaptive": 23.1,
 
1217
  "text_rendering": 7.2,
1218
  "visual_reference_evaluation": 16.9
1219
  },
@@ -1237,6 +1309,7 @@
1237
  "physical_plausibility": 502,
1238
  "prompt_faithfulness": 650,
1239
  "rubric_adaptive": 651,
 
1240
  "text_rendering": 459,
1241
  "visual_reference_evaluation": 502
1242
  },
@@ -1248,6 +1321,7 @@
1248
  "physical_plausibility": 46.2,
1249
  "prompt_faithfulness": 12.4,
1250
  "rubric_adaptive": 18.4,
 
1251
  "text_rendering": 4.2,
1252
  "visual_reference_evaluation": 11.9
1253
  },
@@ -1271,6 +1345,7 @@
1271
  "physical_plausibility": 536,
1272
  "prompt_faithfulness": 651,
1273
  "rubric_adaptive": 651,
 
1274
  "text_rendering": 436,
1275
  "visual_reference_evaluation": 503
1276
  },
@@ -1282,6 +1357,7 @@
1282
  "physical_plausibility": 36.8,
1283
  "prompt_faithfulness": 13.3,
1284
  "rubric_adaptive": 17.6,
 
1285
  "text_rendering": 2.5,
1286
  "visual_reference_evaluation": 13.5
1287
  },
@@ -1305,6 +1381,7 @@
1305
  "physical_plausibility": 556,
1306
  "prompt_faithfulness": 651,
1307
  "rubric_adaptive": 651,
 
1308
  "text_rendering": 496,
1309
  "visual_reference_evaluation": 588
1310
  },
@@ -1316,6 +1393,7 @@
1316
  "physical_plausibility": 23.7,
1317
  "prompt_faithfulness": 6.9,
1318
  "rubric_adaptive": 10.0,
 
1319
  "text_rendering": 1.4,
1320
  "visual_reference_evaluation": 7.0
1321
  },
@@ -1341,6 +1419,7 @@
1341
  "physical_plausibility": 158,
1342
  "prompt_faithfulness": 264,
1343
  "rubric_adaptive": 264,
 
1344
  "text_rendering": 252,
1345
  "visual_reference_evaluation": 173
1346
  },
@@ -1352,6 +1431,7 @@
1352
  "physical_plausibility": 89.1,
1353
  "prompt_faithfulness": 69.3,
1354
  "rubric_adaptive": 67.8,
 
1355
  "text_rendering": 70.1,
1356
  "visual_reference_evaluation": 66.7
1357
  },
@@ -1375,6 +1455,7 @@
1375
  "physical_plausibility": 214,
1376
  "prompt_faithfulness": 264,
1377
  "rubric_adaptive": 264,
 
1378
  "text_rendering": 244,
1379
  "visual_reference_evaluation": 173
1380
  },
@@ -1386,6 +1467,7 @@
1386
  "physical_plausibility": 86.2,
1387
  "prompt_faithfulness": 60.1,
1388
  "rubric_adaptive": 59.8,
 
1389
  "text_rendering": 59.6,
1390
  "visual_reference_evaluation": 54.4
1391
  },
@@ -1409,6 +1491,7 @@
1409
  "physical_plausibility": 171,
1410
  "prompt_faithfulness": 264,
1411
  "rubric_adaptive": 264,
 
1412
  "text_rendering": 248,
1413
  "visual_reference_evaluation": 172
1414
  },
@@ -1420,6 +1503,7 @@
1420
  "physical_plausibility": 85.0,
1421
  "prompt_faithfulness": 60.9,
1422
  "rubric_adaptive": 59.3,
 
1423
  "text_rendering": 57.0,
1424
  "visual_reference_evaluation": 54.8
1425
  },
@@ -1443,6 +1527,7 @@
1443
  "physical_plausibility": 155,
1444
  "prompt_faithfulness": 264,
1445
  "rubric_adaptive": 264,
 
1446
  "text_rendering": 249,
1447
  "visual_reference_evaluation": 172
1448
  },
@@ -1454,6 +1539,7 @@
1454
  "physical_plausibility": 83.1,
1455
  "prompt_faithfulness": 48.0,
1456
  "rubric_adaptive": 48.5,
 
1457
  "text_rendering": 47.3,
1458
  "visual_reference_evaluation": 37.1
1459
  },
@@ -1477,6 +1563,7 @@
1477
  "physical_plausibility": 157,
1478
  "prompt_faithfulness": 264,
1479
  "rubric_adaptive": 264,
 
1480
  "text_rendering": 244,
1481
  "visual_reference_evaluation": 172
1482
  },
@@ -1488,6 +1575,7 @@
1488
  "physical_plausibility": 80.4,
1489
  "prompt_faithfulness": 45.0,
1490
  "rubric_adaptive": 46.4,
 
1491
  "text_rendering": 45.4,
1492
  "visual_reference_evaluation": 34.4
1493
  },
@@ -1511,6 +1599,7 @@
1511
  "physical_plausibility": 189,
1512
  "prompt_faithfulness": 264,
1513
  "rubric_adaptive": 264,
 
1514
  "text_rendering": 256,
1515
  "visual_reference_evaluation": 172
1516
  },
@@ -1522,6 +1611,7 @@
1522
  "physical_plausibility": 69.6,
1523
  "prompt_faithfulness": 40.5,
1524
  "rubric_adaptive": 42.2,
 
1525
  "text_rendering": 41.4,
1526
  "visual_reference_evaluation": 27.2
1527
  },
@@ -1545,6 +1635,7 @@
1545
  "physical_plausibility": 197,
1546
  "prompt_faithfulness": 264,
1547
  "rubric_adaptive": 264,
 
1548
  "text_rendering": 250,
1549
  "visual_reference_evaluation": 172
1550
  },
@@ -1556,6 +1647,7 @@
1556
  "physical_plausibility": 72.3,
1557
  "prompt_faithfulness": 33.6,
1558
  "rubric_adaptive": 36.7,
 
1559
  "text_rendering": 30.1,
1560
  "visual_reference_evaluation": 24.0
1561
  },
@@ -1579,6 +1671,7 @@
1579
  "physical_plausibility": 188,
1580
  "prompt_faithfulness": 264,
1581
  "rubric_adaptive": 264,
 
1582
  "text_rendering": 254,
1583
  "visual_reference_evaluation": 172
1584
  },
@@ -1590,6 +1683,7 @@
1590
  "physical_plausibility": 75.5,
1591
  "prompt_faithfulness": 32.5,
1592
  "rubric_adaptive": 33.7,
 
1593
  "text_rendering": 22.1,
1594
  "visual_reference_evaluation": 25.0
1595
  },
@@ -1613,6 +1707,7 @@
1613
  "physical_plausibility": 233,
1614
  "prompt_faithfulness": 264,
1615
  "rubric_adaptive": 264,
 
1616
  "text_rendering": 253,
1617
  "visual_reference_evaluation": 172
1618
  },
@@ -1624,6 +1719,7 @@
1624
  "physical_plausibility": 44.3,
1625
  "prompt_faithfulness": 13.8,
1626
  "rubric_adaptive": 17.5,
 
1627
  "text_rendering": 5.4,
1628
  "visual_reference_evaluation": 10.4
1629
  },
@@ -1647,6 +1743,7 @@
1647
  "physical_plausibility": 198,
1648
  "prompt_faithfulness": 264,
1649
  "rubric_adaptive": 264,
 
1650
  "text_rendering": 254,
1651
  "visual_reference_evaluation": 172
1652
  },
@@ -1658,6 +1755,7 @@
1658
  "physical_plausibility": 48.7,
1659
  "prompt_faithfulness": 12.4,
1660
  "rubric_adaptive": 16.2,
 
1661
  "text_rendering": 3.9,
1662
  "visual_reference_evaluation": 9.9
1663
  },
@@ -1681,6 +1779,7 @@
1681
  "physical_plausibility": 201,
1682
  "prompt_faithfulness": 263,
1683
  "rubric_adaptive": 264,
 
1684
  "text_rendering": 249,
1685
  "visual_reference_evaluation": 171
1686
  },
@@ -1692,6 +1791,7 @@
1692
  "physical_plausibility": 44.6,
1693
  "prompt_faithfulness": 9.1,
1694
  "rubric_adaptive": 13.6,
 
1695
  "text_rendering": 2.8,
1696
  "visual_reference_evaluation": 7.2
1697
  },
@@ -1715,6 +1815,7 @@
1715
  "physical_plausibility": 203,
1716
  "prompt_faithfulness": 264,
1717
  "rubric_adaptive": 264,
 
1718
  "text_rendering": 244,
1719
  "visual_reference_evaluation": 172
1720
  },
@@ -1726,6 +1827,7 @@
1726
  "physical_plausibility": 37.8,
1727
  "prompt_faithfulness": 9.9,
1728
  "rubric_adaptive": 12.4,
 
1729
  "text_rendering": 1.6,
1730
  "visual_reference_evaluation": 9.3
1731
  },
@@ -1749,6 +1851,7 @@
1749
  "physical_plausibility": 216,
1750
  "prompt_faithfulness": 264,
1751
  "rubric_adaptive": 264,
 
1752
  "text_rendering": 249,
1753
  "visual_reference_evaluation": 239
1754
  },
@@ -1760,6 +1863,7 @@
1760
  "physical_plausibility": 8.1,
1761
  "prompt_faithfulness": 0.6,
1762
  "rubric_adaptive": 1.7,
 
1763
  "text_rendering": 0.0,
1764
  "visual_reference_evaluation": 0.1
1765
  },
@@ -1785,6 +1889,7 @@
1785
  "physical_plausibility": 305,
1786
  "prompt_faithfulness": 387,
1787
  "rubric_adaptive": 387,
 
1788
  "text_rendering": 260,
1789
  "visual_reference_evaluation": 333
1790
  },
@@ -1796,6 +1901,7 @@
1796
  "physical_plausibility": 71.2,
1797
  "prompt_faithfulness": 69.2,
1798
  "rubric_adaptive": 71.7,
 
1799
  "text_rendering": 81.5,
1800
  "visual_reference_evaluation": 65.7
1801
  },
@@ -1819,6 +1925,7 @@
1819
  "physical_plausibility": 319,
1820
  "prompt_faithfulness": 387,
1821
  "rubric_adaptive": 387,
 
1822
  "text_rendering": 223,
1823
  "visual_reference_evaluation": 333
1824
  },
@@ -1830,6 +1937,7 @@
1830
  "physical_plausibility": 73.3,
1831
  "prompt_faithfulness": 61.1,
1832
  "rubric_adaptive": 65.4,
 
1833
  "text_rendering": 70.8,
1834
  "visual_reference_evaluation": 60.4
1835
  },
@@ -1853,6 +1961,7 @@
1853
  "physical_plausibility": 278,
1854
  "prompt_faithfulness": 356,
1855
  "rubric_adaptive": 356,
 
1856
  "text_rendering": 236,
1857
  "visual_reference_evaluation": 321
1858
  },
@@ -1864,6 +1973,7 @@
1864
  "physical_plausibility": 66.5,
1865
  "prompt_faithfulness": 60.8,
1866
  "rubric_adaptive": 64.9,
 
1867
  "text_rendering": 69.0,
1868
  "visual_reference_evaluation": 60.2
1869
  },
@@ -1887,6 +1997,7 @@
1887
  "physical_plausibility": 293,
1888
  "prompt_faithfulness": 378,
1889
  "rubric_adaptive": 378,
 
1890
  "text_rendering": 196,
1891
  "visual_reference_evaluation": 343
1892
  },
@@ -1898,6 +2009,7 @@
1898
  "physical_plausibility": 65.8,
1899
  "prompt_faithfulness": 47.9,
1900
  "rubric_adaptive": 54.1,
 
1901
  "text_rendering": 66.0,
1902
  "visual_reference_evaluation": 47.2
1903
  },
@@ -1921,6 +2033,7 @@
1921
  "physical_plausibility": 308,
1922
  "prompt_faithfulness": 387,
1923
  "rubric_adaptive": 387,
 
1924
  "text_rendering": 200,
1925
  "visual_reference_evaluation": 353
1926
  },
@@ -1932,6 +2045,7 @@
1932
  "physical_plausibility": 60.3,
1933
  "prompt_faithfulness": 44.0,
1934
  "rubric_adaptive": 50.2,
 
1935
  "text_rendering": 62.0,
1936
  "visual_reference_evaluation": 43.2
1937
  },
@@ -1955,6 +2069,7 @@
1955
  "physical_plausibility": 308,
1956
  "prompt_faithfulness": 387,
1957
  "rubric_adaptive": 387,
 
1958
  "text_rendering": 225,
1959
  "visual_reference_evaluation": 351
1960
  },
@@ -1966,6 +2081,7 @@
1966
  "physical_plausibility": 58.3,
1967
  "prompt_faithfulness": 44.8,
1968
  "rubric_adaptive": 50.3,
 
1969
  "text_rendering": 54.4,
1970
  "visual_reference_evaluation": 41.9
1971
  },
@@ -1989,6 +2105,7 @@
1989
  "physical_plausibility": 312,
1990
  "prompt_faithfulness": 386,
1991
  "rubric_adaptive": 387,
 
1992
  "text_rendering": 203,
1993
  "visual_reference_evaluation": 332
1994
  },
@@ -2000,6 +2117,7 @@
2000
  "physical_plausibility": 58.8,
2001
  "prompt_faithfulness": 41.9,
2002
  "rubric_adaptive": 48.3,
 
2003
  "text_rendering": 43.2,
2004
  "visual_reference_evaluation": 40.8
2005
  },
@@ -2023,6 +2141,7 @@
2023
  "physical_plausibility": 314,
2024
  "prompt_faithfulness": 387,
2025
  "rubric_adaptive": 387,
 
2026
  "text_rendering": 214,
2027
  "visual_reference_evaluation": 333
2028
  },
@@ -2034,6 +2153,7 @@
2034
  "physical_plausibility": 59.5,
2035
  "prompt_faithfulness": 38.4,
2036
  "rubric_adaptive": 45.0,
 
2037
  "text_rendering": 35.0,
2038
  "visual_reference_evaluation": 37.4
2039
  },
@@ -2057,6 +2177,7 @@
2057
  "physical_plausibility": 350,
2058
  "prompt_faithfulness": 387,
2059
  "rubric_adaptive": 387,
 
2060
  "text_rendering": 199,
2061
  "visual_reference_evaluation": 331
2062
  },
@@ -2068,6 +2189,7 @@
2068
  "physical_plausibility": 44.8,
2069
  "prompt_faithfulness": 21.9,
2070
  "rubric_adaptive": 29.0,
 
2071
  "text_rendering": 12.8,
2072
  "visual_reference_evaluation": 21.6
2073
  },
@@ -2091,6 +2213,7 @@
2091
  "physical_plausibility": 305,
2092
  "prompt_faithfulness": 387,
2093
  "rubric_adaptive": 387,
 
2094
  "text_rendering": 222,
2095
  "visual_reference_evaluation": 332
2096
  },
@@ -2102,6 +2225,7 @@
2102
  "physical_plausibility": 48.5,
2103
  "prompt_faithfulness": 20.4,
2104
  "rubric_adaptive": 27.7,
 
2105
  "text_rendering": 11.0,
2106
  "visual_reference_evaluation": 20.6
2107
  },
@@ -2125,6 +2249,7 @@
2125
  "physical_plausibility": 301,
2126
  "prompt_faithfulness": 387,
2127
  "rubric_adaptive": 387,
 
2128
  "text_rendering": 210,
2129
  "visual_reference_evaluation": 331
2130
  },
@@ -2136,6 +2261,7 @@
2136
  "physical_plausibility": 47.3,
2137
  "prompt_faithfulness": 14.7,
2138
  "rubric_adaptive": 21.7,
 
2139
  "text_rendering": 6.0,
2140
  "visual_reference_evaluation": 14.3
2141
  },
@@ -2159,6 +2285,7 @@
2159
  "physical_plausibility": 333,
2160
  "prompt_faithfulness": 387,
2161
  "rubric_adaptive": 387,
 
2162
  "text_rendering": 192,
2163
  "visual_reference_evaluation": 331
2164
  },
@@ -2170,6 +2297,7 @@
2170
  "physical_plausibility": 36.2,
2171
  "prompt_faithfulness": 15.5,
2172
  "rubric_adaptive": 21.2,
 
2173
  "text_rendering": 3.6,
2174
  "visual_reference_evaluation": 15.7
2175
  },
@@ -2193,6 +2321,7 @@
2193
  "physical_plausibility": 340,
2194
  "prompt_faithfulness": 387,
2195
  "rubric_adaptive": 387,
 
2196
  "text_rendering": 247,
2197
  "visual_reference_evaluation": 349
2198
  },
@@ -2204,6 +2333,7 @@
2204
  "physical_plausibility": 33.5,
2205
  "prompt_faithfulness": 11.2,
2206
  "rubric_adaptive": 15.7,
 
2207
  "text_rendering": 2.8,
2208
  "visual_reference_evaluation": 11.7
2209
  },
 
9
  "physical_plausibility": 558,
10
  "prompt_faithfulness": 751,
11
  "rubric_adaptive": 751,
12
+ "text_reference_evaluation": 486,
13
  "text_rendering": 544,
14
  "visual_reference_evaluation": 599
15
  },
 
21
  "physical_plausibility": 76.7,
22
  "prompt_faithfulness": 69.4,
23
  "rubric_adaptive": 70.8,
24
+ "text_reference_evaluation": 54.6,
25
  "text_rendering": 75.4,
26
  "visual_reference_evaluation": 65.7
27
  },
 
45
  "physical_plausibility": 627,
46
  "prompt_faithfulness": 751,
47
  "rubric_adaptive": 751,
48
+ "text_reference_evaluation": 480,
49
  "text_rendering": 500,
50
  "visual_reference_evaluation": 598
51
  },
 
57
  "physical_plausibility": 78.4,
58
  "prompt_faithfulness": 62.3,
59
  "rubric_adaptive": 65.1,
60
+ "text_reference_evaluation": 47.4,
61
  "text_rendering": 66.3,
62
  "visual_reference_evaluation": 59.8
63
  },
 
81
  "physical_plausibility": 539,
82
  "prompt_faithfulness": 717,
83
  "rubric_adaptive": 717,
84
+ "text_reference_evaluation": 487,
85
  "text_rendering": 517,
86
  "visual_reference_evaluation": 582
87
  },
 
93
  "physical_plausibility": 73.1,
94
  "prompt_faithfulness": 62.0,
95
  "rubric_adaptive": 64.1,
96
+ "text_reference_evaluation": 46.0,
97
  "text_rendering": 63.4,
98
  "visual_reference_evaluation": 58.9
99
  },
 
117
  "physical_plausibility": 544,
118
  "prompt_faithfulness": 742,
119
  "rubric_adaptive": 742,
120
+ "text_reference_evaluation": 473,
121
  "text_rendering": 471,
122
  "visual_reference_evaluation": 606
123
  },
 
129
  "physical_plausibility": 71.7,
130
  "prompt_faithfulness": 50.0,
131
  "rubric_adaptive": 54.2,
132
+ "text_reference_evaluation": 35.7,
133
  "text_rendering": 56.7,
134
  "visual_reference_evaluation": 46.2
135
  },
 
153
  "physical_plausibility": 561,
154
  "prompt_faithfulness": 751,
155
  "rubric_adaptive": 751,
156
+ "text_reference_evaluation": 492,
157
  "text_rendering": 467,
158
  "visual_reference_evaluation": 617
159
  },
 
165
  "physical_plausibility": 67.9,
166
  "prompt_faithfulness": 47.3,
167
  "rubric_adaptive": 51.9,
168
+ "text_reference_evaluation": 33.1,
169
  "text_rendering": 54.0,
170
  "visual_reference_evaluation": 43.2
171
  },
 
189
  "physical_plausibility": 593,
190
  "prompt_faithfulness": 751,
191
  "rubric_adaptive": 751,
192
+ "text_reference_evaluation": 486,
193
  "text_rendering": 518,
194
  "visual_reference_evaluation": 615
195
  },
 
201
  "physical_plausibility": 64.0,
202
  "prompt_faithfulness": 45.9,
203
  "rubric_adaptive": 50.2,
204
+ "text_reference_evaluation": 28.2,
205
  "text_rendering": 48.9,
206
  "visual_reference_evaluation": 39.9
207
  },
 
225
  "physical_plausibility": 604,
226
  "prompt_faithfulness": 750,
227
  "rubric_adaptive": 751,
228
+ "text_reference_evaluation": 501,
229
  "text_rendering": 483,
230
  "visual_reference_evaluation": 596
231
  },
 
237
  "physical_plausibility": 65.6,
238
  "prompt_faithfulness": 41.6,
239
  "rubric_adaptive": 47.2,
240
+ "text_reference_evaluation": 23.4,
241
  "text_rendering": 38.1,
242
  "visual_reference_evaluation": 38.4
243
  },
 
261
  "physical_plausibility": 594,
262
  "prompt_faithfulness": 751,
263
  "rubric_adaptive": 751,
264
+ "text_reference_evaluation": 522,
265
  "text_rendering": 498,
266
  "visual_reference_evaluation": 597
267
  },
 
273
  "physical_plausibility": 66.0,
274
  "prompt_faithfulness": 39.1,
275
  "rubric_adaptive": 44.0,
276
+ "text_reference_evaluation": 17.8,
277
  "text_rendering": 28.9,
278
  "visual_reference_evaluation": 36.4
279
  },
 
297
  "physical_plausibility": 676,
298
  "prompt_faithfulness": 751,
299
  "rubric_adaptive": 751,
300
+ "text_reference_evaluation": 516,
301
  "text_rendering": 475,
302
  "visual_reference_evaluation": 595
303
  },
 
309
  "physical_plausibility": 48.6,
310
  "prompt_faithfulness": 24.5,
311
  "rubric_adaptive": 30.5,
312
+ "text_reference_evaluation": 7.7,
313
  "text_rendering": 11.3,
314
  "visual_reference_evaluation": 23.8
315
  },
 
333
  "physical_plausibility": 599,
334
  "prompt_faithfulness": 751,
335
  "rubric_adaptive": 751,
336
+ "text_reference_evaluation": 536,
337
  "text_rendering": 501,
338
  "visual_reference_evaluation": 596
339
  },
 
345
  "physical_plausibility": 51.5,
346
  "prompt_faithfulness": 21.7,
347
  "rubric_adaptive": 27.9,
348
+ "text_reference_evaluation": 6.6,
349
  "text_rendering": 8.4,
350
  "visual_reference_evaluation": 21.1
351
  },
 
369
  "physical_plausibility": 597,
370
  "prompt_faithfulness": 750,
371
  "rubric_adaptive": 751,
372
+ "text_reference_evaluation": 537,
373
  "text_rendering": 483,
374
  "visual_reference_evaluation": 594
375
  },
 
381
  "physical_plausibility": 49.0,
382
  "prompt_faithfulness": 16.0,
383
  "rubric_adaptive": 22.9,
384
+ "text_reference_evaluation": 3.6,
385
  "text_rendering": 4.7,
386
  "visual_reference_evaluation": 15.1
387
  },
 
405
  "physical_plausibility": 631,
406
  "prompt_faithfulness": 751,
407
  "rubric_adaptive": 751,
408
+ "text_reference_evaluation": 521,
409
  "text_rendering": 465,
410
  "visual_reference_evaluation": 595
411
  },
 
417
  "physical_plausibility": 40.4,
418
  "prompt_faithfulness": 16.7,
419
  "rubric_adaptive": 21.8,
420
+ "text_reference_evaluation": 3.5,
421
  "text_rendering": 3.5,
422
  "visual_reference_evaluation": 16.8
423
  },
 
441
  "physical_plausibility": 656,
442
  "prompt_faithfulness": 751,
443
  "rubric_adaptive": 751,
444
+ "text_reference_evaluation": 630,
445
  "text_rendering": 596,
446
  "visual_reference_evaluation": 688
447
  },
 
453
  "physical_plausibility": 20.0,
454
  "prompt_faithfulness": 6.0,
455
  "rubric_adaptive": 8.7,
456
+ "text_reference_evaluation": 1.2,
457
  "text_rendering": 1.2,
458
  "visual_reference_evaluation": 6.0
459
  },
 
479
  "physical_plausibility": 94,
480
  "prompt_faithfulness": 100,
481
  "rubric_adaptive": 100,
482
+ "text_reference_evaluation": 35,
483
  "text_rendering": 33,
484
  "visual_reference_evaluation": 92
485
  },
 
491
  "physical_plausibility": 78.2,
492
  "prompt_faithfulness": 72.8,
493
  "rubric_adaptive": 78.1,
494
+ "text_reference_evaluation": 59.5,
495
  "text_rendering": 85.9,
496
  "visual_reference_evaluation": 67.8
497
  },
 
515
  "physical_plausibility": 95,
516
  "prompt_faithfulness": 100,
517
  "rubric_adaptive": 100,
518
+ "text_reference_evaluation": 38,
519
  "text_rendering": 32,
520
  "visual_reference_evaluation": 93
521
  },
 
527
  "physical_plausibility": 73.9,
528
  "prompt_faithfulness": 70.8,
529
  "rubric_adaptive": 75.6,
530
+ "text_reference_evaluation": 48.2,
531
  "text_rendering": 67.7,
532
  "visual_reference_evaluation": 64.3
533
  },
 
551
  "physical_plausibility": 90,
552
  "prompt_faithfulness": 97,
553
  "rubric_adaptive": 97,
554
+ "text_reference_evaluation": 33,
555
  "text_rendering": 33,
556
  "visual_reference_evaluation": 89
557
  },
 
563
  "physical_plausibility": 70.9,
564
  "prompt_faithfulness": 69.2,
565
  "rubric_adaptive": 74.2,
566
+ "text_reference_evaluation": 47.0,
567
  "text_rendering": 71.2,
568
  "visual_reference_evaluation": 61.9
569
  },
 
587
  "physical_plausibility": 96,
588
  "prompt_faithfulness": 100,
589
  "rubric_adaptive": 100,
590
+ "text_reference_evaluation": 34,
591
  "text_rendering": 23,
592
  "visual_reference_evaluation": 92
593
  },
 
599
  "physical_plausibility": 72.0,
600
  "prompt_faithfulness": 66.3,
601
  "rubric_adaptive": 73.2,
602
+ "text_reference_evaluation": 45.1,
603
  "text_rendering": 76.1,
604
  "visual_reference_evaluation": 59.4
605
  },
 
623
  "physical_plausibility": 96,
624
  "prompt_faithfulness": 100,
625
  "rubric_adaptive": 100,
626
+ "text_reference_evaluation": 37,
627
  "text_rendering": 26,
628
  "visual_reference_evaluation": 91
629
  },
 
635
  "physical_plausibility": 71.5,
636
  "prompt_faithfulness": 63.2,
637
  "rubric_adaptive": 69.9,
638
+ "text_reference_evaluation": 47.7,
639
  "text_rendering": 76.9,
640
  "visual_reference_evaluation": 60.1
641
  },
 
659
  "physical_plausibility": 95,
660
  "prompt_faithfulness": 100,
661
  "rubric_adaptive": 100,
662
+ "text_reference_evaluation": 38,
663
  "text_rendering": 30,
664
  "visual_reference_evaluation": 92
665
  },
 
671
  "physical_plausibility": 73.9,
672
  "prompt_faithfulness": 61.7,
673
  "rubric_adaptive": 70.6,
674
+ "text_reference_evaluation": 45.2,
675
  "text_rendering": 71.1,
676
  "visual_reference_evaluation": 56.7
677
  },
 
695
  "physical_plausibility": 93,
696
  "prompt_faithfulness": 100,
697
  "rubric_adaptive": 100,
698
+ "text_reference_evaluation": 38,
699
  "text_rendering": 23,
700
  "visual_reference_evaluation": 92
701
  },
 
707
  "physical_plausibility": 73.8,
708
  "prompt_faithfulness": 62.8,
709
  "rubric_adaptive": 70.8,
710
+ "text_reference_evaluation": 41.2,
711
  "text_rendering": 63.0,
712
  "visual_reference_evaluation": 56.7
713
  },
 
731
  "physical_plausibility": 96,
732
  "prompt_faithfulness": 100,
733
  "rubric_adaptive": 100,
734
+ "text_reference_evaluation": 35,
735
  "text_rendering": 37,
736
  "visual_reference_evaluation": 92
737
  },
 
743
  "physical_plausibility": 71.4,
744
  "prompt_faithfulness": 64.5,
745
  "rubric_adaptive": 71.0,
746
+ "text_reference_evaluation": 43.3,
747
  "text_rendering": 68.0,
748
  "visual_reference_evaluation": 55.8
749
  },
 
767
  "physical_plausibility": 92,
768
  "prompt_faithfulness": 100,
769
  "rubric_adaptive": 100,
770
+ "text_reference_evaluation": 40,
771
  "text_rendering": 30,
772
  "visual_reference_evaluation": 92
773
  },
 
779
  "physical_plausibility": 68.5,
780
  "prompt_faithfulness": 59.7,
781
  "rubric_adaptive": 67.5,
782
+ "text_reference_evaluation": 26.2,
783
  "text_rendering": 42.8,
784
  "visual_reference_evaluation": 53.8
785
  },
 
803
  "physical_plausibility": 96,
804
  "prompt_faithfulness": 100,
805
  "rubric_adaptive": 100,
806
+ "text_reference_evaluation": 42,
807
  "text_rendering": 25,
808
  "visual_reference_evaluation": 92
809
  },
 
815
  "physical_plausibility": 66.7,
816
  "prompt_faithfulness": 51.3,
817
  "rubric_adaptive": 59.8,
818
+ "text_reference_evaluation": 22.2,
819
  "text_rendering": 31.3,
820
  "visual_reference_evaluation": 43.7
821
  },
 
839
  "physical_plausibility": 95,
840
  "prompt_faithfulness": 100,
841
  "rubric_adaptive": 100,
842
+ "text_reference_evaluation": 40,
843
  "text_rendering": 24,
844
  "visual_reference_evaluation": 92
845
  },
 
851
  "physical_plausibility": 63.5,
852
  "prompt_faithfulness": 39.3,
853
  "rubric_adaptive": 51.8,
854
+ "text_reference_evaluation": 19.6,
855
  "text_rendering": 13.2,
856
  "visual_reference_evaluation": 32.6
857
  },
 
875
  "physical_plausibility": 95,
876
  "prompt_faithfulness": 100,
877
  "rubric_adaptive": 100,
878
+ "text_reference_evaluation": 42,
879
  "text_rendering": 29,
880
  "visual_reference_evaluation": 92
881
  },
 
887
  "physical_plausibility": 60.4,
888
  "prompt_faithfulness": 39.2,
889
  "rubric_adaptive": 49.1,
890
+ "text_reference_evaluation": 21.4,
891
  "text_rendering": 18.4,
892
  "visual_reference_evaluation": 34.8
893
  },
 
911
  "physical_plausibility": 100,
912
  "prompt_faithfulness": 100,
913
  "rubric_adaptive": 100,
914
+ "text_reference_evaluation": 100,
915
  "text_rendering": 100,
916
  "visual_reference_evaluation": 100
917
  },
 
923
  "physical_plausibility": 0.0,
924
  "prompt_faithfulness": 0.0,
925
  "rubric_adaptive": 0.0,
926
+ "text_reference_evaluation": 0.0,
927
  "text_rendering": 0.0,
928
  "visual_reference_evaluation": 0.0
929
  },
 
949
  "physical_plausibility": 463,
950
  "prompt_faithfulness": 651,
951
  "rubric_adaptive": 651,
952
+ "text_reference_evaluation": 448,
953
  "text_rendering": 512,
954
  "visual_reference_evaluation": 506
955
  },
 
961
  "physical_plausibility": 77.3,
962
  "prompt_faithfulness": 69.2,
963
  "rubric_adaptive": 70.1,
964
+ "text_reference_evaluation": 55.1,
965
  "text_rendering": 75.9,
966
  "visual_reference_evaluation": 66.0
967
  },
 
985
  "physical_plausibility": 533,
986
  "prompt_faithfulness": 651,
987
  "rubric_adaptive": 651,
988
+ "text_reference_evaluation": 445,
989
  "text_rendering": 467,
990
  "visual_reference_evaluation": 506
991
  },
 
997
  "physical_plausibility": 78.5,
998
  "prompt_faithfulness": 60.7,
999
  "rubric_adaptive": 63.1,
1000
+ "text_reference_evaluation": 46.4,
1001
  "text_rendering": 65.0,
1002
  "visual_reference_evaluation": 58.3
1003
  },
 
1021
  "physical_plausibility": 449,
1022
  "prompt_faithfulness": 620,
1023
  "rubric_adaptive": 620,
1024
+ "text_reference_evaluation": 454,
1025
  "text_rendering": 484,
1026
  "visual_reference_evaluation": 493
1027
  },
 
1033
  "physical_plausibility": 73.6,
1034
  "prompt_faithfulness": 60.8,
1035
  "rubric_adaptive": 62.5,
1036
+ "text_reference_evaluation": 46.0,
1037
  "text_rendering": 62.8,
1038
  "visual_reference_evaluation": 58.3
1039
  },
 
1057
  "physical_plausibility": 448,
1058
  "prompt_faithfulness": 642,
1059
  "rubric_adaptive": 642,
1060
+ "text_reference_evaluation": 436,
1061
  "text_rendering": 445,
1062
  "visual_reference_evaluation": 515
1063
  },
 
1069
  "physical_plausibility": 71.8,
1070
  "prompt_faithfulness": 47.9,
1071
  "rubric_adaptive": 51.8,
1072
+ "text_reference_evaluation": 34.7,
1073
  "text_rendering": 55.5,
1074
  "visual_reference_evaluation": 43.8
1075
  },
 
1093
  "physical_plausibility": 465,
1094
  "prompt_faithfulness": 651,
1095
  "rubric_adaptive": 651,
1096
+ "text_reference_evaluation": 458,
1097
  "text_rendering": 444,
1098
  "visual_reference_evaluation": 525
1099
  },
 
1105
  "physical_plausibility": 67.1,
1106
  "prompt_faithfulness": 44.4,
1107
  "rubric_adaptive": 48.7,
1108
+ "text_reference_evaluation": 32.2,
1109
  "text_rendering": 52.9,
1110
  "visual_reference_evaluation": 40.3
1111
  },
 
1129
  "physical_plausibility": 497,
1130
  "prompt_faithfulness": 651,
1131
  "rubric_adaptive": 651,
1132
+ "text_reference_evaluation": 451,
1133
  "text_rendering": 481,
1134
  "visual_reference_evaluation": 523
1135
  },
 
1141
  "physical_plausibility": 62.6,
1142
  "prompt_faithfulness": 43.1,
1143
  "rubric_adaptive": 47.0,
1144
+ "text_reference_evaluation": 27.0,
1145
  "text_rendering": 47.5,
1146
  "visual_reference_evaluation": 37.1
1147
  },
 
1165
  "physical_plausibility": 509,
1166
  "prompt_faithfulness": 650,
1167
  "rubric_adaptive": 651,
1168
+ "text_reference_evaluation": 463,
1169
  "text_rendering": 453,
1170
  "visual_reference_evaluation": 504
1171
  },
 
1177
  "physical_plausibility": 64.0,
1178
  "prompt_faithfulness": 38.5,
1179
  "rubric_adaptive": 43.6,
1180
+ "text_reference_evaluation": 21.6,
1181
  "text_rendering": 35.9,
1182
  "visual_reference_evaluation": 35.1
1183
  },
 
1201
  "physical_plausibility": 502,
1202
  "prompt_faithfulness": 651,
1203
  "rubric_adaptive": 651,
1204
+ "text_reference_evaluation": 482,
1205
  "text_rendering": 468,
1206
  "visual_reference_evaluation": 505
1207
  },
 
1213
  "physical_plausibility": 65.5,
1214
  "prompt_faithfulness": 36.0,
1215
  "rubric_adaptive": 40.4,
1216
+ "text_reference_evaluation": 17.1,
1217
  "text_rendering": 28.0,
1218
  "visual_reference_evaluation": 33.2
1219
  },
 
1237
  "physical_plausibility": 583,
1238
  "prompt_faithfulness": 651,
1239
  "rubric_adaptive": 651,
1240
+ "text_reference_evaluation": 478,
1241
  "text_rendering": 452,
1242
  "visual_reference_evaluation": 503
1243
  },
 
1249
  "physical_plausibility": 44.6,
1250
  "prompt_faithfulness": 18.6,
1251
  "rubric_adaptive": 24.3,
1252
+ "text_reference_evaluation": 5.0,
1253
  "text_rendering": 8.7,
1254
  "visual_reference_evaluation": 17.7
1255
  },
 
1273
  "physical_plausibility": 503,
1274
  "prompt_faithfulness": 651,
1275
  "rubric_adaptive": 651,
1276
+ "text_reference_evaluation": 494,
1277
  "text_rendering": 476,
1278
  "visual_reference_evaluation": 504
1279
  },
 
1285
  "physical_plausibility": 48.6,
1286
  "prompt_faithfulness": 17.2,
1287
  "rubric_adaptive": 23.1,
1288
+ "text_reference_evaluation": 5.3,
1289
  "text_rendering": 7.2,
1290
  "visual_reference_evaluation": 16.9
1291
  },
 
1309
  "physical_plausibility": 502,
1310
  "prompt_faithfulness": 650,
1311
  "rubric_adaptive": 651,
1312
+ "text_reference_evaluation": 497,
1313
  "text_rendering": 459,
1314
  "visual_reference_evaluation": 502
1315
  },
 
1321
  "physical_plausibility": 46.2,
1322
  "prompt_faithfulness": 12.4,
1323
  "rubric_adaptive": 18.4,
1324
+ "text_reference_evaluation": 2.3,
1325
  "text_rendering": 4.2,
1326
  "visual_reference_evaluation": 11.9
1327
  },
 
1345
  "physical_plausibility": 536,
1346
  "prompt_faithfulness": 651,
1347
  "rubric_adaptive": 651,
1348
+ "text_reference_evaluation": 479,
1349
  "text_rendering": 436,
1350
  "visual_reference_evaluation": 503
1351
  },
 
1357
  "physical_plausibility": 36.8,
1358
  "prompt_faithfulness": 13.3,
1359
  "rubric_adaptive": 17.6,
1360
+ "text_reference_evaluation": 1.9,
1361
  "text_rendering": 2.5,
1362
  "visual_reference_evaluation": 13.5
1363
  },
 
1381
  "physical_plausibility": 556,
1382
  "prompt_faithfulness": 651,
1383
  "rubric_adaptive": 651,
1384
+ "text_reference_evaluation": 530,
1385
  "text_rendering": 496,
1386
  "visual_reference_evaluation": 588
1387
  },
 
1393
  "physical_plausibility": 23.7,
1394
  "prompt_faithfulness": 6.9,
1395
  "rubric_adaptive": 10.0,
1396
+ "text_reference_evaluation": 1.4,
1397
  "text_rendering": 1.4,
1398
  "visual_reference_evaluation": 7.0
1399
  },
 
1419
  "physical_plausibility": 158,
1420
  "prompt_faithfulness": 264,
1421
  "rubric_adaptive": 264,
1422
+ "text_reference_evaluation": 254,
1423
  "text_rendering": 252,
1424
  "visual_reference_evaluation": 173
1425
  },
 
1431
  "physical_plausibility": 89.1,
1432
  "prompt_faithfulness": 69.3,
1433
  "rubric_adaptive": 67.8,
1434
+ "text_reference_evaluation": 48.5,
1435
  "text_rendering": 70.1,
1436
  "visual_reference_evaluation": 66.7
1437
  },
 
1455
  "physical_plausibility": 214,
1456
  "prompt_faithfulness": 264,
1457
  "rubric_adaptive": 264,
1458
+ "text_reference_evaluation": 255,
1459
  "text_rendering": 244,
1460
  "visual_reference_evaluation": 173
1461
  },
 
1467
  "physical_plausibility": 86.2,
1468
  "prompt_faithfulness": 60.1,
1469
  "rubric_adaptive": 59.8,
1470
+ "text_reference_evaluation": 39.5,
1471
  "text_rendering": 59.6,
1472
  "visual_reference_evaluation": 54.4
1473
  },
 
1491
  "physical_plausibility": 171,
1492
  "prompt_faithfulness": 264,
1493
  "rubric_adaptive": 264,
1494
+ "text_reference_evaluation": 260,
1495
  "text_rendering": 248,
1496
  "visual_reference_evaluation": 172
1497
  },
 
1503
  "physical_plausibility": 85.0,
1504
  "prompt_faithfulness": 60.9,
1505
  "rubric_adaptive": 59.3,
1506
+ "text_reference_evaluation": 39.5,
1507
  "text_rendering": 57.0,
1508
  "visual_reference_evaluation": 54.8
1509
  },
 
1527
  "physical_plausibility": 155,
1528
  "prompt_faithfulness": 264,
1529
  "rubric_adaptive": 264,
1530
+ "text_reference_evaluation": 258,
1531
  "text_rendering": 249,
1532
  "visual_reference_evaluation": 172
1533
  },
 
1539
  "physical_plausibility": 83.1,
1540
  "prompt_faithfulness": 48.0,
1541
  "rubric_adaptive": 48.5,
1542
+ "text_reference_evaluation": 29.7,
1543
  "text_rendering": 47.3,
1544
  "visual_reference_evaluation": 37.1
1545
  },
 
1563
  "physical_plausibility": 157,
1564
  "prompt_faithfulness": 264,
1565
  "rubric_adaptive": 264,
1566
+ "text_reference_evaluation": 258,
1567
  "text_rendering": 244,
1568
  "visual_reference_evaluation": 172
1569
  },
 
1575
  "physical_plausibility": 80.4,
1576
  "prompt_faithfulness": 45.0,
1577
  "rubric_adaptive": 46.4,
1578
+ "text_reference_evaluation": 26.2,
1579
  "text_rendering": 45.4,
1580
  "visual_reference_evaluation": 34.4
1581
  },
 
1599
  "physical_plausibility": 189,
1600
  "prompt_faithfulness": 264,
1601
  "rubric_adaptive": 264,
1602
+ "text_reference_evaluation": 257,
1603
  "text_rendering": 256,
1604
  "visual_reference_evaluation": 172
1605
  },
 
1611
  "physical_plausibility": 69.6,
1612
  "prompt_faithfulness": 40.5,
1613
  "rubric_adaptive": 42.2,
1614
+ "text_reference_evaluation": 22.4,
1615
  "text_rendering": 41.4,
1616
  "visual_reference_evaluation": 27.2
1617
  },
 
1635
  "physical_plausibility": 197,
1636
  "prompt_faithfulness": 264,
1637
  "rubric_adaptive": 264,
1638
+ "text_reference_evaluation": 260,
1639
  "text_rendering": 250,
1640
  "visual_reference_evaluation": 172
1641
  },
 
1647
  "physical_plausibility": 72.3,
1648
  "prompt_faithfulness": 33.6,
1649
  "rubric_adaptive": 36.7,
1650
+ "text_reference_evaluation": 16.3,
1651
  "text_rendering": 30.1,
1652
  "visual_reference_evaluation": 24.0
1653
  },
 
1671
  "physical_plausibility": 188,
1672
  "prompt_faithfulness": 264,
1673
  "rubric_adaptive": 264,
1674
+ "text_reference_evaluation": 261,
1675
  "text_rendering": 254,
1676
  "visual_reference_evaluation": 172
1677
  },
 
1683
  "physical_plausibility": 75.5,
1684
  "prompt_faithfulness": 32.5,
1685
  "rubric_adaptive": 33.7,
1686
+ "text_reference_evaluation": 12.1,
1687
  "text_rendering": 22.1,
1688
  "visual_reference_evaluation": 25.0
1689
  },
 
1707
  "physical_plausibility": 233,
1708
  "prompt_faithfulness": 264,
1709
  "rubric_adaptive": 264,
1710
+ "text_reference_evaluation": 264,
1711
  "text_rendering": 253,
1712
  "visual_reference_evaluation": 172
1713
  },
 
1719
  "physical_plausibility": 44.3,
1720
  "prompt_faithfulness": 13.8,
1721
  "rubric_adaptive": 17.5,
1722
+ "text_reference_evaluation": 3.5,
1723
  "text_rendering": 5.4,
1724
  "visual_reference_evaluation": 10.4
1725
  },
 
1743
  "physical_plausibility": 198,
1744
  "prompt_faithfulness": 264,
1745
  "rubric_adaptive": 264,
1746
+ "text_reference_evaluation": 263,
1747
  "text_rendering": 254,
1748
  "visual_reference_evaluation": 172
1749
  },
 
1755
  "physical_plausibility": 48.7,
1756
  "prompt_faithfulness": 12.4,
1757
  "rubric_adaptive": 16.2,
1758
+ "text_reference_evaluation": 3.6,
1759
  "text_rendering": 3.9,
1760
  "visual_reference_evaluation": 9.9
1761
  },
 
1779
  "physical_plausibility": 201,
1780
  "prompt_faithfulness": 263,
1781
  "rubric_adaptive": 264,
1782
+ "text_reference_evaluation": 262,
1783
  "text_rendering": 249,
1784
  "visual_reference_evaluation": 171
1785
  },
 
1791
  "physical_plausibility": 44.6,
1792
  "prompt_faithfulness": 9.1,
1793
  "rubric_adaptive": 13.6,
1794
+ "text_reference_evaluation": 1.7,
1795
  "text_rendering": 2.8,
1796
  "visual_reference_evaluation": 7.2
1797
  },
 
1815
  "physical_plausibility": 203,
1816
  "prompt_faithfulness": 264,
1817
  "rubric_adaptive": 264,
1818
+ "text_reference_evaluation": 264,
1819
  "text_rendering": 244,
1820
  "visual_reference_evaluation": 172
1821
  },
 
1827
  "physical_plausibility": 37.8,
1828
  "prompt_faithfulness": 9.9,
1829
  "rubric_adaptive": 12.4,
1830
+ "text_reference_evaluation": 1.1,
1831
  "text_rendering": 1.6,
1832
  "visual_reference_evaluation": 9.3
1833
  },
 
1851
  "physical_plausibility": 216,
1852
  "prompt_faithfulness": 264,
1853
  "rubric_adaptive": 264,
1854
+ "text_reference_evaluation": 264,
1855
  "text_rendering": 249,
1856
  "visual_reference_evaluation": 239
1857
  },
 
1863
  "physical_plausibility": 8.1,
1864
  "prompt_faithfulness": 0.6,
1865
  "rubric_adaptive": 1.7,
1866
+ "text_reference_evaluation": 0.2,
1867
  "text_rendering": 0.0,
1868
  "visual_reference_evaluation": 0.1
1869
  },
 
1889
  "physical_plausibility": 305,
1890
  "prompt_faithfulness": 387,
1891
  "rubric_adaptive": 387,
1892
+ "text_reference_evaluation": 194,
1893
  "text_rendering": 260,
1894
  "visual_reference_evaluation": 333
1895
  },
 
1901
  "physical_plausibility": 71.2,
1902
  "prompt_faithfulness": 69.2,
1903
  "rubric_adaptive": 71.7,
1904
+ "text_reference_evaluation": 63.7,
1905
  "text_rendering": 81.5,
1906
  "visual_reference_evaluation": 65.7
1907
  },
 
1925
  "physical_plausibility": 319,
1926
  "prompt_faithfulness": 387,
1927
  "rubric_adaptive": 387,
1928
+ "text_reference_evaluation": 190,
1929
  "text_rendering": 223,
1930
  "visual_reference_evaluation": 333
1931
  },
 
1937
  "physical_plausibility": 73.3,
1938
  "prompt_faithfulness": 61.1,
1939
  "rubric_adaptive": 65.4,
1940
+ "text_reference_evaluation": 55.6,
1941
  "text_rendering": 70.8,
1942
  "visual_reference_evaluation": 60.4
1943
  },
 
1961
  "physical_plausibility": 278,
1962
  "prompt_faithfulness": 356,
1963
  "rubric_adaptive": 356,
1964
+ "text_reference_evaluation": 194,
1965
  "text_rendering": 236,
1966
  "visual_reference_evaluation": 321
1967
  },
 
1973
  "physical_plausibility": 66.5,
1974
  "prompt_faithfulness": 60.8,
1975
  "rubric_adaptive": 64.9,
1976
+ "text_reference_evaluation": 54.6,
1977
  "text_rendering": 69.0,
1978
  "visual_reference_evaluation": 60.2
1979
  },
 
1997
  "physical_plausibility": 293,
1998
  "prompt_faithfulness": 378,
1999
  "rubric_adaptive": 378,
2000
+ "text_reference_evaluation": 178,
2001
  "text_rendering": 196,
2002
  "visual_reference_evaluation": 343
2003
  },
 
2009
  "physical_plausibility": 65.8,
2010
  "prompt_faithfulness": 47.9,
2011
  "rubric_adaptive": 54.1,
2012
+ "text_reference_evaluation": 41.9,
2013
  "text_rendering": 66.0,
2014
  "visual_reference_evaluation": 47.2
2015
  },
 
2033
  "physical_plausibility": 308,
2034
  "prompt_faithfulness": 387,
2035
  "rubric_adaptive": 387,
2036
+ "text_reference_evaluation": 200,
2037
  "text_rendering": 200,
2038
  "visual_reference_evaluation": 353
2039
  },
 
2045
  "physical_plausibility": 60.3,
2046
  "prompt_faithfulness": 44.0,
2047
  "rubric_adaptive": 50.2,
2048
+ "text_reference_evaluation": 39.9,
2049
  "text_rendering": 62.0,
2050
  "visual_reference_evaluation": 43.2
2051
  },
 
2069
  "physical_plausibility": 308,
2070
  "prompt_faithfulness": 387,
2071
  "rubric_adaptive": 387,
2072
+ "text_reference_evaluation": 194,
2073
  "text_rendering": 225,
2074
  "visual_reference_evaluation": 351
2075
  },
 
2081
  "physical_plausibility": 58.3,
2082
  "prompt_faithfulness": 44.8,
2083
  "rubric_adaptive": 50.3,
2084
+ "text_reference_evaluation": 33.2,
2085
  "text_rendering": 54.4,
2086
  "visual_reference_evaluation": 41.9
2087
  },
 
2105
  "physical_plausibility": 312,
2106
  "prompt_faithfulness": 386,
2107
  "rubric_adaptive": 387,
2108
+ "text_reference_evaluation": 203,
2109
  "text_rendering": 203,
2110
  "visual_reference_evaluation": 332
2111
  },
 
2117
  "physical_plausibility": 58.8,
2118
  "prompt_faithfulness": 41.9,
2119
  "rubric_adaptive": 48.3,
2120
+ "text_reference_evaluation": 28.5,
2121
  "text_rendering": 43.2,
2122
  "visual_reference_evaluation": 40.8
2123
  },
 
2141
  "physical_plausibility": 314,
2142
  "prompt_faithfulness": 387,
2143
  "rubric_adaptive": 387,
2144
+ "text_reference_evaluation": 221,
2145
  "text_rendering": 214,
2146
  "visual_reference_evaluation": 333
2147
  },
 
2153
  "physical_plausibility": 59.5,
2154
  "prompt_faithfulness": 38.4,
2155
  "rubric_adaptive": 45.0,
2156
+ "text_reference_evaluation": 23.0,
2157
  "text_rendering": 35.0,
2158
  "visual_reference_evaluation": 37.4
2159
  },
 
2177
  "physical_plausibility": 350,
2178
  "prompt_faithfulness": 387,
2179
  "rubric_adaptive": 387,
2180
+ "text_reference_evaluation": 214,
2181
  "text_rendering": 199,
2182
  "visual_reference_evaluation": 331
2183
  },
 
2189
  "physical_plausibility": 44.8,
2190
  "prompt_faithfulness": 21.9,
2191
  "rubric_adaptive": 29.0,
2192
+ "text_reference_evaluation": 6.9,
2193
  "text_rendering": 12.8,
2194
  "visual_reference_evaluation": 21.6
2195
  },
 
2213
  "physical_plausibility": 305,
2214
  "prompt_faithfulness": 387,
2215
  "rubric_adaptive": 387,
2216
+ "text_reference_evaluation": 231,
2217
  "text_rendering": 222,
2218
  "visual_reference_evaluation": 332
2219
  },
 
2225
  "physical_plausibility": 48.5,
2226
  "prompt_faithfulness": 20.4,
2227
  "rubric_adaptive": 27.7,
2228
+ "text_reference_evaluation": 7.2,
2229
  "text_rendering": 11.0,
2230
  "visual_reference_evaluation": 20.6
2231
  },
 
2249
  "physical_plausibility": 301,
2250
  "prompt_faithfulness": 387,
2251
  "rubric_adaptive": 387,
2252
+ "text_reference_evaluation": 235,
2253
  "text_rendering": 210,
2254
  "visual_reference_evaluation": 331
2255
  },
 
2261
  "physical_plausibility": 47.3,
2262
  "prompt_faithfulness": 14.7,
2263
  "rubric_adaptive": 21.7,
2264
+ "text_reference_evaluation": 3.0,
2265
  "text_rendering": 6.0,
2266
  "visual_reference_evaluation": 14.3
2267
  },
 
2285
  "physical_plausibility": 333,
2286
  "prompt_faithfulness": 387,
2287
  "rubric_adaptive": 387,
2288
+ "text_reference_evaluation": 215,
2289
  "text_rendering": 192,
2290
  "visual_reference_evaluation": 331
2291
  },
 
2297
  "physical_plausibility": 36.2,
2298
  "prompt_faithfulness": 15.5,
2299
  "rubric_adaptive": 21.2,
2300
+ "text_reference_evaluation": 2.9,
2301
  "text_rendering": 3.6,
2302
  "visual_reference_evaluation": 15.7
2303
  },
 
2321
  "physical_plausibility": 340,
2322
  "prompt_faithfulness": 387,
2323
  "rubric_adaptive": 387,
2324
+ "text_reference_evaluation": 266,
2325
  "text_rendering": 247,
2326
  "visual_reference_evaluation": 349
2327
  },
 
2333
  "physical_plausibility": 33.5,
2334
  "prompt_faithfulness": 11.2,
2335
  "rubric_adaptive": 15.7,
2336
+ "text_reference_evaluation": 2.6,
2337
  "text_rendering": 2.8,
2338
  "visual_reference_evaluation": 11.7
2339
  },
data/leaderboard_overall.json CHANGED
@@ -8,6 +8,7 @@
8
  "physical_plausibility": 558,
9
  "prompt_faithfulness": 751,
10
  "rubric_adaptive": 751,
 
11
  "text_rendering": 544,
12
  "visual_reference_evaluation": 599
13
  },
@@ -19,6 +20,7 @@
19
  "physical_plausibility": 76.7,
20
  "prompt_faithfulness": 69.4,
21
  "rubric_adaptive": 70.8,
 
22
  "text_rendering": 75.4,
23
  "visual_reference_evaluation": 65.7
24
  },
@@ -42,6 +44,7 @@
42
  "physical_plausibility": 627,
43
  "prompt_faithfulness": 751,
44
  "rubric_adaptive": 751,
 
45
  "text_rendering": 500,
46
  "visual_reference_evaluation": 598
47
  },
@@ -53,6 +56,7 @@
53
  "physical_plausibility": 78.4,
54
  "prompt_faithfulness": 62.3,
55
  "rubric_adaptive": 65.1,
 
56
  "text_rendering": 66.3,
57
  "visual_reference_evaluation": 59.8
58
  },
@@ -76,6 +80,7 @@
76
  "physical_plausibility": 539,
77
  "prompt_faithfulness": 717,
78
  "rubric_adaptive": 717,
 
79
  "text_rendering": 517,
80
  "visual_reference_evaluation": 582
81
  },
@@ -87,6 +92,7 @@
87
  "physical_plausibility": 73.1,
88
  "prompt_faithfulness": 62.0,
89
  "rubric_adaptive": 64.1,
 
90
  "text_rendering": 63.4,
91
  "visual_reference_evaluation": 58.9
92
  },
@@ -110,6 +116,7 @@
110
  "physical_plausibility": 544,
111
  "prompt_faithfulness": 742,
112
  "rubric_adaptive": 742,
 
113
  "text_rendering": 471,
114
  "visual_reference_evaluation": 606
115
  },
@@ -121,6 +128,7 @@
121
  "physical_plausibility": 71.7,
122
  "prompt_faithfulness": 50.0,
123
  "rubric_adaptive": 54.2,
 
124
  "text_rendering": 56.7,
125
  "visual_reference_evaluation": 46.2
126
  },
@@ -144,6 +152,7 @@
144
  "physical_plausibility": 561,
145
  "prompt_faithfulness": 751,
146
  "rubric_adaptive": 751,
 
147
  "text_rendering": 467,
148
  "visual_reference_evaluation": 617
149
  },
@@ -155,6 +164,7 @@
155
  "physical_plausibility": 67.9,
156
  "prompt_faithfulness": 47.3,
157
  "rubric_adaptive": 51.9,
 
158
  "text_rendering": 54.0,
159
  "visual_reference_evaluation": 43.2
160
  },
@@ -178,6 +188,7 @@
178
  "physical_plausibility": 593,
179
  "prompt_faithfulness": 751,
180
  "rubric_adaptive": 751,
 
181
  "text_rendering": 518,
182
  "visual_reference_evaluation": 615
183
  },
@@ -189,6 +200,7 @@
189
  "physical_plausibility": 64.0,
190
  "prompt_faithfulness": 45.9,
191
  "rubric_adaptive": 50.2,
 
192
  "text_rendering": 48.9,
193
  "visual_reference_evaluation": 39.9
194
  },
@@ -212,6 +224,7 @@
212
  "physical_plausibility": 604,
213
  "prompt_faithfulness": 750,
214
  "rubric_adaptive": 751,
 
215
  "text_rendering": 483,
216
  "visual_reference_evaluation": 596
217
  },
@@ -223,6 +236,7 @@
223
  "physical_plausibility": 65.6,
224
  "prompt_faithfulness": 41.6,
225
  "rubric_adaptive": 47.2,
 
226
  "text_rendering": 38.1,
227
  "visual_reference_evaluation": 38.4
228
  },
@@ -246,6 +260,7 @@
246
  "physical_plausibility": 594,
247
  "prompt_faithfulness": 751,
248
  "rubric_adaptive": 751,
 
249
  "text_rendering": 498,
250
  "visual_reference_evaluation": 597
251
  },
@@ -257,6 +272,7 @@
257
  "physical_plausibility": 66.0,
258
  "prompt_faithfulness": 39.1,
259
  "rubric_adaptive": 44.0,
 
260
  "text_rendering": 28.9,
261
  "visual_reference_evaluation": 36.4
262
  },
@@ -280,6 +296,7 @@
280
  "physical_plausibility": 676,
281
  "prompt_faithfulness": 751,
282
  "rubric_adaptive": 751,
 
283
  "text_rendering": 475,
284
  "visual_reference_evaluation": 595
285
  },
@@ -291,6 +308,7 @@
291
  "physical_plausibility": 48.6,
292
  "prompt_faithfulness": 24.5,
293
  "rubric_adaptive": 30.5,
 
294
  "text_rendering": 11.3,
295
  "visual_reference_evaluation": 23.8
296
  },
@@ -314,6 +332,7 @@
314
  "physical_plausibility": 599,
315
  "prompt_faithfulness": 751,
316
  "rubric_adaptive": 751,
 
317
  "text_rendering": 501,
318
  "visual_reference_evaluation": 596
319
  },
@@ -325,6 +344,7 @@
325
  "physical_plausibility": 51.5,
326
  "prompt_faithfulness": 21.7,
327
  "rubric_adaptive": 27.9,
 
328
  "text_rendering": 8.4,
329
  "visual_reference_evaluation": 21.1
330
  },
@@ -348,6 +368,7 @@
348
  "physical_plausibility": 597,
349
  "prompt_faithfulness": 750,
350
  "rubric_adaptive": 751,
 
351
  "text_rendering": 483,
352
  "visual_reference_evaluation": 594
353
  },
@@ -359,6 +380,7 @@
359
  "physical_plausibility": 49.0,
360
  "prompt_faithfulness": 16.0,
361
  "rubric_adaptive": 22.9,
 
362
  "text_rendering": 4.7,
363
  "visual_reference_evaluation": 15.1
364
  },
@@ -382,6 +404,7 @@
382
  "physical_plausibility": 631,
383
  "prompt_faithfulness": 751,
384
  "rubric_adaptive": 751,
 
385
  "text_rendering": 465,
386
  "visual_reference_evaluation": 595
387
  },
@@ -393,6 +416,7 @@
393
  "physical_plausibility": 40.4,
394
  "prompt_faithfulness": 16.7,
395
  "rubric_adaptive": 21.8,
 
396
  "text_rendering": 3.5,
397
  "visual_reference_evaluation": 16.8
398
  },
@@ -416,6 +440,7 @@
416
  "physical_plausibility": 656,
417
  "prompt_faithfulness": 751,
418
  "rubric_adaptive": 751,
 
419
  "text_rendering": 596,
420
  "visual_reference_evaluation": 688
421
  },
@@ -427,6 +452,7 @@
427
  "physical_plausibility": 20.0,
428
  "prompt_faithfulness": 6.0,
429
  "rubric_adaptive": 8.7,
 
430
  "text_rendering": 1.2,
431
  "visual_reference_evaluation": 6.0
432
  },
 
8
  "physical_plausibility": 558,
9
  "prompt_faithfulness": 751,
10
  "rubric_adaptive": 751,
11
+ "text_reference_evaluation": 486,
12
  "text_rendering": 544,
13
  "visual_reference_evaluation": 599
14
  },
 
20
  "physical_plausibility": 76.7,
21
  "prompt_faithfulness": 69.4,
22
  "rubric_adaptive": 70.8,
23
+ "text_reference_evaluation": 54.6,
24
  "text_rendering": 75.4,
25
  "visual_reference_evaluation": 65.7
26
  },
 
44
  "physical_plausibility": 627,
45
  "prompt_faithfulness": 751,
46
  "rubric_adaptive": 751,
47
+ "text_reference_evaluation": 480,
48
  "text_rendering": 500,
49
  "visual_reference_evaluation": 598
50
  },
 
56
  "physical_plausibility": 78.4,
57
  "prompt_faithfulness": 62.3,
58
  "rubric_adaptive": 65.1,
59
+ "text_reference_evaluation": 47.4,
60
  "text_rendering": 66.3,
61
  "visual_reference_evaluation": 59.8
62
  },
 
80
  "physical_plausibility": 539,
81
  "prompt_faithfulness": 717,
82
  "rubric_adaptive": 717,
83
+ "text_reference_evaluation": 487,
84
  "text_rendering": 517,
85
  "visual_reference_evaluation": 582
86
  },
 
92
  "physical_plausibility": 73.1,
93
  "prompt_faithfulness": 62.0,
94
  "rubric_adaptive": 64.1,
95
+ "text_reference_evaluation": 46.0,
96
  "text_rendering": 63.4,
97
  "visual_reference_evaluation": 58.9
98
  },
 
116
  "physical_plausibility": 544,
117
  "prompt_faithfulness": 742,
118
  "rubric_adaptive": 742,
119
+ "text_reference_evaluation": 473,
120
  "text_rendering": 471,
121
  "visual_reference_evaluation": 606
122
  },
 
128
  "physical_plausibility": 71.7,
129
  "prompt_faithfulness": 50.0,
130
  "rubric_adaptive": 54.2,
131
+ "text_reference_evaluation": 35.7,
132
  "text_rendering": 56.7,
133
  "visual_reference_evaluation": 46.2
134
  },
 
152
  "physical_plausibility": 561,
153
  "prompt_faithfulness": 751,
154
  "rubric_adaptive": 751,
155
+ "text_reference_evaluation": 492,
156
  "text_rendering": 467,
157
  "visual_reference_evaluation": 617
158
  },
 
164
  "physical_plausibility": 67.9,
165
  "prompt_faithfulness": 47.3,
166
  "rubric_adaptive": 51.9,
167
+ "text_reference_evaluation": 33.1,
168
  "text_rendering": 54.0,
169
  "visual_reference_evaluation": 43.2
170
  },
 
188
  "physical_plausibility": 593,
189
  "prompt_faithfulness": 751,
190
  "rubric_adaptive": 751,
191
+ "text_reference_evaluation": 486,
192
  "text_rendering": 518,
193
  "visual_reference_evaluation": 615
194
  },
 
200
  "physical_plausibility": 64.0,
201
  "prompt_faithfulness": 45.9,
202
  "rubric_adaptive": 50.2,
203
+ "text_reference_evaluation": 28.2,
204
  "text_rendering": 48.9,
205
  "visual_reference_evaluation": 39.9
206
  },
 
224
  "physical_plausibility": 604,
225
  "prompt_faithfulness": 750,
226
  "rubric_adaptive": 751,
227
+ "text_reference_evaluation": 501,
228
  "text_rendering": 483,
229
  "visual_reference_evaluation": 596
230
  },
 
236
  "physical_plausibility": 65.6,
237
  "prompt_faithfulness": 41.6,
238
  "rubric_adaptive": 47.2,
239
+ "text_reference_evaluation": 23.4,
240
  "text_rendering": 38.1,
241
  "visual_reference_evaluation": 38.4
242
  },
 
260
  "physical_plausibility": 594,
261
  "prompt_faithfulness": 751,
262
  "rubric_adaptive": 751,
263
+ "text_reference_evaluation": 522,
264
  "text_rendering": 498,
265
  "visual_reference_evaluation": 597
266
  },
 
272
  "physical_plausibility": 66.0,
273
  "prompt_faithfulness": 39.1,
274
  "rubric_adaptive": 44.0,
275
+ "text_reference_evaluation": 17.8,
276
  "text_rendering": 28.9,
277
  "visual_reference_evaluation": 36.4
278
  },
 
296
  "physical_plausibility": 676,
297
  "prompt_faithfulness": 751,
298
  "rubric_adaptive": 751,
299
+ "text_reference_evaluation": 516,
300
  "text_rendering": 475,
301
  "visual_reference_evaluation": 595
302
  },
 
308
  "physical_plausibility": 48.6,
309
  "prompt_faithfulness": 24.5,
310
  "rubric_adaptive": 30.5,
311
+ "text_reference_evaluation": 7.7,
312
  "text_rendering": 11.3,
313
  "visual_reference_evaluation": 23.8
314
  },
 
332
  "physical_plausibility": 599,
333
  "prompt_faithfulness": 751,
334
  "rubric_adaptive": 751,
335
+ "text_reference_evaluation": 536,
336
  "text_rendering": 501,
337
  "visual_reference_evaluation": 596
338
  },
 
344
  "physical_plausibility": 51.5,
345
  "prompt_faithfulness": 21.7,
346
  "rubric_adaptive": 27.9,
347
+ "text_reference_evaluation": 6.6,
348
  "text_rendering": 8.4,
349
  "visual_reference_evaluation": 21.1
350
  },
 
368
  "physical_plausibility": 597,
369
  "prompt_faithfulness": 750,
370
  "rubric_adaptive": 751,
371
+ "text_reference_evaluation": 537,
372
  "text_rendering": 483,
373
  "visual_reference_evaluation": 594
374
  },
 
380
  "physical_plausibility": 49.0,
381
  "prompt_faithfulness": 16.0,
382
  "rubric_adaptive": 22.9,
383
+ "text_reference_evaluation": 3.6,
384
  "text_rendering": 4.7,
385
  "visual_reference_evaluation": 15.1
386
  },
 
404
  "physical_plausibility": 631,
405
  "prompt_faithfulness": 751,
406
  "rubric_adaptive": 751,
407
+ "text_reference_evaluation": 521,
408
  "text_rendering": 465,
409
  "visual_reference_evaluation": 595
410
  },
 
416
  "physical_plausibility": 40.4,
417
  "prompt_faithfulness": 16.7,
418
  "rubric_adaptive": 21.8,
419
+ "text_reference_evaluation": 3.5,
420
  "text_rendering": 3.5,
421
  "visual_reference_evaluation": 16.8
422
  },
 
440
  "physical_plausibility": 656,
441
  "prompt_faithfulness": 751,
442
  "rubric_adaptive": 751,
443
+ "text_reference_evaluation": 630,
444
  "text_rendering": 596,
445
  "visual_reference_evaluation": 688
446
  },
 
452
  "physical_plausibility": 20.0,
453
  "prompt_faithfulness": 6.0,
454
  "rubric_adaptive": 8.7,
455
+ "text_reference_evaluation": 1.2,
456
  "text_rendering": 1.2,
457
  "visual_reference_evaluation": 6.0
458
  },
data/manifest.json CHANGED
@@ -88,7 +88,6 @@
88
  },
89
  "schema_version": "1.0.0",
90
  "scoring": {
91
- "excluded_public_component": "text_reference_evaluation",
92
  "missing_policy_default": "zero_fill",
93
  "missing_policy_exceptions": [
94
  "qwen_image_2_pro",
@@ -117,6 +116,8 @@
117
  "physical_plausibility",
118
  "visual_reference_evaluation"
119
  ],
 
 
120
  "public_rounding_decimals": 1,
121
  "scale_public": [
122
  0,
 
88
  },
89
  "schema_version": "1.0.0",
90
  "scoring": {
 
91
  "missing_policy_default": "zero_fill",
92
  "missing_policy_exceptions": [
93
  "qwen_image_2_pro",
 
116
  "physical_plausibility",
117
  "visual_reference_evaluation"
118
  ],
119
+ "overall_9_excluded_component": "text_reference_evaluation",
120
+ "primary_metric": "overall_10",
121
  "public_rounding_decimals": 1,
122
  "scale_public": [
123
  0,
index.html CHANGED
@@ -24,6 +24,12 @@
24
  <header>
25
  <h1>SearchGen-Bench</h1>
26
  <p class="subtitle">Evaluating search-grounded image generation across knowledge boundaries</p>
 
 
 
 
 
 
27
  <div id="intro-container" class="intro-container">
28
  <div id="intro-markdown" class="markdown-body"></div>
29
  </div>
@@ -32,6 +38,9 @@
32
  <button class="expand-btn" data-target="metrics-details">
33
  <i class="fa-solid fa-chart-line"></i> Metric Details
34
  </button>
 
 
 
35
  <button class="expand-btn" data-target="submit-here">
36
  <i class="fa-solid fa-rocket"></i> Submit Here
37
  </button>
@@ -50,6 +59,7 @@
50
  </div>
51
 
52
  <div id="metrics-details" class="expandable-content markdown-body"></div>
 
53
  <div id="submit-here" class="expandable-content markdown-body"></div>
54
  </header>
55
 
@@ -104,6 +114,7 @@
104
  </table>
105
  </div>
106
  </div>
 
107
 
108
  <!-- Citation Section -->
109
  <section id="citation-section" class="citation-section">
 
24
  <header>
25
  <h1>SearchGen-Bench</h1>
26
  <p class="subtitle">Evaluating search-grounded image generation across knowledge boundaries</p>
27
+ <div class="stat-grid" aria-label="Benchmark summary">
28
+ <article><strong>751</strong><span>evaluation prompts</span></article>
29
+ <article><strong>22</strong><span>knowledge domains</span></article>
30
+ <article><strong>12</strong><span>failure modes</span></article>
31
+ <article><strong>10</strong><span>score components</span></article>
32
+ </div>
33
  <div id="intro-container" class="intro-container">
34
  <div id="intro-markdown" class="markdown-body"></div>
35
  </div>
 
38
  <button class="expand-btn" data-target="metrics-details">
39
  <i class="fa-solid fa-chart-line"></i> Metric Details
40
  </button>
41
+ <button class="expand-btn" data-target="column-guide">
42
+ <i class="fa-solid fa-table-columns"></i> Column Guide
43
+ </button>
44
  <button class="expand-btn" data-target="submit-here">
45
  <i class="fa-solid fa-rocket"></i> Submit Here
46
  </button>
 
59
  </div>
60
 
61
  <div id="metrics-details" class="expandable-content markdown-body"></div>
62
+ <div id="column-guide" class="expandable-content markdown-body"></div>
63
  <div id="submit-here" class="expandable-content markdown-body"></div>
64
  </header>
65
 
 
114
  </table>
115
  </div>
116
  </div>
117
+ <p class="table-note">Click any column heading to sort. Hover over a heading for a short definition, or open the Column Guide above for the complete explanation.</p>
118
 
119
  <!-- Citation Section -->
120
  <section id="citation-section" class="citation-section">
main.js CHANGED
@@ -9,17 +9,19 @@ const TOP_SCROLLBAR_WRAPPER = document.getElementById('top-scrollbar-wrapper');
9
  const TOP_SCROLLBAR_CONTENT = document.getElementById('top-scrollbar-content');
10
  const BOTTOM_SCROLLBAR_WRAPPER = document.getElementById('bottom-scrollbar-wrapper');
11
  const TABLE = document.getElementById('leaderboard-table');
 
12
 
13
  const COMPONENTS = [
14
- ['checklist', 'Checklist'],
15
- ['rubric_adaptive', 'Rubric Adaptive'],
16
- ['prompt_faithfulness', 'Prompt Faithfulness'],
17
- ['image_quality', 'Image Quality'],
18
- ['text_rendering', 'Text Rendering'],
19
- ['ai_naturalness', 'AI Naturalness'],
20
- ['composition_and_aesthetics', 'Composition & Aesthetics'],
21
- ['physical_plausibility', 'Physical Plausibility'],
22
- ['visual_reference_evaluation', 'Visual Reference'],
 
23
  ];
24
 
25
  let manifest = null;
@@ -27,7 +29,7 @@ let strataData = {};
27
  let domainData = {};
28
  let failureModeData = {};
29
  let displayRows = [];
30
- let sortKey = 'overall_9';
31
  let sortAsc = false;
32
 
33
  const escapeHtml = (value) => String(value ?? '')
@@ -59,12 +61,12 @@ async function init() {
59
  SEARCH_INPUT.addEventListener('input', updateBoard);
60
  BOARD_SELECT.addEventListener('change', () => {
61
  STRATUM_CONTROL.hidden = BOARD_SELECT.value !== 'components';
62
- sortKey = BOARD_SELECT.value === 'components' ? 'overall_9' : 'All';
63
  sortAsc = false;
64
  updateBoard();
65
  });
66
  STRATUM_SELECT.addEventListener('change', () => {
67
- sortKey = 'overall_9';
68
  sortAsc = false;
69
  updateBoard();
70
  });
@@ -79,6 +81,7 @@ async function initMarkdown() {
79
  const targets = [
80
  ['intro-markdown', 'blobs/intro.md'],
81
  ['metrics-details', 'blobs/metrics.md'],
 
82
  ['submit-here', 'blobs/submitting.md'],
83
  ];
84
  await Promise.all(targets.map(async ([id, path]) => {
@@ -126,21 +129,23 @@ function buildBreakdownRows(groups) {
126
  .map((displayName) => strataData.All.find((row) => row.display_name === displayName))
127
  .filter(Boolean)
128
  .map((base) => {
129
- const row = { ...base, All: base.overall_9, groupCoverage: {} };
130
  Object.entries(groups).forEach(([tag, scores]) => {
131
  const match = modelMap(scores)[base.model_id];
132
- row[tag] = match?.overall_9 ?? null;
133
  row.groupCoverage[tag] = match ? `${match.n_scored}/${match.n_total}` : '0/0';
134
  });
135
- row.All = overall[base.model_id]?.overall_9 ?? null;
136
  return row;
137
  });
138
  }
139
 
140
  function currentRows() {
141
- if (BOARD_SELECT.value === 'domains') return buildBreakdownRows(domainData);
142
- if (BOARD_SELECT.value === 'failure_modes') return buildBreakdownRows(failureModeData);
143
- return [...(strataData[STRATUM_SELECT.value] || [])];
 
 
144
  }
145
 
146
  function numericValue(row, key) {
@@ -173,17 +178,17 @@ function arrowFor(key) {
173
  return sortKey === key ? (sortAsc ? ' ↑' : ' ↓') : '';
174
  }
175
 
176
- function sortableHeader(key, label, className = '') {
177
- return `<th class="${className}" data-sort="${escapeHtml(key)}">${escapeHtml(label)}${arrowFor(key)}</th>`;
 
178
  }
179
 
180
  function renderHeaders() {
181
- let html = '<th class="rank-column">#</th>' + sortableHeader('display_name', 'Model', 'model-column');
182
  if (BOARD_SELECT.value === 'components') {
183
- html += sortableHeader('overall_9', 'Overall-9', 'primary-metric');
184
- html += sortableHeader('overall_10', 'Overall-10 (Paper)');
185
- COMPONENTS.forEach(([key, label]) => { html += sortableHeader(`component:${key}`, label); });
186
- html += sortableHeader('coverage', 'Coverage');
187
  } else {
188
  html += sortableHeader('All', 'All 751', 'primary-metric');
189
  const groups = BOARD_SELECT.value === 'domains' ? domainData : failureModeData;
@@ -219,8 +224,7 @@ function renderComponentRow(row, index) {
219
  return `<tr>
220
  <td class="rank-column">${index + 1}</td>
221
  ${modelCell(row)}
222
- <td class="metric-cell">${formatScore(row.overall_9)}</td>
223
- <td>${formatScore(row.overall_10)}</td>
224
  ${components}
225
  <td class="${coverageClass}" title="${row.n_scored} scored of ${row.n_total}; missing policy: ${escapeHtml(row.missing_policy)}">
226
  ${coveragePercent}% <span class="coverage-count">${row.n_scored}/${row.n_total}</span>
 
9
  const TOP_SCROLLBAR_CONTENT = document.getElementById('top-scrollbar-content');
10
  const BOTTOM_SCROLLBAR_WRAPPER = document.getElementById('bottom-scrollbar-wrapper');
11
  const TABLE = document.getElementById('leaderboard-table');
12
+ const EXCLUDED_MODELS = new Set(['imagen3fast']);
13
 
14
  const COMPONENTS = [
15
+ ['checklist', 'Checklist', 'Satisfaction of prompt-specific verification checklist items.'],
16
+ ['rubric_adaptive', 'Rubric Adaptive', 'Satisfaction of prompt-specific weighted evaluation-rubric criteria.'],
17
+ ['prompt_faithfulness', 'Prompt Faithfulness', 'How completely the image follows the user prompt.'],
18
+ ['image_quality', 'Image Quality', 'Visual fidelity, clarity, detail, and absence of rendering defects.'],
19
+ ['text_rendering', 'Text Rendering', 'Correctness and legibility of text shown in the image.'],
20
+ ['ai_naturalness', 'AI Naturalness', 'How natural and non-synthetic the image appears.'],
21
+ ['composition_and_aesthetics', 'Composition & Aesthetics', 'Layout, balance, coherence, and aesthetic quality.'],
22
+ ['physical_plausibility', 'Physical Plausibility', 'Consistency with real-world geometry, anatomy, lighting, and physics.'],
23
+ ['visual_reference_evaluation', 'Visual Reference', 'Consistency with required visual-reference entities or attributes.'],
24
+ ['text_reference_evaluation', 'Text Reference', 'Factual consistency with required text-derived knowledge.'],
25
  ];
26
 
27
  let manifest = null;
 
29
  let domainData = {};
30
  let failureModeData = {};
31
  let displayRows = [];
32
+ let sortKey = 'overall_10';
33
  let sortAsc = false;
34
 
35
  const escapeHtml = (value) => String(value ?? '')
 
61
  SEARCH_INPUT.addEventListener('input', updateBoard);
62
  BOARD_SELECT.addEventListener('change', () => {
63
  STRATUM_CONTROL.hidden = BOARD_SELECT.value !== 'components';
64
+ sortKey = BOARD_SELECT.value === 'components' ? 'overall_10' : 'All';
65
  sortAsc = false;
66
  updateBoard();
67
  });
68
  STRATUM_SELECT.addEventListener('change', () => {
69
+ sortKey = 'overall_10';
70
  sortAsc = false;
71
  updateBoard();
72
  });
 
81
  const targets = [
82
  ['intro-markdown', 'blobs/intro.md'],
83
  ['metrics-details', 'blobs/metrics.md'],
84
+ ['column-guide', 'blobs/columns.md'],
85
  ['submit-here', 'blobs/submitting.md'],
86
  ];
87
  await Promise.all(targets.map(async ([id, path]) => {
 
129
  .map((displayName) => strataData.All.find((row) => row.display_name === displayName))
130
  .filter(Boolean)
131
  .map((base) => {
132
+ const row = { ...base, All: base.overall_10, groupCoverage: {} };
133
  Object.entries(groups).forEach(([tag, scores]) => {
134
  const match = modelMap(scores)[base.model_id];
135
+ row[tag] = match?.overall_10 ?? null;
136
  row.groupCoverage[tag] = match ? `${match.n_scored}/${match.n_total}` : '0/0';
137
  });
138
+ row.All = overall[base.model_id]?.overall_10 ?? null;
139
  return row;
140
  });
141
  }
142
 
143
  function currentRows() {
144
+ let rows;
145
+ if (BOARD_SELECT.value === 'domains') rows = buildBreakdownRows(domainData);
146
+ else if (BOARD_SELECT.value === 'failure_modes') rows = buildBreakdownRows(failureModeData);
147
+ else rows = [...(strataData[STRATUM_SELECT.value] || [])];
148
+ return rows.filter((row) => !EXCLUDED_MODELS.has(row.model_id));
149
  }
150
 
151
  function numericValue(row, key) {
 
178
  return sortKey === key ? (sortAsc ? ' ↑' : ' ↓') : '';
179
  }
180
 
181
+ function sortableHeader(key, label, className = '', description = '') {
182
+ const title = description ? ` title="${escapeHtml(description)}"` : '';
183
+ return `<th class="${className}" data-sort="${escapeHtml(key)}"${title}>${escapeHtml(label)}${arrowFor(key)}</th>`;
184
  }
185
 
186
  function renderHeaders() {
187
+ let html = '<th class="rank-column">#</th>' + sortableHeader('display_name', 'Model', 'model-column', 'Evaluated image-generation model.');
188
  if (BOARD_SELECT.value === 'components') {
189
+ html += sortableHeader('overall_10', 'Overall-10', 'primary-metric', 'Prompt-macro average across the ten applicable components, scaled to 0–100.');
190
+ COMPONENTS.forEach(([key, label, description]) => { html += sortableHeader(`component:${key}`, label, '', description); });
191
+ html += sortableHeader('coverage', 'Coverage', '', 'Share and count of prompts with valid scored results.');
 
192
  } else {
193
  html += sortableHeader('All', 'All 751', 'primary-metric');
194
  const groups = BOARD_SELECT.value === 'domains' ? domainData : failureModeData;
 
224
  return `<tr>
225
  <td class="rank-column">${index + 1}</td>
226
  ${modelCell(row)}
227
+ <td class="metric-cell">${formatScore(row.overall_10)}</td>
 
228
  ${components}
229
  <td class="${coverageClass}" title="${row.n_scored} scored of ${row.n_total}; missing policy: ${escapeHtml(row.missing_policy)}">
230
  ${coveragePercent}% <span class="coverage-count">${row.n_scored}/${row.n_total}</span>
public/blobs/columns.md ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Column guide
2
+
3
+ - **Overall-10** — Prompt-macro average across the ten applicable components, scaled from 0–3 to 0–100.
4
+ - **Checklist** — Satisfaction of prompt-specific verification checklist items.
5
+ - **Rubric Adaptive** — Satisfaction of prompt-specific weighted evaluation-rubric criteria.
6
+ - **Prompt Faithfulness** — How completely the image follows the user prompt.
7
+ - **Image Quality** — Visual fidelity, clarity, detail, and absence of rendering defects.
8
+ - **Text Rendering** — Correctness and legibility of text shown in the image.
9
+ - **AI Naturalness** — How natural and non-synthetic the image appears.
10
+ - **Composition & Aesthetics** — Layout, balance, coherence, and aesthetic quality.
11
+ - **Physical Plausibility** — Consistency with real-world geometry, anatomy, lighting, and physics.
12
+ - **Visual Reference** — Consistency with required visual-reference entities or attributes.
13
+ - **Text Reference** — Factual consistency with required text-derived knowledge.
14
+ - **Coverage** — Percentage and count of prompts with valid scored results. Missing-result handling follows the model-specific policy described in Metric Details.
15
+
16
+ All score columns use the 0–100 public scale. **N/A** means a component is not applicable, not a score of zero.
public/blobs/intro.md CHANGED
@@ -1,5 +1,7 @@
1
- **SearchGen-Bench** evaluates image generators on 751 prompts spanning 22 domains and 12 failure modes. It separates prompts that generators can answer without retrieval from visually and textually search-intensive prompts.
2
 
3
- The primary leaderboard metric, **Overall-9**, is the prompt-macro average of nine physical-plausibility judge components. The paper-compatible **Overall-10** additionally includes Text Reference. Use the scoreboard selector to inspect component, domain, and failure-mode rankings.
 
 
4
 
5
  All scores are generated from versioned prompt-level records. Counts and coverage are shown because domains and failure modes are multi-label and some commercial generators have incomplete evaluations.
 
1
+ ## Where visual generators know—and where they need search
2
 
3
+ **SearchGen-Bench** compares image generators across 751 evaluation prompts, knowledge-boundary strata, 22 domains, and 12 recurring failure modes. The benchmark separates 100 **NoSearch** prompts that strong generators can answer from parametric knowledge from 651 **SearchIntensive** prompts whose visual or textual requirements expose gaps that retrieval can address.
4
+
5
+ The primary metric is **Overall-10**: a prompt-macro average over the canonical ten applicable FF-judge+PP components, reported on a 0–100 scale. Use the scoreboard selector to inspect results by component, domain, or failure mode.
6
 
7
  All scores are generated from versioned prompt-level records. Counts and coverage are shown because domains and failure modes are multi-label and some commercial generators have incomplete evaluations.
public/blobs/metrics.md CHANGED
@@ -1,8 +1,6 @@
1
  ## Metric details
2
 
3
- **Overall-9** is the mean of all applicable public components for each prompt, followed by a macro average over prompts and conversion from the raw 0–3 scale to 0–100. Its components are Checklist, Rubric Adaptive, Prompt Faithfulness, Image Quality, Text Rendering, AI Naturalness, Composition and Aesthetics, Physical Plausibility, and Visual Reference.
4
-
5
- **Overall-10 (Paper)** uses the same procedure but additionally includes Text Reference. It is retained so results can be reconciled with the paper's canonical tables.
6
 
7
  An inapplicable component is excluded from its prompt-level mean. Missing model results are zero-filled by default, matching the canonical paper convention. Missing Grok-Imagine-Image and Qwen-Image-2-Pro results are excluded from their denominators. Coverage always reports valid scored prompts over prompts in the selected group.
8
 
 
1
  ## Metric details
2
 
3
+ **Overall-10** is the primary benchmark metric. For each prompt, it averages all applicable values across Checklist, Rubric Adaptive, Prompt Faithfulness, Image Quality, Text Rendering, AI Naturalness, Composition and Aesthetics, Physical Plausibility, Visual Reference, and Text Reference. Prompt-level means are then macro-averaged and converted from the raw 0–3 scale to 0–100.
 
 
4
 
5
  An inapplicable component is excluded from its prompt-level mean. Missing model results are zero-filled by default, matching the canonical paper convention. Missing Grok-Imagine-Image and Qwen-Image-2-Pro results are excluded from their denominators. Coverage always reports valid scored prompts over prompts in the selected group.
6
 
public/data/leaderboard_by_domain.json CHANGED
The diff for this file is too large to render. See raw diff
 
public/data/leaderboard_by_failure_mode.json CHANGED
@@ -9,6 +9,7 @@
9
  "physical_plausibility": 415,
10
  "prompt_faithfulness": 534,
11
  "rubric_adaptive": 534,
 
12
  "text_rendering": 376,
13
  "visual_reference_evaluation": 439
14
  },
@@ -20,6 +21,7 @@
20
  "physical_plausibility": 73.8,
21
  "prompt_faithfulness": 68.5,
22
  "rubric_adaptive": 69.7,
 
23
  "text_rendering": 73.2,
24
  "visual_reference_evaluation": 66.6
25
  },
@@ -43,6 +45,7 @@
43
  "physical_plausibility": 455,
44
  "prompt_faithfulness": 534,
45
  "rubric_adaptive": 534,
 
46
  "text_rendering": 344,
47
  "visual_reference_evaluation": 437
48
  },
@@ -54,6 +57,7 @@
54
  "physical_plausibility": 76.2,
55
  "prompt_faithfulness": 62.2,
56
  "rubric_adaptive": 65.8,
 
57
  "text_rendering": 66.4,
58
  "visual_reference_evaluation": 61.6
59
  },
@@ -77,6 +81,7 @@
77
  "physical_plausibility": 389,
78
  "prompt_faithfulness": 504,
79
  "rubric_adaptive": 504,
 
80
  "text_rendering": 355,
81
  "visual_reference_evaluation": 417
82
  },
@@ -88,6 +93,7 @@
88
  "physical_plausibility": 69.9,
89
  "prompt_faithfulness": 61.3,
90
  "rubric_adaptive": 63.8,
 
91
  "text_rendering": 61.7,
92
  "visual_reference_evaluation": 60.7
93
  },
@@ -111,6 +117,7 @@
111
  "physical_plausibility": 410,
112
  "prompt_faithfulness": 526,
113
  "rubric_adaptive": 526,
 
114
  "text_rendering": 321,
115
  "visual_reference_evaluation": 439
116
  },
@@ -122,6 +129,7 @@
122
  "physical_plausibility": 70.2,
123
  "prompt_faithfulness": 50.8,
124
  "rubric_adaptive": 54.7,
 
125
  "text_rendering": 56.9,
126
  "visual_reference_evaluation": 47.0
127
  },
@@ -145,6 +153,7 @@
145
  "physical_plausibility": 422,
146
  "prompt_faithfulness": 534,
147
  "rubric_adaptive": 534,
 
148
  "text_rendering": 319,
149
  "visual_reference_evaluation": 448
150
  },
@@ -156,6 +165,7 @@
156
  "physical_plausibility": 65.3,
157
  "prompt_faithfulness": 47.5,
158
  "rubric_adaptive": 51.6,
 
159
  "text_rendering": 52.0,
160
  "visual_reference_evaluation": 44.0
161
  },
@@ -179,6 +189,7 @@
179
  "physical_plausibility": 441,
180
  "prompt_faithfulness": 534,
181
  "rubric_adaptive": 534,
 
182
  "text_rendering": 353,
183
  "visual_reference_evaluation": 446
184
  },
@@ -190,6 +201,7 @@
190
  "physical_plausibility": 62.1,
191
  "prompt_faithfulness": 46.1,
192
  "rubric_adaptive": 50.8,
 
193
  "text_rendering": 48.6,
194
  "visual_reference_evaluation": 41.3
195
  },
@@ -213,6 +225,7 @@
213
  "physical_plausibility": 445,
214
  "prompt_faithfulness": 534,
215
  "rubric_adaptive": 534,
 
216
  "text_rendering": 333,
217
  "visual_reference_evaluation": 436
218
  },
@@ -224,6 +237,7 @@
224
  "physical_plausibility": 64.5,
225
  "prompt_faithfulness": 41.4,
226
  "rubric_adaptive": 47.1,
 
227
  "text_rendering": 37.8,
228
  "visual_reference_evaluation": 39.6
229
  },
@@ -247,6 +261,7 @@
247
  "physical_plausibility": 427,
248
  "prompt_faithfulness": 534,
249
  "rubric_adaptive": 534,
 
250
  "text_rendering": 346,
251
  "visual_reference_evaluation": 437
252
  },
@@ -258,6 +273,7 @@
258
  "physical_plausibility": 63.3,
259
  "prompt_faithfulness": 39.6,
260
  "rubric_adaptive": 44.3,
 
261
  "text_rendering": 29.3,
262
  "visual_reference_evaluation": 38.4
263
  },
@@ -281,6 +297,7 @@
281
  "physical_plausibility": 486,
282
  "prompt_faithfulness": 534,
283
  "rubric_adaptive": 534,
 
284
  "text_rendering": 328,
285
  "visual_reference_evaluation": 435
286
  },
@@ -292,6 +309,7 @@
292
  "physical_plausibility": 48.5,
293
  "prompt_faithfulness": 25.9,
294
  "rubric_adaptive": 32.0,
 
295
  "text_rendering": 11.4,
296
  "visual_reference_evaluation": 25.4
297
  },
@@ -315,6 +333,7 @@
315
  "physical_plausibility": 440,
316
  "prompt_faithfulness": 534,
317
  "rubric_adaptive": 534,
 
318
  "text_rendering": 345,
319
  "visual_reference_evaluation": 436
320
  },
@@ -326,6 +345,7 @@
326
  "physical_plausibility": 51.2,
327
  "prompt_faithfulness": 23.0,
328
  "rubric_adaptive": 29.1,
 
329
  "text_rendering": 8.7,
330
  "visual_reference_evaluation": 23.0
331
  },
@@ -349,6 +369,7 @@
349
  "physical_plausibility": 442,
350
  "prompt_faithfulness": 533,
351
  "rubric_adaptive": 534,
 
352
  "text_rendering": 327,
353
  "visual_reference_evaluation": 434
354
  },
@@ -360,6 +381,7 @@
360
  "physical_plausibility": 48.1,
361
  "prompt_faithfulness": 17.0,
362
  "rubric_adaptive": 23.4,
 
363
  "text_rendering": 4.5,
364
  "visual_reference_evaluation": 16.3
365
  },
@@ -383,6 +405,7 @@
383
  "physical_plausibility": 460,
384
  "prompt_faithfulness": 534,
385
  "rubric_adaptive": 534,
 
386
  "text_rendering": 313,
387
  "visual_reference_evaluation": 435
388
  },
@@ -394,6 +417,7 @@
394
  "physical_plausibility": 41.4,
395
  "prompt_faithfulness": 18.4,
396
  "rubric_adaptive": 23.2,
 
397
  "text_rendering": 4.1,
398
  "visual_reference_evaluation": 19.0
399
  },
@@ -417,6 +441,7 @@
417
  "physical_plausibility": 473,
418
  "prompt_faithfulness": 534,
419
  "rubric_adaptive": 534,
 
420
  "text_rendering": 430,
421
  "visual_reference_evaluation": 506
422
  },
@@ -428,6 +453,7 @@
428
  "physical_plausibility": 17.3,
429
  "prompt_faithfulness": 6.0,
430
  "rubric_adaptive": 8.1,
 
431
  "text_rendering": 0.9,
432
  "visual_reference_evaluation": 5.9
433
  },
@@ -453,6 +479,7 @@
453
  "physical_plausibility": 144,
454
  "prompt_faithfulness": 159,
455
  "rubric_adaptive": 159,
 
456
  "text_rendering": 95,
457
  "visual_reference_evaluation": 121
458
  },
@@ -464,6 +491,7 @@
464
  "physical_plausibility": 75.3,
465
  "prompt_faithfulness": 68.3,
466
  "rubric_adaptive": 71.3,
 
467
  "text_rendering": 70.9,
468
  "visual_reference_evaluation": 62.4
469
  },
@@ -487,6 +515,7 @@
487
  "physical_plausibility": 149,
488
  "prompt_faithfulness": 159,
489
  "rubric_adaptive": 159,
 
490
  "text_rendering": 78,
491
  "visual_reference_evaluation": 121
492
  },
@@ -498,6 +527,7 @@
498
  "physical_plausibility": 77.9,
499
  "prompt_faithfulness": 63.1,
500
  "rubric_adaptive": 68.7,
 
501
  "text_rendering": 61.3,
502
  "visual_reference_evaluation": 59.5
503
  },
@@ -521,6 +551,7 @@
521
  "physical_plausibility": 136,
522
  "prompt_faithfulness": 153,
523
  "rubric_adaptive": 153,
 
524
  "text_rendering": 92,
525
  "visual_reference_evaluation": 121
526
  },
@@ -532,6 +563,7 @@
532
  "physical_plausibility": 71.3,
533
  "prompt_faithfulness": 63.8,
534
  "rubric_adaptive": 68.1,
 
535
  "text_rendering": 64.7,
536
  "visual_reference_evaluation": 61.0
537
  },
@@ -555,6 +587,7 @@
555
  "physical_plausibility": 139,
556
  "prompt_faithfulness": 158,
557
  "rubric_adaptive": 158,
 
558
  "text_rendering": 70,
559
  "visual_reference_evaluation": 124
560
  },
@@ -566,6 +599,7 @@
566
  "physical_plausibility": 71.0,
567
  "prompt_faithfulness": 54.7,
568
  "rubric_adaptive": 62.6,
 
569
  "text_rendering": 65.5,
570
  "visual_reference_evaluation": 53.2
571
  },
@@ -589,6 +623,7 @@
589
  "physical_plausibility": 139,
590
  "prompt_faithfulness": 159,
591
  "rubric_adaptive": 159,
 
592
  "text_rendering": 73,
593
  "visual_reference_evaluation": 126
594
  },
@@ -600,6 +635,7 @@
600
  "physical_plausibility": 69.3,
601
  "prompt_faithfulness": 54.8,
602
  "rubric_adaptive": 61.9,
 
603
  "text_rendering": 60.7,
604
  "visual_reference_evaluation": 53.8
605
  },
@@ -623,6 +659,7 @@
623
  "physical_plausibility": 141,
624
  "prompt_faithfulness": 159,
625
  "rubric_adaptive": 159,
 
626
  "text_rendering": 75,
627
  "visual_reference_evaluation": 121
628
  },
@@ -634,6 +671,7 @@
634
  "physical_plausibility": 70.7,
635
  "prompt_faithfulness": 51.2,
636
  "rubric_adaptive": 57.5,
 
637
  "text_rendering": 49.6,
638
  "visual_reference_evaluation": 50.0
639
  },
@@ -657,6 +695,7 @@
657
  "physical_plausibility": 139,
658
  "prompt_faithfulness": 159,
659
  "rubric_adaptive": 159,
 
660
  "text_rendering": 86,
661
  "visual_reference_evaluation": 126
662
  },
@@ -668,6 +707,7 @@
668
  "physical_plausibility": 70.0,
669
  "prompt_faithfulness": 53.6,
670
  "rubric_adaptive": 58.6,
 
671
  "text_rendering": 54.5,
672
  "visual_reference_evaluation": 48.3
673
  },
@@ -691,6 +731,7 @@
691
  "physical_plausibility": 143,
692
  "prompt_faithfulness": 159,
693
  "rubric_adaptive": 159,
 
694
  "text_rendering": 79,
695
  "visual_reference_evaluation": 121
696
  },
@@ -702,6 +743,7 @@
702
  "physical_plausibility": 68.1,
703
  "prompt_faithfulness": 44.5,
704
  "rubric_adaptive": 52.5,
 
705
  "text_rendering": 20.8,
706
  "visual_reference_evaluation": 42.8
707
  },
@@ -725,6 +767,7 @@
725
  "physical_plausibility": 153,
726
  "prompt_faithfulness": 159,
727
  "rubric_adaptive": 159,
 
728
  "text_rendering": 74,
729
  "visual_reference_evaluation": 121
730
  },
@@ -736,6 +779,7 @@
736
  "physical_plausibility": 60.1,
737
  "prompt_faithfulness": 38.4,
738
  "rubric_adaptive": 44.8,
 
739
  "text_rendering": 21.2,
740
  "visual_reference_evaluation": 39.9
741
  },
@@ -759,6 +803,7 @@
759
  "physical_plausibility": 143,
760
  "prompt_faithfulness": 159,
761
  "rubric_adaptive": 159,
 
762
  "text_rendering": 81,
763
  "visual_reference_evaluation": 121
764
  },
@@ -770,6 +815,7 @@
770
  "physical_plausibility": 60.5,
771
  "prompt_faithfulness": 32.0,
772
  "rubric_adaptive": 39.4,
 
773
  "text_rendering": 6.8,
774
  "visual_reference_evaluation": 33.3
775
  },
@@ -793,6 +839,7 @@
793
  "physical_plausibility": 140,
794
  "prompt_faithfulness": 159,
795
  "rubric_adaptive": 159,
 
796
  "text_rendering": 79,
797
  "visual_reference_evaluation": 121
798
  },
@@ -804,6 +851,7 @@
804
  "physical_plausibility": 58.2,
805
  "prompt_faithfulness": 23.3,
806
  "rubric_adaptive": 31.3,
 
807
  "text_rendering": 4.2,
808
  "visual_reference_evaluation": 22.6
809
  },
@@ -827,6 +875,7 @@
827
  "physical_plausibility": 142,
828
  "prompt_faithfulness": 159,
829
  "rubric_adaptive": 159,
 
830
  "text_rendering": 70,
831
  "visual_reference_evaluation": 121
832
  },
@@ -838,6 +887,7 @@
838
  "physical_plausibility": 49.4,
839
  "prompt_faithfulness": 24.3,
840
  "rubric_adaptive": 30.4,
 
841
  "text_rendering": 2.6,
842
  "visual_reference_evaluation": 24.8
843
  },
@@ -861,6 +911,7 @@
861
  "physical_plausibility": 151,
862
  "prompt_faithfulness": 159,
863
  "rubric_adaptive": 159,
 
864
  "text_rendering": 124,
865
  "visual_reference_evaluation": 147
866
  },
@@ -872,6 +923,7 @@
872
  "physical_plausibility": 19.6,
873
  "prompt_faithfulness": 6.1,
874
  "rubric_adaptive": 8.3,
 
875
  "text_rendering": 0.7,
876
  "visual_reference_evaluation": 6.3
877
  },
@@ -897,6 +949,7 @@
897
  "physical_plausibility": 193,
898
  "prompt_faithfulness": 281,
899
  "rubric_adaptive": 281,
 
900
  "text_rendering": 226,
901
  "visual_reference_evaluation": 224
902
  },
@@ -908,6 +961,7 @@
908
  "physical_plausibility": 81.0,
909
  "prompt_faithfulness": 71.9,
910
  "rubric_adaptive": 72.6,
 
911
  "text_rendering": 78.8,
912
  "visual_reference_evaluation": 67.3
913
  },
@@ -931,6 +985,7 @@
931
  "physical_plausibility": 221,
932
  "prompt_faithfulness": 281,
933
  "rubric_adaptive": 281,
 
934
  "text_rendering": 210,
935
  "visual_reference_evaluation": 223
936
  },
@@ -942,6 +997,7 @@
942
  "physical_plausibility": 80.9,
943
  "prompt_faithfulness": 62.9,
944
  "rubric_adaptive": 64.5,
 
945
  "text_rendering": 67.1,
946
  "visual_reference_evaluation": 59.2
947
  },
@@ -965,6 +1021,7 @@
965
  "physical_plausibility": 181,
966
  "prompt_faithfulness": 269,
967
  "rubric_adaptive": 269,
 
968
  "text_rendering": 218,
969
  "visual_reference_evaluation": 221
970
  },
@@ -976,6 +1033,7 @@
976
  "physical_plausibility": 76.4,
977
  "prompt_faithfulness": 63.5,
978
  "rubric_adaptive": 63.6,
 
979
  "text_rendering": 62.9,
980
  "visual_reference_evaluation": 57.5
981
  },
@@ -999,6 +1057,7 @@
999
  "physical_plausibility": 190,
1000
  "prompt_faithfulness": 277,
1001
  "rubric_adaptive": 277,
 
1002
  "text_rendering": 208,
1003
  "visual_reference_evaluation": 229
1004
  },
@@ -1010,6 +1069,7 @@
1010
  "physical_plausibility": 72.5,
1011
  "prompt_faithfulness": 52.2,
1012
  "rubric_adaptive": 53.8,
 
1013
  "text_rendering": 58.7,
1014
  "visual_reference_evaluation": 44.8
1015
  },
@@ -1033,6 +1093,7 @@
1033
  "physical_plausibility": 199,
1034
  "prompt_faithfulness": 281,
1035
  "rubric_adaptive": 281,
 
1036
  "text_rendering": 203,
1037
  "visual_reference_evaluation": 234
1038
  },
@@ -1044,6 +1105,7 @@
1044
  "physical_plausibility": 66.3,
1045
  "prompt_faithfulness": 49.7,
1046
  "rubric_adaptive": 51.8,
 
1047
  "text_rendering": 56.2,
1048
  "visual_reference_evaluation": 41.3
1049
  },
@@ -1067,6 +1129,7 @@
1067
  "physical_plausibility": 212,
1068
  "prompt_faithfulness": 281,
1069
  "rubric_adaptive": 281,
 
1070
  "text_rendering": 220,
1071
  "visual_reference_evaluation": 233
1072
  },
@@ -1078,6 +1141,7 @@
1078
  "physical_plausibility": 62.6,
1079
  "prompt_faithfulness": 42.3,
1080
  "rubric_adaptive": 47.0,
 
1081
  "text_rendering": 47.3,
1082
  "visual_reference_evaluation": 35.6
1083
  },
@@ -1101,6 +1165,7 @@
1101
  "physical_plausibility": 217,
1102
  "prompt_faithfulness": 280,
1103
  "rubric_adaptive": 281,
 
1104
  "text_rendering": 208,
1105
  "visual_reference_evaluation": 223
1106
  },
@@ -1112,6 +1177,7 @@
1112
  "physical_plausibility": 61.5,
1113
  "prompt_faithfulness": 37.7,
1114
  "rubric_adaptive": 42.8,
 
1115
  "text_rendering": 35.8,
1116
  "visual_reference_evaluation": 33.5
1117
  },
@@ -1135,6 +1201,7 @@
1135
  "physical_plausibility": 205,
1136
  "prompt_faithfulness": 281,
1137
  "rubric_adaptive": 281,
 
1138
  "text_rendering": 216,
1139
  "visual_reference_evaluation": 223
1140
  },
@@ -1146,6 +1213,7 @@
1146
  "physical_plausibility": 66.7,
1147
  "prompt_faithfulness": 36.6,
1148
  "rubric_adaptive": 40.3,
 
1149
  "text_rendering": 26.9,
1150
  "visual_reference_evaluation": 32.2
1151
  },
@@ -1169,6 +1237,7 @@
1169
  "physical_plausibility": 250,
1170
  "prompt_faithfulness": 281,
1171
  "rubric_adaptive": 281,
 
1172
  "text_rendering": 206,
1173
  "visual_reference_evaluation": 223
1174
  },
@@ -1180,6 +1249,7 @@
1180
  "physical_plausibility": 44.9,
1181
  "prompt_faithfulness": 20.8,
1182
  "rubric_adaptive": 25.9,
 
1183
  "text_rendering": 11.2,
1184
  "visual_reference_evaluation": 18.4
1185
  },
@@ -1203,6 +1273,7 @@
1203
  "physical_plausibility": 211,
1204
  "prompt_faithfulness": 281,
1205
  "rubric_adaptive": 281,
 
1206
  "text_rendering": 219,
1207
  "visual_reference_evaluation": 223
1208
  },
@@ -1214,6 +1285,7 @@
1214
  "physical_plausibility": 48.6,
1215
  "prompt_faithfulness": 18.1,
1216
  "rubric_adaptive": 23.8,
 
1217
  "text_rendering": 7.4,
1218
  "visual_reference_evaluation": 15.7
1219
  },
@@ -1237,6 +1309,7 @@
1237
  "physical_plausibility": 211,
1238
  "prompt_faithfulness": 280,
1239
  "rubric_adaptive": 281,
 
1240
  "text_rendering": 203,
1241
  "visual_reference_evaluation": 222
1242
  },
@@ -1248,6 +1321,7 @@
1248
  "physical_plausibility": 44.9,
1249
  "prompt_faithfulness": 12.7,
1250
  "rubric_adaptive": 19.3,
 
1251
  "text_rendering": 4.1,
1252
  "visual_reference_evaluation": 12.1
1253
  },
@@ -1271,6 +1345,7 @@
1271
  "physical_plausibility": 226,
1272
  "prompt_faithfulness": 281,
1273
  "rubric_adaptive": 281,
 
1274
  "text_rendering": 204,
1275
  "visual_reference_evaluation": 223
1276
  },
@@ -1282,6 +1357,7 @@
1282
  "physical_plausibility": 34.5,
1283
  "prompt_faithfulness": 11.9,
1284
  "rubric_adaptive": 16.8,
 
1285
  "text_rendering": 3.6,
1286
  "visual_reference_evaluation": 11.4
1287
  },
@@ -1305,6 +1381,7 @@
1305
  "physical_plausibility": 234,
1306
  "prompt_faithfulness": 281,
1307
  "rubric_adaptive": 281,
 
1308
  "text_rendering": 229,
1309
  "visual_reference_evaluation": 256
1310
  },
@@ -1316,6 +1393,7 @@
1316
  "physical_plausibility": 21.2,
1317
  "prompt_faithfulness": 4.2,
1318
  "rubric_adaptive": 6.8,
 
1319
  "text_rendering": 0.6,
1320
  "visual_reference_evaluation": 4.8
1321
  },
@@ -1341,6 +1419,7 @@
1341
  "physical_plausibility": 23,
1342
  "prompt_faithfulness": 118,
1343
  "rubric_adaptive": 118,
 
1344
  "text_rendering": 110,
1345
  "visual_reference_evaluation": 95
1346
  },
@@ -1352,6 +1431,7 @@
1352
  "physical_plausibility": 91.3,
1353
  "prompt_faithfulness": 68.2,
1354
  "rubric_adaptive": 63.6,
 
1355
  "text_rendering": 74.1,
1356
  "visual_reference_evaluation": 66.1
1357
  },
@@ -1375,6 +1455,7 @@
1375
  "physical_plausibility": 72,
1376
  "prompt_faithfulness": 118,
1377
  "rubric_adaptive": 118,
 
1378
  "text_rendering": 110,
1379
  "visual_reference_evaluation": 95
1380
  },
@@ -1386,6 +1467,7 @@
1386
  "physical_plausibility": 85.6,
1387
  "prompt_faithfulness": 58.4,
1388
  "rubric_adaptive": 53.3,
 
1389
  "text_rendering": 63.5,
1390
  "visual_reference_evaluation": 53.6
1391
  },
@@ -1409,6 +1491,7 @@
1409
  "physical_plausibility": 39,
1410
  "prompt_faithfulness": 118,
1411
  "rubric_adaptive": 118,
 
1412
  "text_rendering": 113,
1413
  "visual_reference_evaluation": 96
1414
  },
@@ -1420,6 +1503,7 @@
1420
  "physical_plausibility": 90.2,
1421
  "prompt_faithfulness": 57.5,
1422
  "rubric_adaptive": 53.1,
 
1423
  "text_rendering": 55.6,
1424
  "visual_reference_evaluation": 53.3
1425
  },
@@ -1443,6 +1527,7 @@
1443
  "physical_plausibility": 20,
1444
  "prompt_faithfulness": 118,
1445
  "rubric_adaptive": 118,
 
1446
  "text_rendering": 115,
1447
  "visual_reference_evaluation": 96
1448
  },
@@ -1454,6 +1539,7 @@
1454
  "physical_plausibility": 69.2,
1455
  "prompt_faithfulness": 37.6,
1456
  "rubric_adaptive": 36.8,
 
1457
  "text_rendering": 41.3,
1458
  "visual_reference_evaluation": 28.3
1459
  },
@@ -1477,6 +1563,7 @@
1477
  "physical_plausibility": 23,
1478
  "prompt_faithfulness": 118,
1479
  "rubric_adaptive": 118,
 
1480
  "text_rendering": 113,
1481
  "visual_reference_evaluation": 96
1482
  },
@@ -1488,6 +1575,7 @@
1488
  "physical_plausibility": 74.6,
1489
  "prompt_faithfulness": 36.6,
1490
  "rubric_adaptive": 34.8,
 
1491
  "text_rendering": 41.6,
1492
  "visual_reference_evaluation": 28.6
1493
  },
@@ -1511,6 +1599,7 @@
1511
  "physical_plausibility": 45,
1512
  "prompt_faithfulness": 118,
1513
  "rubric_adaptive": 118,
 
1514
  "text_rendering": 113,
1515
  "visual_reference_evaluation": 96
1516
  },
@@ -1522,6 +1611,7 @@
1522
  "physical_plausibility": 65.2,
1523
  "prompt_faithfulness": 32.9,
1524
  "rubric_adaptive": 31.1,
 
1525
  "text_rendering": 37.2,
1526
  "visual_reference_evaluation": 20.1
1527
  },
@@ -1545,6 +1635,7 @@
1545
  "physical_plausibility": 55,
1546
  "prompt_faithfulness": 118,
1547
  "rubric_adaptive": 118,
 
1548
  "text_rendering": 112,
1549
  "visual_reference_evaluation": 95
1550
  },
@@ -1556,6 +1647,7 @@
1556
  "physical_plausibility": 65.8,
1557
  "prompt_faithfulness": 25.2,
1558
  "rubric_adaptive": 25.2,
 
1559
  "text_rendering": 20.2,
1560
  "visual_reference_evaluation": 17.7
1561
  },
@@ -1579,6 +1671,7 @@
1579
  "physical_plausibility": 55,
1580
  "prompt_faithfulness": 118,
1581
  "rubric_adaptive": 118,
 
1582
  "text_rendering": 114,
1583
  "visual_reference_evaluation": 95
1584
  },
@@ -1590,6 +1683,7 @@
1590
  "physical_plausibility": 59.7,
1591
  "prompt_faithfulness": 21.6,
1592
  "rubric_adaptive": 24.2,
 
1593
  "text_rendering": 22.1,
1594
  "visual_reference_evaluation": 17.4
1595
  },
@@ -1613,6 +1707,7 @@
1613
  "physical_plausibility": 83,
1614
  "prompt_faithfulness": 118,
1615
  "rubric_adaptive": 118,
 
1616
  "text_rendering": 114,
1617
  "visual_reference_evaluation": 95
1618
  },
@@ -1624,6 +1719,7 @@
1624
  "physical_plausibility": 16.1,
1625
  "prompt_faithfulness": 1.3,
1626
  "rubric_adaptive": 4.1,
 
1627
  "text_rendering": 0.3,
1628
  "visual_reference_evaluation": 2.3
1629
  },
@@ -1647,6 +1743,7 @@
1647
  "physical_plausibility": 59,
1648
  "prompt_faithfulness": 118,
1649
  "rubric_adaptive": 118,
 
1650
  "text_rendering": 117,
1651
  "visual_reference_evaluation": 95
1652
  },
@@ -1658,6 +1755,7 @@
1658
  "physical_plausibility": 12.1,
1659
  "prompt_faithfulness": 2.0,
1660
  "rubric_adaptive": 3.3,
 
1661
  "text_rendering": 1.1,
1662
  "visual_reference_evaluation": 1.8
1663
  },
@@ -1681,6 +1779,7 @@
1681
  "physical_plausibility": 80,
1682
  "prompt_faithfulness": 118,
1683
  "rubric_adaptive": 118,
 
1684
  "text_rendering": 112,
1685
  "visual_reference_evaluation": 96
1686
  },
@@ -1692,6 +1791,7 @@
1692
  "physical_plausibility": 11.2,
1693
  "prompt_faithfulness": 1.1,
1694
  "rubric_adaptive": 2.6,
 
1695
  "text_rendering": 0.3,
1696
  "visual_reference_evaluation": 1.4
1697
  },
@@ -1715,6 +1815,7 @@
1715
  "physical_plausibility": 64,
1716
  "prompt_faithfulness": 117,
1717
  "rubric_adaptive": 118,
 
1718
  "text_rendering": 115,
1719
  "visual_reference_evaluation": 94
1720
  },
@@ -1726,6 +1827,7 @@
1726
  "physical_plausibility": 9.4,
1727
  "prompt_faithfulness": 0.4,
1728
  "rubric_adaptive": 2.0,
 
1729
  "text_rendering": 0.1,
1730
  "visual_reference_evaluation": 0.9
1731
  },
@@ -1749,6 +1851,7 @@
1749
  "physical_plausibility": 69,
1750
  "prompt_faithfulness": 118,
1751
  "rubric_adaptive": 118,
 
1752
  "text_rendering": 112,
1753
  "visual_reference_evaluation": 95
1754
  },
@@ -1760,6 +1863,7 @@
1760
  "physical_plausibility": 5.1,
1761
  "prompt_faithfulness": 1.0,
1762
  "rubric_adaptive": 1.8,
 
1763
  "text_rendering": 0.0,
1764
  "visual_reference_evaluation": 1.2
1765
  },
@@ -1785,6 +1889,7 @@
1785
  "physical_plausibility": 352,
1786
  "prompt_faithfulness": 419,
1787
  "rubric_adaptive": 419,
 
1788
  "text_rendering": 264,
1789
  "visual_reference_evaluation": 352
1790
  },
@@ -1796,6 +1901,7 @@
1796
  "physical_plausibility": 70.5,
1797
  "prompt_faithfulness": 63.5,
1798
  "rubric_adaptive": 66.5,
 
1799
  "text_rendering": 69.8,
1800
  "visual_reference_evaluation": 60.4
1801
  },
@@ -1819,6 +1925,7 @@
1819
  "physical_plausibility": 371,
1820
  "prompt_faithfulness": 419,
1821
  "rubric_adaptive": 419,
 
1822
  "text_rendering": 237,
1823
  "visual_reference_evaluation": 351
1824
  },
@@ -1830,6 +1937,7 @@
1830
  "physical_plausibility": 73.2,
1831
  "prompt_faithfulness": 58.9,
1832
  "rubric_adaptive": 64.0,
 
1833
  "text_rendering": 62.0,
1834
  "visual_reference_evaluation": 57.1
1835
  },
@@ -1853,6 +1961,7 @@
1853
  "physical_plausibility": 323,
1854
  "prompt_faithfulness": 388,
1855
  "rubric_adaptive": 388,
 
1856
  "text_rendering": 237,
1857
  "visual_reference_evaluation": 326
1858
  },
@@ -1864,6 +1973,7 @@
1864
  "physical_plausibility": 68.2,
1865
  "prompt_faithfulness": 58.8,
1866
  "rubric_adaptive": 63.1,
 
1867
  "text_rendering": 62.1,
1868
  "visual_reference_evaluation": 55.9
1869
  },
@@ -1887,6 +1997,7 @@
1887
  "physical_plausibility": 344,
1888
  "prompt_faithfulness": 410,
1889
  "rubric_adaptive": 410,
 
1890
  "text_rendering": 203,
1891
  "visual_reference_evaluation": 347
1892
  },
@@ -1898,6 +2009,7 @@
1898
  "physical_plausibility": 65.9,
1899
  "prompt_faithfulness": 44.4,
1900
  "rubric_adaptive": 51.0,
 
1901
  "text_rendering": 52.5,
1902
  "visual_reference_evaluation": 40.5
1903
  },
@@ -1921,6 +2033,7 @@
1921
  "physical_plausibility": 354,
1922
  "prompt_faithfulness": 419,
1923
  "rubric_adaptive": 419,
 
1924
  "text_rendering": 205,
1925
  "visual_reference_evaluation": 358
1926
  },
@@ -1932,6 +2045,7 @@
1932
  "physical_plausibility": 62.5,
1933
  "prompt_faithfulness": 41.9,
1934
  "rubric_adaptive": 48.4,
 
1935
  "text_rendering": 48.1,
1936
  "visual_reference_evaluation": 37.3
1937
  },
@@ -1955,6 +2069,7 @@
1955
  "physical_plausibility": 366,
1956
  "prompt_faithfulness": 419,
1957
  "rubric_adaptive": 419,
 
1958
  "text_rendering": 241,
1959
  "visual_reference_evaluation": 356
1960
  },
@@ -1966,6 +2081,7 @@
1966
  "physical_plausibility": 59.9,
1967
  "prompt_faithfulness": 43.5,
1968
  "rubric_adaptive": 49.4,
 
1969
  "text_rendering": 45.3,
1970
  "visual_reference_evaluation": 37.2
1971
  },
@@ -1989,6 +2105,7 @@
1989
  "physical_plausibility": 369,
1990
  "prompt_faithfulness": 418,
1991
  "rubric_adaptive": 419,
 
1992
  "text_rendering": 219,
1993
  "visual_reference_evaluation": 348
1994
  },
@@ -2000,6 +2117,7 @@
2000
  "physical_plausibility": 63.0,
2001
  "prompt_faithfulness": 40.4,
2002
  "rubric_adaptive": 47.6,
 
2003
  "text_rendering": 35.8,
2004
  "visual_reference_evaluation": 36.3
2005
  },
@@ -2023,6 +2141,7 @@
2023
  "physical_plausibility": 367,
2024
  "prompt_faithfulness": 419,
2025
  "rubric_adaptive": 419,
 
2026
  "text_rendering": 236,
2027
  "visual_reference_evaluation": 349
2028
  },
@@ -2034,6 +2153,7 @@
2034
  "physical_plausibility": 62.0,
2035
  "prompt_faithfulness": 40.2,
2036
  "rubric_adaptive": 46.2,
 
2037
  "text_rendering": 29.8,
2038
  "visual_reference_evaluation": 36.4
2039
  },
@@ -2057,6 +2177,7 @@
2057
  "physical_plausibility": 388,
2058
  "prompt_faithfulness": 419,
2059
  "rubric_adaptive": 419,
 
2060
  "text_rendering": 212,
2061
  "visual_reference_evaluation": 348
2062
  },
@@ -2068,6 +2189,7 @@
2068
  "physical_plausibility": 52.0,
2069
  "prompt_faithfulness": 28.4,
2070
  "rubric_adaptive": 35.2,
 
2071
  "text_rendering": 14.9,
2072
  "visual_reference_evaluation": 25.9
2073
  },
@@ -2091,6 +2213,7 @@
2091
  "physical_plausibility": 365,
2092
  "prompt_faithfulness": 419,
2093
  "rubric_adaptive": 419,
 
2094
  "text_rendering": 230,
2095
  "visual_reference_evaluation": 348
2096
  },
@@ -2102,6 +2225,7 @@
2102
  "physical_plausibility": 53.1,
2103
  "prompt_faithfulness": 23.9,
2104
  "rubric_adaptive": 31.2,
 
2105
  "text_rendering": 9.9,
2106
  "visual_reference_evaluation": 21.3
2107
  },
@@ -2125,6 +2249,7 @@
2125
  "physical_plausibility": 355,
2126
  "prompt_faithfulness": 418,
2127
  "rubric_adaptive": 419,
 
2128
  "text_rendering": 223,
2129
  "visual_reference_evaluation": 347
2130
  },
@@ -2136,6 +2261,7 @@
2136
  "physical_plausibility": 49.9,
2137
  "prompt_faithfulness": 17.6,
2138
  "rubric_adaptive": 25.6,
 
2139
  "text_rendering": 5.0,
2140
  "visual_reference_evaluation": 14.6
2141
  },
@@ -2159,6 +2285,7 @@
2159
  "physical_plausibility": 373,
2160
  "prompt_faithfulness": 419,
2161
  "rubric_adaptive": 419,
 
2162
  "text_rendering": 213,
2163
  "visual_reference_evaluation": 348
2164
  },
@@ -2170,6 +2297,7 @@
2170
  "physical_plausibility": 41.1,
2171
  "prompt_faithfulness": 18.9,
2172
  "rubric_adaptive": 25.4,
 
2173
  "text_rendering": 4.5,
2174
  "visual_reference_evaluation": 18.8
2175
  },
@@ -2193,6 +2321,7 @@
2193
  "physical_plausibility": 388,
2194
  "prompt_faithfulness": 419,
2195
  "rubric_adaptive": 419,
 
2196
  "text_rendering": 305,
2197
  "visual_reference_evaluation": 402
2198
  },
@@ -2204,6 +2333,7 @@
2204
  "physical_plausibility": 21.5,
2205
  "prompt_faithfulness": 6.7,
2206
  "rubric_adaptive": 9.6,
 
2207
  "text_rendering": 0.2,
2208
  "visual_reference_evaluation": 6.1
2209
  },
@@ -2229,6 +2359,7 @@
2229
  "physical_plausibility": 176,
2230
  "prompt_faithfulness": 273,
2231
  "rubric_adaptive": 273,
 
2232
  "text_rendering": 217,
2233
  "visual_reference_evaluation": 222
2234
  },
@@ -2240,6 +2371,7 @@
2240
  "physical_plausibility": 80.2,
2241
  "prompt_faithfulness": 68.9,
2242
  "rubric_adaptive": 69.1,
 
2243
  "text_rendering": 73.8,
2244
  "visual_reference_evaluation": 67.1
2245
  },
@@ -2263,6 +2395,7 @@
2263
  "physical_plausibility": 215,
2264
  "prompt_faithfulness": 273,
2265
  "rubric_adaptive": 273,
 
2266
  "text_rendering": 208,
2267
  "visual_reference_evaluation": 223
2268
  },
@@ -2274,6 +2407,7 @@
2274
  "physical_plausibility": 80.2,
2275
  "prompt_faithfulness": 59.3,
2276
  "rubric_adaptive": 60.3,
 
2277
  "text_rendering": 62.4,
2278
  "visual_reference_evaluation": 56.9
2279
  },
@@ -2297,6 +2431,7 @@
2297
  "physical_plausibility": 184,
2298
  "prompt_faithfulness": 272,
2299
  "rubric_adaptive": 272,
 
2300
  "text_rendering": 213,
2301
  "visual_reference_evaluation": 226
2302
  },
@@ -2308,6 +2443,7 @@
2308
  "physical_plausibility": 74.8,
2309
  "prompt_faithfulness": 58.5,
2310
  "rubric_adaptive": 58.2,
 
2311
  "text_rendering": 56.3,
2312
  "visual_reference_evaluation": 56.2
2313
  },
@@ -2331,6 +2467,7 @@
2331
  "physical_plausibility": 173,
2332
  "prompt_faithfulness": 271,
2333
  "rubric_adaptive": 271,
 
2334
  "text_rendering": 197,
2335
  "visual_reference_evaluation": 224
2336
  },
@@ -2342,6 +2479,7 @@
2342
  "physical_plausibility": 73.4,
2343
  "prompt_faithfulness": 46.1,
2344
  "rubric_adaptive": 48.4,
 
2345
  "text_rendering": 48.8,
2346
  "visual_reference_evaluation": 41.5
2347
  },
@@ -2365,6 +2503,7 @@
2365
  "physical_plausibility": 179,
2366
  "prompt_faithfulness": 273,
2367
  "rubric_adaptive": 273,
 
2368
  "text_rendering": 194,
2369
  "visual_reference_evaluation": 227
2370
  },
@@ -2376,6 +2515,7 @@
2376
  "physical_plausibility": 67.9,
2377
  "prompt_faithfulness": 42.6,
2378
  "rubric_adaptive": 45.5,
 
2379
  "text_rendering": 44.5,
2380
  "visual_reference_evaluation": 39.2
2381
  },
@@ -2399,6 +2539,7 @@
2399
  "physical_plausibility": 206,
2400
  "prompt_faithfulness": 273,
2401
  "rubric_adaptive": 273,
 
2402
  "text_rendering": 214,
2403
  "visual_reference_evaluation": 227
2404
  },
@@ -2410,6 +2551,7 @@
2410
  "physical_plausibility": 60.2,
2411
  "prompt_faithfulness": 37.9,
2412
  "rubric_adaptive": 42.2,
 
2413
  "text_rendering": 39.6,
2414
  "visual_reference_evaluation": 32.5
2415
  },
@@ -2433,6 +2575,7 @@
2433
  "physical_plausibility": 211,
2434
  "prompt_faithfulness": 273,
2435
  "rubric_adaptive": 273,
 
2436
  "text_rendering": 208,
2437
  "visual_reference_evaluation": 222
2438
  },
@@ -2444,6 +2587,7 @@
2444
  "physical_plausibility": 63.7,
2445
  "prompt_faithfulness": 35.2,
2446
  "rubric_adaptive": 38.4,
 
2447
  "text_rendering": 28.5,
2448
  "visual_reference_evaluation": 30.7
2449
  },
@@ -2467,6 +2611,7 @@
2467
  "physical_plausibility": 202,
2468
  "prompt_faithfulness": 273,
2469
  "rubric_adaptive": 273,
 
2470
  "text_rendering": 212,
2471
  "visual_reference_evaluation": 222
2472
  },
@@ -2478,6 +2623,7 @@
2478
  "physical_plausibility": 64.5,
2479
  "prompt_faithfulness": 34.8,
2480
  "rubric_adaptive": 37.4,
 
2481
  "text_rendering": 24.5,
2482
  "visual_reference_evaluation": 31.3
2483
  },
@@ -2501,6 +2647,7 @@
2501
  "physical_plausibility": 240,
2502
  "prompt_faithfulness": 273,
2503
  "rubric_adaptive": 273,
 
2504
  "text_rendering": 198,
2505
  "visual_reference_evaluation": 222
2506
  },
@@ -2512,6 +2659,7 @@
2512
  "physical_plausibility": 39.8,
2513
  "prompt_faithfulness": 16.3,
2514
  "rubric_adaptive": 20.3,
 
2515
  "text_rendering": 2.8,
2516
  "visual_reference_evaluation": 16.9
2517
  },
@@ -2535,6 +2683,7 @@
2535
  "physical_plausibility": 212,
2536
  "prompt_faithfulness": 273,
2537
  "rubric_adaptive": 273,
 
2538
  "text_rendering": 209,
2539
  "visual_reference_evaluation": 222
2540
  },
@@ -2546,6 +2695,7 @@
2546
  "physical_plausibility": 43.9,
2547
  "prompt_faithfulness": 15.8,
2548
  "rubric_adaptive": 19.9,
 
2549
  "text_rendering": 2.5,
2550
  "visual_reference_evaluation": 15.7
2551
  },
@@ -2569,6 +2719,7 @@
2569
  "physical_plausibility": 215,
2570
  "prompt_faithfulness": 272,
2571
  "rubric_adaptive": 273,
 
2572
  "text_rendering": 202,
2573
  "visual_reference_evaluation": 221
2574
  },
@@ -2580,6 +2731,7 @@
2580
  "physical_plausibility": 39.5,
2581
  "prompt_faithfulness": 10.0,
2582
  "rubric_adaptive": 15.1,
 
2583
  "text_rendering": 1.6,
2584
  "visual_reference_evaluation": 9.5
2585
  },
@@ -2603,6 +2755,7 @@
2603
  "physical_plausibility": 216,
2604
  "prompt_faithfulness": 273,
2605
  "rubric_adaptive": 273,
 
2606
  "text_rendering": 193,
2607
  "visual_reference_evaluation": 222
2608
  },
@@ -2614,6 +2767,7 @@
2614
  "physical_plausibility": 34.9,
2615
  "prompt_faithfulness": 12.8,
2616
  "rubric_adaptive": 14.8,
 
2617
  "text_rendering": 1.9,
2618
  "visual_reference_evaluation": 12.8
2619
  },
@@ -2637,6 +2791,7 @@
2637
  "physical_plausibility": 227,
2638
  "prompt_faithfulness": 273,
2639
  "rubric_adaptive": 273,
 
2640
  "text_rendering": 225,
2641
  "visual_reference_evaluation": 252
2642
  },
@@ -2648,6 +2803,7 @@
2648
  "physical_plausibility": 17.6,
2649
  "prompt_faithfulness": 5.1,
2650
  "rubric_adaptive": 6.7,
 
2651
  "text_rendering": 1.0,
2652
  "visual_reference_evaluation": 5.1
2653
  },
@@ -2673,6 +2829,7 @@
2673
  "physical_plausibility": 23,
2674
  "prompt_faithfulness": 30,
2675
  "rubric_adaptive": 30,
 
2676
  "text_rendering": 23,
2677
  "visual_reference_evaluation": 22
2678
  },
@@ -2684,6 +2841,7 @@
2684
  "physical_plausibility": 78.3,
2685
  "prompt_faithfulness": 66.1,
2686
  "rubric_adaptive": 69.0,
 
2687
  "text_rendering": 76.1,
2688
  "visual_reference_evaluation": 65.9
2689
  },
@@ -2707,6 +2865,7 @@
2707
  "physical_plausibility": 25,
2708
  "prompt_faithfulness": 30,
2709
  "rubric_adaptive": 30,
 
2710
  "text_rendering": 20,
2711
  "visual_reference_evaluation": 21
2712
  },
@@ -2718,6 +2877,7 @@
2718
  "physical_plausibility": 78.0,
2719
  "prompt_faithfulness": 52.2,
2720
  "rubric_adaptive": 55.4,
 
2721
  "text_rendering": 60.8,
2722
  "visual_reference_evaluation": 51.6
2723
  },
@@ -2741,6 +2901,7 @@
2741
  "physical_plausibility": 23,
2742
  "prompt_faithfulness": 30,
2743
  "rubric_adaptive": 30,
 
2744
  "text_rendering": 20,
2745
  "visual_reference_evaluation": 24
2746
  },
@@ -2752,6 +2913,7 @@
2752
  "physical_plausibility": 63.8,
2753
  "prompt_faithfulness": 54.4,
2754
  "rubric_adaptive": 56.2,
 
2755
  "text_rendering": 66.7,
2756
  "visual_reference_evaluation": 50.7
2757
  },
@@ -2775,6 +2937,7 @@
2775
  "physical_plausibility": 23,
2776
  "prompt_faithfulness": 30,
2777
  "rubric_adaptive": 30,
 
2778
  "text_rendering": 19,
2779
  "visual_reference_evaluation": 24
2780
  },
@@ -2786,6 +2949,7 @@
2786
  "physical_plausibility": 58.0,
2787
  "prompt_faithfulness": 46.7,
2788
  "rubric_adaptive": 54.6,
 
2789
  "text_rendering": 66.7,
2790
  "visual_reference_evaluation": 50.0
2791
  },
@@ -2809,6 +2973,7 @@
2809
  "physical_plausibility": 21,
2810
  "prompt_faithfulness": 30,
2811
  "rubric_adaptive": 30,
 
2812
  "text_rendering": 21,
2813
  "visual_reference_evaluation": 24
2814
  },
@@ -2820,6 +2985,7 @@
2820
  "physical_plausibility": 60.3,
2821
  "prompt_faithfulness": 45.6,
2822
  "rubric_adaptive": 47.7,
 
2823
  "text_rendering": 68.3,
2824
  "visual_reference_evaluation": 40.3
2825
  },
@@ -2843,6 +3009,7 @@
2843
  "physical_plausibility": 23,
2844
  "prompt_faithfulness": 30,
2845
  "rubric_adaptive": 30,
 
2846
  "text_rendering": 19,
2847
  "visual_reference_evaluation": 24
2848
  },
@@ -2854,6 +3021,7 @@
2854
  "physical_plausibility": 62.3,
2855
  "prompt_faithfulness": 41.1,
2856
  "rubric_adaptive": 46.3,
 
2857
  "text_rendering": 57.0,
2858
  "visual_reference_evaluation": 43.1
2859
  },
@@ -2877,6 +3045,7 @@
2877
  "physical_plausibility": 22,
2878
  "prompt_faithfulness": 30,
2879
  "rubric_adaptive": 30,
 
2880
  "text_rendering": 20,
2881
  "visual_reference_evaluation": 21
2882
  },
@@ -2888,6 +3057,7 @@
2888
  "physical_plausibility": 68.2,
2889
  "prompt_faithfulness": 37.8,
2890
  "rubric_adaptive": 42.2,
 
2891
  "text_rendering": 35.0,
2892
  "visual_reference_evaluation": 32.5
2893
  },
@@ -2911,6 +3081,7 @@
2911
  "physical_plausibility": 24,
2912
  "prompt_faithfulness": 29,
2913
  "rubric_adaptive": 30,
 
2914
  "text_rendering": 17,
2915
  "visual_reference_evaluation": 21
2916
  },
@@ -2922,6 +3093,7 @@
2922
  "physical_plausibility": 64.6,
2923
  "prompt_faithfulness": 40.8,
2924
  "rubric_adaptive": 41.6,
 
2925
  "text_rendering": 47.1,
2926
  "visual_reference_evaluation": 37.3
2927
  },
@@ -2945,6 +3117,7 @@
2945
  "physical_plausibility": 29,
2946
  "prompt_faithfulness": 30,
2947
  "rubric_adaptive": 30,
 
2948
  "text_rendering": 16,
2949
  "visual_reference_evaluation": 21
2950
  },
@@ -2956,6 +3129,7 @@
2956
  "physical_plausibility": 37.9,
2957
  "prompt_faithfulness": 15.6,
2958
  "rubric_adaptive": 22.8,
 
2959
  "text_rendering": 8.3,
2960
  "visual_reference_evaluation": 18.3
2961
  },
@@ -2979,6 +3153,7 @@
2979
  "physical_plausibility": 23,
2980
  "prompt_faithfulness": 30,
2981
  "rubric_adaptive": 30,
 
2982
  "text_rendering": 19,
2983
  "visual_reference_evaluation": 21
2984
  },
@@ -2990,6 +3165,7 @@
2990
  "physical_plausibility": 44.9,
2991
  "prompt_faithfulness": 12.8,
2992
  "rubric_adaptive": 19.0,
 
2993
  "text_rendering": 7.0,
2994
  "visual_reference_evaluation": 7.9
2995
  },
@@ -3013,6 +3189,7 @@
3013
  "physical_plausibility": 23,
3014
  "prompt_faithfulness": 30,
3015
  "rubric_adaptive": 30,
 
3016
  "text_rendering": 21,
3017
  "visual_reference_evaluation": 21
3018
  },
@@ -3024,6 +3201,7 @@
3024
  "physical_plausibility": 34.1,
3025
  "prompt_faithfulness": 14.4,
3026
  "rubric_adaptive": 22.0,
 
3027
  "text_rendering": 2.4,
3028
  "visual_reference_evaluation": 15.1
3029
  },
@@ -3047,6 +3225,7 @@
3047
  "physical_plausibility": 27,
3048
  "prompt_faithfulness": 30,
3049
  "rubric_adaptive": 30,
 
3050
  "text_rendering": 18,
3051
  "visual_reference_evaluation": 21
3052
  },
@@ -3058,6 +3237,7 @@
3058
  "physical_plausibility": 31.5,
3059
  "prompt_faithfulness": 7.8,
3060
  "rubric_adaptive": 10.2,
 
3061
  "text_rendering": 5.6,
3062
  "visual_reference_evaluation": 9.5
3063
  },
@@ -3081,6 +3261,7 @@
3081
  "physical_plausibility": 28,
3082
  "prompt_faithfulness": 30,
3083
  "rubric_adaptive": 30,
 
3084
  "text_rendering": 20,
3085
  "visual_reference_evaluation": 24
3086
  },
@@ -3092,6 +3273,7 @@
3092
  "physical_plausibility": 31.5,
3093
  "prompt_faithfulness": 3.9,
3094
  "rubric_adaptive": 7.9,
 
3095
  "text_rendering": 8.3,
3096
  "visual_reference_evaluation": 0.7
3097
  },
@@ -3117,6 +3299,7 @@
3117
  "physical_plausibility": 259,
3118
  "prompt_faithfulness": 411,
3119
  "rubric_adaptive": 411,
 
3120
  "text_rendering": 393,
3121
  "visual_reference_evaluation": 299
3122
  },
@@ -3128,6 +3311,7 @@
3128
  "physical_plausibility": 86.5,
3129
  "prompt_faithfulness": 73.7,
3130
  "rubric_adaptive": 73.5,
 
3131
  "text_rendering": 76.3,
3132
  "visual_reference_evaluation": 70.7
3133
  },
@@ -3151,6 +3335,7 @@
3151
  "physical_plausibility": 320,
3152
  "prompt_faithfulness": 411,
3153
  "rubric_adaptive": 411,
 
3154
  "text_rendering": 385,
3155
  "visual_reference_evaluation": 299
3156
  },
@@ -3162,6 +3347,7 @@
3162
  "physical_plausibility": 85.3,
3163
  "prompt_faithfulness": 64.7,
3164
  "rubric_adaptive": 65.4,
 
3165
  "text_rendering": 65.2,
3166
  "visual_reference_evaluation": 62.5
3167
  },
@@ -3185,6 +3371,7 @@
3185
  "physical_plausibility": 270,
3186
  "prompt_faithfulness": 404,
3187
  "rubric_adaptive": 404,
 
3188
  "text_rendering": 388,
3189
  "visual_reference_evaluation": 299
3190
  },
@@ -3196,6 +3383,7 @@
3196
  "physical_plausibility": 82.8,
3197
  "prompt_faithfulness": 64.4,
3198
  "rubric_adaptive": 64.2,
 
3199
  "text_rendering": 61.0,
3200
  "visual_reference_evaluation": 61.2
3201
  },
@@ -3219,6 +3407,7 @@
3219
  "physical_plausibility": 251,
3220
  "prompt_faithfulness": 408,
3221
  "rubric_adaptive": 408,
 
3222
  "text_rendering": 391,
3223
  "visual_reference_evaluation": 303
3224
  },
@@ -3230,6 +3419,7 @@
3230
  "physical_plausibility": 80.9,
3231
  "prompt_faithfulness": 51.7,
3232
  "rubric_adaptive": 54.0,
 
3233
  "text_rendering": 54.9,
3234
  "visual_reference_evaluation": 46.3
3235
  },
@@ -3253,6 +3443,7 @@
3253
  "physical_plausibility": 253,
3254
  "prompt_faithfulness": 411,
3255
  "rubric_adaptive": 411,
 
3256
  "text_rendering": 394,
3257
  "visual_reference_evaluation": 307
3258
  },
@@ -3264,6 +3455,7 @@
3264
  "physical_plausibility": 78.2,
3265
  "prompt_faithfulness": 49.2,
3266
  "rubric_adaptive": 51.5,
 
3267
  "text_rendering": 53.2,
3268
  "visual_reference_evaluation": 43.4
3269
  },
@@ -3287,6 +3479,7 @@
3287
  "physical_plausibility": 291,
3288
  "prompt_faithfulness": 411,
3289
  "rubric_adaptive": 411,
 
3290
  "text_rendering": 399,
3291
  "visual_reference_evaluation": 306
3292
  },
@@ -3298,6 +3491,7 @@
3298
  "physical_plausibility": 69.6,
3299
  "prompt_faithfulness": 45.6,
3300
  "rubric_adaptive": 48.5,
 
3301
  "text_rendering": 49.1,
3302
  "visual_reference_evaluation": 37.5
3303
  },
@@ -3321,6 +3515,7 @@
3321
  "physical_plausibility": 297,
3322
  "prompt_faithfulness": 411,
3323
  "rubric_adaptive": 411,
 
3324
  "text_rendering": 396,
3325
  "visual_reference_evaluation": 298
3326
  },
@@ -3332,6 +3527,7 @@
3332
  "physical_plausibility": 70.9,
3333
  "prompt_faithfulness": 38.2,
3334
  "rubric_adaptive": 42.4,
 
3335
  "text_rendering": 36.3,
3336
  "visual_reference_evaluation": 33.9
3337
  },
@@ -3355,6 +3551,7 @@
3355
  "physical_plausibility": 293,
3356
  "prompt_faithfulness": 411,
3357
  "rubric_adaptive": 411,
 
3358
  "text_rendering": 392,
3359
  "visual_reference_evaluation": 299
3360
  },
@@ -3366,6 +3563,7 @@
3366
  "physical_plausibility": 72.9,
3367
  "prompt_faithfulness": 34.3,
3368
  "rubric_adaptive": 37.4,
 
3369
  "text_rendering": 26.0,
3370
  "visual_reference_evaluation": 30.5
3371
  },
@@ -3389,6 +3587,7 @@
3389
  "physical_plausibility": 354,
3390
  "prompt_faithfulness": 411,
3391
  "rubric_adaptive": 411,
 
3392
  "text_rendering": 402,
3393
  "visual_reference_evaluation": 298
3394
  },
@@ -3400,6 +3599,7 @@
3400
  "physical_plausibility": 44.4,
3401
  "prompt_faithfulness": 16.7,
3402
  "rubric_adaptive": 20.9,
 
3403
  "text_rendering": 10.9,
3404
  "visual_reference_evaluation": 15.8
3405
  },
@@ -3423,6 +3623,7 @@
3423
  "physical_plausibility": 297,
3424
  "prompt_faithfulness": 411,
3425
  "rubric_adaptive": 411,
 
3426
  "text_rendering": 400,
3427
  "visual_reference_evaluation": 298
3428
  },
@@ -3434,6 +3635,7 @@
3434
  "physical_plausibility": 49.6,
3435
  "prompt_faithfulness": 14.1,
3436
  "rubric_adaptive": 18.8,
 
3437
  "text_rendering": 7.2,
3438
  "visual_reference_evaluation": 12.8
3439
  },
@@ -3457,6 +3659,7 @@
3457
  "physical_plausibility": 289,
3458
  "prompt_faithfulness": 410,
3459
  "rubric_adaptive": 411,
 
3460
  "text_rendering": 391,
3461
  "visual_reference_evaluation": 297
3462
  },
@@ -3468,6 +3671,7 @@
3468
  "physical_plausibility": 45.8,
3469
  "prompt_faithfulness": 10.1,
3470
  "rubric_adaptive": 15.3,
 
3471
  "text_rendering": 3.9,
3472
  "visual_reference_evaluation": 9.3
3473
  },
@@ -3491,6 +3695,7 @@
3491
  "physical_plausibility": 319,
3492
  "prompt_faithfulness": 411,
3493
  "rubric_adaptive": 411,
 
3494
  "text_rendering": 390,
3495
  "visual_reference_evaluation": 298
3496
  },
@@ -3502,6 +3707,7 @@
3502
  "physical_plausibility": 35.9,
3503
  "prompt_faithfulness": 10.3,
3504
  "rubric_adaptive": 13.7,
 
3505
  "text_rendering": 3.4,
3506
  "visual_reference_evaluation": 9.7
3507
  },
@@ -3525,6 +3731,7 @@
3525
  "physical_plausibility": 337,
3526
  "prompt_faithfulness": 411,
3527
  "rubric_adaptive": 411,
 
3528
  "text_rendering": 397,
3529
  "visual_reference_evaluation": 369
3530
  },
@@ -3536,6 +3743,7 @@
3536
  "physical_plausibility": 14.3,
3537
  "prompt_faithfulness": 2.8,
3538
  "rubric_adaptive": 4.7,
 
3539
  "text_rendering": 1.0,
3540
  "visual_reference_evaluation": 3.3
3541
  },
@@ -3561,6 +3769,7 @@
3561
  "physical_plausibility": 10,
3562
  "prompt_faithfulness": 38,
3563
  "rubric_adaptive": 38,
 
3564
  "text_rendering": 35,
3565
  "visual_reference_evaluation": 25
3566
  },
@@ -3572,6 +3781,7 @@
3572
  "physical_plausibility": 85.0,
3573
  "prompt_faithfulness": 63.2,
3574
  "rubric_adaptive": 57.9,
 
3575
  "text_rendering": 68.1,
3576
  "visual_reference_evaluation": 56.7
3577
  },
@@ -3595,6 +3805,7 @@
3595
  "physical_plausibility": 29,
3596
  "prompt_faithfulness": 38,
3597
  "rubric_adaptive": 38,
 
3598
  "text_rendering": 36,
3599
  "visual_reference_evaluation": 25
3600
  },
@@ -3606,6 +3817,7 @@
3606
  "physical_plausibility": 86.8,
3607
  "prompt_faithfulness": 53.9,
3608
  "rubric_adaptive": 48.5,
 
3609
  "text_rendering": 60.6,
3610
  "visual_reference_evaluation": 45.3
3611
  },
@@ -3629,6 +3841,7 @@
3629
  "physical_plausibility": 16,
3630
  "prompt_faithfulness": 38,
3631
  "rubric_adaptive": 38,
 
3632
  "text_rendering": 37,
3633
  "visual_reference_evaluation": 27
3634
  },
@@ -3640,6 +3853,7 @@
3640
  "physical_plausibility": 89.6,
3641
  "prompt_faithfulness": 56.1,
3642
  "rubric_adaptive": 53.6,
 
3643
  "text_rendering": 58.1,
3644
  "visual_reference_evaluation": 46.9
3645
  },
@@ -3663,6 +3877,7 @@
3663
  "physical_plausibility": 8,
3664
  "prompt_faithfulness": 38,
3665
  "rubric_adaptive": 38,
 
3666
  "text_rendering": 38,
3667
  "visual_reference_evaluation": 27
3668
  },
@@ -3674,6 +3889,7 @@
3674
  "physical_plausibility": 56.2,
3675
  "prompt_faithfulness": 36.0,
3676
  "rubric_adaptive": 32.7,
 
3677
  "text_rendering": 40.4,
3678
  "visual_reference_evaluation": 20.4
3679
  },
@@ -3697,6 +3913,7 @@
3697
  "physical_plausibility": 11,
3698
  "prompt_faithfulness": 38,
3699
  "rubric_adaptive": 38,
 
3700
  "text_rendering": 35,
3701
  "visual_reference_evaluation": 27
3702
  },
@@ -3708,6 +3925,7 @@
3708
  "physical_plausibility": 77.3,
3709
  "prompt_faithfulness": 32.5,
3710
  "rubric_adaptive": 29.2,
 
3711
  "text_rendering": 35.2,
3712
  "visual_reference_evaluation": 19.1
3713
  },
@@ -3731,6 +3949,7 @@
3731
  "physical_plausibility": 16,
3732
  "prompt_faithfulness": 38,
3733
  "rubric_adaptive": 38,
 
3734
  "text_rendering": 37,
3735
  "visual_reference_evaluation": 27
3736
  },
@@ -3742,6 +3961,7 @@
3742
  "physical_plausibility": 55.2,
3743
  "prompt_faithfulness": 35.1,
3744
  "rubric_adaptive": 27.5,
 
3745
  "text_rendering": 39.6,
3746
  "visual_reference_evaluation": 9.3
3747
  },
@@ -3765,6 +3985,7 @@
3765
  "physical_plausibility": 23,
3766
  "prompt_faithfulness": 38,
3767
  "rubric_adaptive": 38,
 
3768
  "text_rendering": 35,
3769
  "visual_reference_evaluation": 25
3770
  },
@@ -3776,6 +3997,7 @@
3776
  "physical_plausibility": 75.4,
3777
  "prompt_faithfulness": 22.4,
3778
  "rubric_adaptive": 21.2,
 
3779
  "text_rendering": 19.0,
3780
  "visual_reference_evaluation": 16.7
3781
  },
@@ -3799,6 +4021,7 @@
3799
  "physical_plausibility": 20,
3800
  "prompt_faithfulness": 38,
3801
  "rubric_adaptive": 38,
 
3802
  "text_rendering": 38,
3803
  "visual_reference_evaluation": 25
3804
  },
@@ -3810,6 +4033,7 @@
3810
  "physical_plausibility": 55.8,
3811
  "prompt_faithfulness": 22.4,
3812
  "rubric_adaptive": 22.0,
 
3813
  "text_rendering": 23.2,
3814
  "visual_reference_evaluation": 9.3
3815
  },
@@ -3833,6 +4057,7 @@
3833
  "physical_plausibility": 28,
3834
  "prompt_faithfulness": 38,
3835
  "rubric_adaptive": 38,
 
3836
  "text_rendering": 38,
3837
  "visual_reference_evaluation": 25
3838
  },
@@ -3844,6 +4069,7 @@
3844
  "physical_plausibility": 28.0,
3845
  "prompt_faithfulness": 3.5,
3846
  "rubric_adaptive": 5.7,
 
3847
  "text_rendering": 3.1,
3848
  "visual_reference_evaluation": 4.0
3849
  },
@@ -3867,6 +4093,7 @@
3867
  "physical_plausibility": 23,
3868
  "prompt_faithfulness": 38,
3869
  "rubric_adaptive": 38,
 
3870
  "text_rendering": 38,
3871
  "visual_reference_evaluation": 25
3872
  },
@@ -3878,6 +4105,7 @@
3878
  "physical_plausibility": 15.2,
3879
  "prompt_faithfulness": 2.6,
3880
  "rubric_adaptive": 3.3,
 
3881
  "text_rendering": 1.3,
3882
  "visual_reference_evaluation": 1.3
3883
  },
@@ -3901,6 +4129,7 @@
3901
  "physical_plausibility": 20,
3902
  "prompt_faithfulness": 38,
3903
  "rubric_adaptive": 38,
 
3904
  "text_rendering": 38,
3905
  "visual_reference_evaluation": 25
3906
  },
@@ -3912,6 +4141,7 @@
3912
  "physical_plausibility": 28.3,
3913
  "prompt_faithfulness": 1.8,
3914
  "rubric_adaptive": 3.8,
 
3915
  "text_rendering": 0.9,
3916
  "visual_reference_evaluation": 4.0
3917
  },
@@ -3935,6 +4165,7 @@
3935
  "physical_plausibility": 26,
3936
  "prompt_faithfulness": 38,
3937
  "rubric_adaptive": 38,
 
3938
  "text_rendering": 34,
3939
  "visual_reference_evaluation": 25
3940
  },
@@ -3946,6 +4177,7 @@
3946
  "physical_plausibility": 18.6,
3947
  "prompt_faithfulness": 0.4,
3948
  "rubric_adaptive": 2.2,
 
3949
  "text_rendering": 0.0,
3950
  "visual_reference_evaluation": 0.0
3951
  },
@@ -3969,6 +4201,7 @@
3969
  "physical_plausibility": 26,
3970
  "prompt_faithfulness": 38,
3971
  "rubric_adaptive": 38,
 
3972
  "text_rendering": 36,
3973
  "visual_reference_evaluation": 25
3974
  },
@@ -3980,6 +4213,7 @@
3980
  "physical_plausibility": 6.4,
3981
  "prompt_faithfulness": 0.4,
3982
  "rubric_adaptive": 1.2,
 
3983
  "text_rendering": 0.0,
3984
  "visual_reference_evaluation": 0.7
3985
  },
@@ -4005,6 +4239,7 @@
4005
  "physical_plausibility": 24,
4006
  "prompt_faithfulness": 56,
4007
  "rubric_adaptive": 56,
 
4008
  "text_rendering": 53,
4009
  "visual_reference_evaluation": 46
4010
  },
@@ -4016,6 +4251,7 @@
4016
  "physical_plausibility": 86.8,
4017
  "prompt_faithfulness": 69.6,
4018
  "rubric_adaptive": 64.9,
 
4019
  "text_rendering": 77.0,
4020
  "visual_reference_evaluation": 64.9
4021
  },
@@ -4039,6 +4275,7 @@
4039
  "physical_plausibility": 33,
4040
  "prompt_faithfulness": 56,
4041
  "rubric_adaptive": 56,
 
4042
  "text_rendering": 53,
4043
  "visual_reference_evaluation": 46
4044
  },
@@ -4050,6 +4287,7 @@
4050
  "physical_plausibility": 81.8,
4051
  "prompt_faithfulness": 59.5,
4052
  "rubric_adaptive": 58.9,
 
4053
  "text_rendering": 60.1,
4054
  "visual_reference_evaluation": 51.1
4055
  },
@@ -4073,6 +4311,7 @@
4073
  "physical_plausibility": 50,
4074
  "prompt_faithfulness": 56,
4075
  "rubric_adaptive": 56,
 
4076
  "text_rendering": 50,
4077
  "visual_reference_evaluation": 46
4078
  },
@@ -4084,6 +4323,7 @@
4084
  "physical_plausibility": 79.7,
4085
  "prompt_faithfulness": 59.4,
4086
  "rubric_adaptive": 52.9,
 
4087
  "text_rendering": 59.0,
4088
  "visual_reference_evaluation": 49.6
4089
  },
@@ -4107,6 +4347,7 @@
4107
  "physical_plausibility": 25,
4108
  "prompt_faithfulness": 56,
4109
  "rubric_adaptive": 56,
 
4110
  "text_rendering": 53,
4111
  "visual_reference_evaluation": 46
4112
  },
@@ -4118,6 +4359,7 @@
4118
  "physical_plausibility": 75.3,
4119
  "prompt_faithfulness": 45.1,
4120
  "rubric_adaptive": 43.3,
 
4121
  "text_rendering": 51.9,
4122
  "visual_reference_evaluation": 34.1
4123
  },
@@ -4141,6 +4383,7 @@
4141
  "physical_plausibility": 19,
4142
  "prompt_faithfulness": 56,
4143
  "rubric_adaptive": 56,
 
4144
  "text_rendering": 55,
4145
  "visual_reference_evaluation": 46
4146
  },
@@ -4152,6 +4395,7 @@
4152
  "physical_plausibility": 71.1,
4153
  "prompt_faithfulness": 45.5,
4154
  "rubric_adaptive": 44.0,
 
4155
  "text_rendering": 51.2,
4156
  "visual_reference_evaluation": 35.9
4157
  },
@@ -4175,6 +4419,7 @@
4175
  "physical_plausibility": 31,
4176
  "prompt_faithfulness": 56,
4177
  "rubric_adaptive": 56,
 
4178
  "text_rendering": 53,
4179
  "visual_reference_evaluation": 46
4180
  },
@@ -4186,6 +4431,7 @@
4186
  "physical_plausibility": 66.7,
4187
  "prompt_faithfulness": 42.3,
4188
  "rubric_adaptive": 39.8,
 
4189
  "text_rendering": 49.1,
4190
  "visual_reference_evaluation": 25.7
4191
  },
@@ -4209,6 +4455,7 @@
4209
  "physical_plausibility": 34,
4210
  "prompt_faithfulness": 56,
4211
  "rubric_adaptive": 56,
 
4212
  "text_rendering": 55,
4213
  "visual_reference_evaluation": 46
4214
  },
@@ -4220,6 +4467,7 @@
4220
  "physical_plausibility": 68.6,
4221
  "prompt_faithfulness": 31.8,
4222
  "rubric_adaptive": 34.3,
 
4223
  "text_rendering": 31.5,
4224
  "visual_reference_evaluation": 24.6
4225
  },
@@ -4243,6 +4491,7 @@
4243
  "physical_plausibility": 38,
4244
  "prompt_faithfulness": 56,
4245
  "rubric_adaptive": 56,
 
4246
  "text_rendering": 54,
4247
  "visual_reference_evaluation": 46
4248
  },
@@ -4254,6 +4503,7 @@
4254
  "physical_plausibility": 64.9,
4255
  "prompt_faithfulness": 27.1,
4256
  "rubric_adaptive": 26.6,
 
4257
  "text_rendering": 19.1,
4258
  "visual_reference_evaluation": 21.7
4259
  },
@@ -4277,6 +4527,7 @@
4277
  "physical_plausibility": 46,
4278
  "prompt_faithfulness": 56,
4279
  "rubric_adaptive": 56,
 
4280
  "text_rendering": 55,
4281
  "visual_reference_evaluation": 46
4282
  },
@@ -4288,6 +4539,7 @@
4288
  "physical_plausibility": 35.5,
4289
  "prompt_faithfulness": 8.0,
4290
  "rubric_adaptive": 13.1,
 
4291
  "text_rendering": 5.5,
4292
  "visual_reference_evaluation": 9.4
4293
  },
@@ -4311,6 +4563,7 @@
4311
  "physical_plausibility": 39,
4312
  "prompt_faithfulness": 56,
4313
  "rubric_adaptive": 56,
 
4314
  "text_rendering": 52,
4315
  "visual_reference_evaluation": 46
4316
  },
@@ -4322,6 +4575,7 @@
4322
  "physical_plausibility": 32.1,
4323
  "prompt_faithfulness": 6.0,
4324
  "rubric_adaptive": 9.1,
 
4325
  "text_rendering": 3.8,
4326
  "visual_reference_evaluation": 6.2
4327
  },
@@ -4345,6 +4599,7 @@
4345
  "physical_plausibility": 33,
4346
  "prompt_faithfulness": 56,
4347
  "rubric_adaptive": 56,
 
4348
  "text_rendering": 55,
4349
  "visual_reference_evaluation": 46
4350
  },
@@ -4356,6 +4611,7 @@
4356
  "physical_plausibility": 29.3,
4357
  "prompt_faithfulness": 3.0,
4358
  "rubric_adaptive": 6.3,
 
4359
  "text_rendering": 1.5,
4360
  "visual_reference_evaluation": 4.3
4361
  },
@@ -4379,6 +4635,7 @@
4379
  "physical_plausibility": 41,
4380
  "prompt_faithfulness": 56,
4381
  "rubric_adaptive": 56,
 
4382
  "text_rendering": 51,
4383
  "visual_reference_evaluation": 46
4384
  },
@@ -4390,6 +4647,7 @@
4390
  "physical_plausibility": 14.6,
4391
  "prompt_faithfulness": 2.7,
4392
  "rubric_adaptive": 5.2,
 
4393
  "text_rendering": 0.3,
4394
  "visual_reference_evaluation": 3.6
4395
  },
@@ -4413,6 +4671,7 @@
4413
  "physical_plausibility": 46,
4414
  "prompt_faithfulness": 56,
4415
  "rubric_adaptive": 56,
 
4416
  "text_rendering": 53,
4417
  "visual_reference_evaluation": 47
4418
  },
@@ -4424,6 +4683,7 @@
4424
  "physical_plausibility": 14.5,
4425
  "prompt_faithfulness": 1.8,
4426
  "rubric_adaptive": 2.9,
 
4427
  "text_rendering": 0.0,
4428
  "visual_reference_evaluation": 2.1
4429
  },
@@ -4449,6 +4709,7 @@
4449
  "physical_plausibility": 27,
4450
  "prompt_faithfulness": 33,
4451
  "rubric_adaptive": 33,
 
4452
  "text_rendering": 21,
4453
  "visual_reference_evaluation": 25
4454
  },
@@ -4460,6 +4721,7 @@
4460
  "physical_plausibility": 78.4,
4461
  "prompt_faithfulness": 67.2,
4462
  "rubric_adaptive": 68.6,
 
4463
  "text_rendering": 78.6,
4464
  "visual_reference_evaluation": 66.0
4465
  },
@@ -4483,6 +4745,7 @@
4483
  "physical_plausibility": 28,
4484
  "prompt_faithfulness": 33,
4485
  "rubric_adaptive": 33,
 
4486
  "text_rendering": 14,
4487
  "visual_reference_evaluation": 25
4488
  },
@@ -4494,6 +4757,7 @@
4494
  "physical_plausibility": 84.5,
4495
  "prompt_faithfulness": 58.1,
4496
  "rubric_adaptive": 62.7,
 
4497
  "text_rendering": 63.1,
4498
  "visual_reference_evaluation": 51.3
4499
  },
@@ -4508,40 +4772,6 @@
4508
  "overall_9": 67.1,
4509
  "type": "Commercial"
4510
  },
4511
- {
4512
- "component_counts": {
4513
- "ai_naturalness": 33,
4514
- "checklist": 33,
4515
- "composition_and_aesthetics": 33,
4516
- "image_quality": 33,
4517
- "physical_plausibility": 28,
4518
- "prompt_faithfulness": 33,
4519
- "rubric_adaptive": 33,
4520
- "text_rendering": 15,
4521
- "visual_reference_evaluation": 30
4522
- },
4523
- "components": {
4524
- "ai_naturalness": 65.2,
4525
- "checklist": 59.8,
4526
- "composition_and_aesthetics": 75.8,
4527
- "image_quality": 75.8,
4528
- "physical_plausibility": 79.2,
4529
- "prompt_faithfulness": 51.5,
4530
- "rubric_adaptive": 58.2,
4531
- "text_rendering": 78.9,
4532
- "visual_reference_evaluation": 56.1
4533
- },
4534
- "coverage": 1.0,
4535
- "display_name": "Qwen-Image-2",
4536
- "missing_policy": "zero_fill",
4537
- "model_id": "qwen2",
4538
- "n_included": 33,
4539
- "n_scored": 33,
4540
- "n_total": 33,
4541
- "overall_10": 63.9,
4542
- "overall_9": 65.6,
4543
- "type": "Commercial"
4544
- },
4545
  {
4546
  "component_counts": {
4547
  "ai_naturalness": 33,
@@ -4551,6 +4781,7 @@
4551
  "physical_plausibility": 24,
4552
  "prompt_faithfulness": 33,
4553
  "rubric_adaptive": 33,
 
4554
  "text_rendering": 15,
4555
  "visual_reference_evaluation": 26
4556
  },
@@ -4562,6 +4793,7 @@
4562
  "physical_plausibility": 75.0,
4563
  "prompt_faithfulness": 60.6,
4564
  "rubric_adaptive": 64.4,
 
4565
  "text_rendering": 60.0,
4566
  "visual_reference_evaluation": 56.4
4567
  },
@@ -4585,6 +4817,7 @@
4585
  "physical_plausibility": 23,
4586
  "prompt_faithfulness": 31,
4587
  "rubric_adaptive": 31,
 
4588
  "text_rendering": 18,
4589
  "visual_reference_evaluation": 28
4590
  },
@@ -4596,6 +4829,7 @@
4596
  "physical_plausibility": 64.5,
4597
  "prompt_faithfulness": 59.7,
4598
  "rubric_adaptive": 62.2,
 
4599
  "text_rendering": 75.9,
4600
  "visual_reference_evaluation": 60.7
4601
  },
@@ -4610,6 +4844,42 @@
4610
  "overall_9": 65.2,
4611
  "type": "Commercial"
4612
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4613
  {
4614
  "component_counts": {
4615
  "ai_naturalness": 33,
@@ -4619,6 +4889,7 @@
4619
  "physical_plausibility": 26,
4620
  "prompt_faithfulness": 33,
4621
  "rubric_adaptive": 33,
 
4622
  "text_rendering": 15,
4623
  "visual_reference_evaluation": 30
4624
  },
@@ -4630,6 +4901,7 @@
4630
  "physical_plausibility": 75.0,
4631
  "prompt_faithfulness": 51.5,
4632
  "rubric_adaptive": 55.8,
 
4633
  "text_rendering": 75.6,
4634
  "visual_reference_evaluation": 54.4
4635
  },
@@ -4653,6 +4925,7 @@
4653
  "physical_plausibility": 24,
4654
  "prompt_faithfulness": 33,
4655
  "rubric_adaptive": 33,
 
4656
  "text_rendering": 19,
4657
  "visual_reference_evaluation": 30
4658
  },
@@ -4664,6 +4937,7 @@
4664
  "physical_plausibility": 72.2,
4665
  "prompt_faithfulness": 52.5,
4666
  "rubric_adaptive": 58.6,
 
4667
  "text_rendering": 61.4,
4668
  "visual_reference_evaluation": 51.1
4669
  },
@@ -4687,6 +4961,7 @@
4687
  "physical_plausibility": 23,
4688
  "prompt_faithfulness": 33,
4689
  "rubric_adaptive": 33,
 
4690
  "text_rendering": 14,
4691
  "visual_reference_evaluation": 25
4692
  },
@@ -4698,6 +4973,7 @@
4698
  "physical_plausibility": 70.3,
4699
  "prompt_faithfulness": 43.4,
4700
  "rubric_adaptive": 49.2,
 
4701
  "text_rendering": 35.7,
4702
  "visual_reference_evaluation": 34.7
4703
  },
@@ -4721,6 +4997,7 @@
4721
  "physical_plausibility": 31,
4722
  "prompt_faithfulness": 33,
4723
  "rubric_adaptive": 33,
 
4724
  "text_rendering": 13,
4725
  "visual_reference_evaluation": 25
4726
  },
@@ -4732,6 +5009,7 @@
4732
  "physical_plausibility": 55.9,
4733
  "prompt_faithfulness": 22.0,
4734
  "rubric_adaptive": 29.3,
 
4735
  "text_rendering": 3.8,
4736
  "visual_reference_evaluation": 28.7
4737
  },
@@ -4755,6 +5033,7 @@
4755
  "physical_plausibility": 24,
4756
  "prompt_faithfulness": 33,
4757
  "rubric_adaptive": 33,
 
4758
  "text_rendering": 16,
4759
  "visual_reference_evaluation": 26
4760
  },
@@ -4766,6 +5045,7 @@
4766
  "physical_plausibility": 61.8,
4767
  "prompt_faithfulness": 20.7,
4768
  "rubric_adaptive": 29.2,
 
4769
  "text_rendering": 4.2,
4770
  "visual_reference_evaluation": 22.4
4771
  },
@@ -4789,6 +5069,7 @@
4789
  "physical_plausibility": 23,
4790
  "prompt_faithfulness": 33,
4791
  "rubric_adaptive": 33,
 
4792
  "text_rendering": 16,
4793
  "visual_reference_evaluation": 25
4794
  },
@@ -4800,6 +5081,7 @@
4800
  "physical_plausibility": 58.7,
4801
  "prompt_faithfulness": 13.1,
4802
  "rubric_adaptive": 23.1,
 
4803
  "text_rendering": 2.1,
4804
  "visual_reference_evaluation": 13.3
4805
  },
@@ -4823,6 +5105,7 @@
4823
  "physical_plausibility": 30,
4824
  "prompt_faithfulness": 33,
4825
  "rubric_adaptive": 33,
 
4826
  "text_rendering": 13,
4827
  "visual_reference_evaluation": 25
4828
  },
@@ -4834,6 +5117,7 @@
4834
  "physical_plausibility": 43.9,
4835
  "prompt_faithfulness": 17.7,
4836
  "rubric_adaptive": 22.6,
 
4837
  "text_rendering": 1.3,
4838
  "visual_reference_evaluation": 18.0
4839
  },
@@ -4857,6 +5141,7 @@
4857
  "physical_plausibility": 28,
4858
  "prompt_faithfulness": 33,
4859
  "rubric_adaptive": 33,
 
4860
  "text_rendering": 15,
4861
  "visual_reference_evaluation": 26
4862
  },
@@ -4868,6 +5153,7 @@
4868
  "physical_plausibility": 51.2,
4869
  "prompt_faithfulness": 14.6,
4870
  "rubric_adaptive": 21.6,
 
4871
  "text_rendering": 3.3,
4872
  "visual_reference_evaluation": 15.4
4873
  },
@@ -4893,6 +5179,7 @@
4893
  "physical_plausibility": 117,
4894
  "prompt_faithfulness": 185,
4895
  "rubric_adaptive": 185,
 
4896
  "text_rendering": 164,
4897
  "visual_reference_evaluation": 150
4898
  },
@@ -4904,6 +5191,7 @@
4904
  "physical_plausibility": 86.8,
4905
  "prompt_faithfulness": 76.1,
4906
  "rubric_adaptive": 75.5,
 
4907
  "text_rendering": 79.8,
4908
  "visual_reference_evaluation": 74.4
4909
  },
@@ -4927,6 +5215,7 @@
4927
  "physical_plausibility": 142,
4928
  "prompt_faithfulness": 185,
4929
  "rubric_adaptive": 185,
 
4930
  "text_rendering": 158,
4931
  "visual_reference_evaluation": 150
4932
  },
@@ -4938,6 +5227,7 @@
4938
  "physical_plausibility": 86.9,
4939
  "prompt_faithfulness": 66.1,
4940
  "rubric_adaptive": 67.7,
 
4941
  "text_rendering": 70.6,
4942
  "visual_reference_evaluation": 65.6
4943
  },
@@ -4961,6 +5251,7 @@
4961
  "physical_plausibility": 123,
4962
  "prompt_faithfulness": 180,
4963
  "rubric_adaptive": 180,
 
4964
  "text_rendering": 157,
4965
  "visual_reference_evaluation": 151
4966
  },
@@ -4972,6 +5263,7 @@
4972
  "physical_plausibility": 80.2,
4973
  "prompt_faithfulness": 63.4,
4974
  "rubric_adaptive": 64.8,
 
4975
  "text_rendering": 64.2,
4976
  "visual_reference_evaluation": 61.9
4977
  },
@@ -4995,6 +5287,7 @@
4995
  "physical_plausibility": 119,
4996
  "prompt_faithfulness": 183,
4997
  "rubric_adaptive": 183,
 
4998
  "text_rendering": 148,
4999
  "visual_reference_evaluation": 154
5000
  },
@@ -5006,6 +5299,7 @@
5006
  "physical_plausibility": 76.8,
5007
  "prompt_faithfulness": 51.4,
5008
  "rubric_adaptive": 54.2,
 
5009
  "text_rendering": 58.6,
5010
  "visual_reference_evaluation": 47.3
5011
  },
@@ -5029,6 +5323,7 @@
5029
  "physical_plausibility": 119,
5030
  "prompt_faithfulness": 185,
5031
  "rubric_adaptive": 185,
 
5032
  "text_rendering": 148,
5033
  "visual_reference_evaluation": 156
5034
  },
@@ -5040,6 +5335,7 @@
5040
  "physical_plausibility": 73.7,
5041
  "prompt_faithfulness": 49.0,
5042
  "rubric_adaptive": 52.4,
 
5043
  "text_rendering": 54.8,
5044
  "visual_reference_evaluation": 44.4
5045
  },
@@ -5063,6 +5359,7 @@
5063
  "physical_plausibility": 134,
5064
  "prompt_faithfulness": 185,
5065
  "rubric_adaptive": 185,
 
5066
  "text_rendering": 154,
5067
  "visual_reference_evaluation": 156
5068
  },
@@ -5074,6 +5371,7 @@
5074
  "physical_plausibility": 68.7,
5075
  "prompt_faithfulness": 45.5,
5076
  "rubric_adaptive": 49.4,
 
5077
  "text_rendering": 51.9,
5078
  "visual_reference_evaluation": 41.6
5079
  },
@@ -5097,6 +5395,7 @@
5097
  "physical_plausibility": 136,
5098
  "prompt_faithfulness": 185,
5099
  "rubric_adaptive": 185,
 
5100
  "text_rendering": 148,
5101
  "visual_reference_evaluation": 150
5102
  },
@@ -5108,6 +5407,7 @@
5108
  "physical_plausibility": 67.2,
5109
  "prompt_faithfulness": 37.8,
5110
  "rubric_adaptive": 43.8,
 
5111
  "text_rendering": 37.3,
5112
  "visual_reference_evaluation": 38.8
5113
  },
@@ -5131,6 +5431,7 @@
5131
  "physical_plausibility": 129,
5132
  "prompt_faithfulness": 185,
5133
  "rubric_adaptive": 185,
 
5134
  "text_rendering": 153,
5135
  "visual_reference_evaluation": 150
5136
  },
@@ -5142,6 +5443,7 @@
5142
  "physical_plausibility": 74.2,
5143
  "prompt_faithfulness": 36.8,
5144
  "rubric_adaptive": 41.1,
 
5145
  "text_rendering": 26.6,
5146
  "visual_reference_evaluation": 37.7
5147
  },
@@ -5165,6 +5467,7 @@
5165
  "physical_plausibility": 156,
5166
  "prompt_faithfulness": 185,
5167
  "rubric_adaptive": 185,
 
5168
  "text_rendering": 153,
5169
  "visual_reference_evaluation": 150
5170
  },
@@ -5176,6 +5479,7 @@
5176
  "physical_plausibility": 47.1,
5177
  "prompt_faithfulness": 18.9,
5178
  "rubric_adaptive": 24.3,
 
5179
  "text_rendering": 10.7,
5180
  "visual_reference_evaluation": 20.4
5181
  },
@@ -5199,6 +5503,7 @@
5199
  "physical_plausibility": 134,
5200
  "prompt_faithfulness": 185,
5201
  "rubric_adaptive": 185,
 
5202
  "text_rendering": 157,
5203
  "visual_reference_evaluation": 150
5204
  },
@@ -5210,6 +5515,7 @@
5210
  "physical_plausibility": 50.1,
5211
  "prompt_faithfulness": 17.2,
5212
  "rubric_adaptive": 22.6,
 
5213
  "text_rendering": 9.1,
5214
  "visual_reference_evaluation": 20.2
5215
  },
@@ -5233,6 +5539,7 @@
5233
  "physical_plausibility": 131,
5234
  "prompt_faithfulness": 184,
5235
  "rubric_adaptive": 185,
 
5236
  "text_rendering": 148,
5237
  "visual_reference_evaluation": 149
5238
  },
@@ -5244,6 +5551,7 @@
5244
  "physical_plausibility": 50.0,
5245
  "prompt_faithfulness": 12.1,
5246
  "rubric_adaptive": 18.1,
 
5247
  "text_rendering": 3.7,
5248
  "visual_reference_evaluation": 15.7
5249
  },
@@ -5267,6 +5575,7 @@
5267
  "physical_plausibility": 148,
5268
  "prompt_faithfulness": 185,
5269
  "rubric_adaptive": 185,
 
5270
  "text_rendering": 149,
5271
  "visual_reference_evaluation": 150
5272
  },
@@ -5278,6 +5587,7 @@
5278
  "physical_plausibility": 35.8,
5279
  "prompt_faithfulness": 10.7,
5280
  "rubric_adaptive": 14.6,
 
5281
  "text_rendering": 1.7,
5282
  "visual_reference_evaluation": 12.8
5283
  },
@@ -5301,6 +5611,7 @@
5301
  "physical_plausibility": 151,
5302
  "prompt_faithfulness": 185,
5303
  "rubric_adaptive": 185,
 
5304
  "text_rendering": 159,
5305
  "visual_reference_evaluation": 169
5306
  },
@@ -5312,6 +5623,7 @@
5312
  "physical_plausibility": 22.0,
5313
  "prompt_faithfulness": 6.3,
5314
  "rubric_adaptive": 9.5,
 
5315
  "text_rendering": 1.2,
5316
  "visual_reference_evaluation": 6.3
5317
  },
 
9
  "physical_plausibility": 415,
10
  "prompt_faithfulness": 534,
11
  "rubric_adaptive": 534,
12
+ "text_reference_evaluation": 336,
13
  "text_rendering": 376,
14
  "visual_reference_evaluation": 439
15
  },
 
21
  "physical_plausibility": 73.8,
22
  "prompt_faithfulness": 68.5,
23
  "rubric_adaptive": 69.7,
24
+ "text_reference_evaluation": 55.3,
25
  "text_rendering": 73.2,
26
  "visual_reference_evaluation": 66.6
27
  },
 
45
  "physical_plausibility": 455,
46
  "prompt_faithfulness": 534,
47
  "rubric_adaptive": 534,
48
+ "text_reference_evaluation": 327,
49
  "text_rendering": 344,
50
  "visual_reference_evaluation": 437
51
  },
 
57
  "physical_plausibility": 76.2,
58
  "prompt_faithfulness": 62.2,
59
  "rubric_adaptive": 65.8,
60
+ "text_reference_evaluation": 49.5,
61
  "text_rendering": 66.4,
62
  "visual_reference_evaluation": 61.6
63
  },
 
81
  "physical_plausibility": 389,
82
  "prompt_faithfulness": 504,
83
  "rubric_adaptive": 504,
84
+ "text_reference_evaluation": 331,
85
  "text_rendering": 355,
86
  "visual_reference_evaluation": 417
87
  },
 
93
  "physical_plausibility": 69.9,
94
  "prompt_faithfulness": 61.3,
95
  "rubric_adaptive": 63.8,
96
+ "text_reference_evaluation": 46.6,
97
  "text_rendering": 61.7,
98
  "visual_reference_evaluation": 60.7
99
  },
 
117
  "physical_plausibility": 410,
118
  "prompt_faithfulness": 526,
119
  "rubric_adaptive": 526,
120
+ "text_reference_evaluation": 320,
121
  "text_rendering": 321,
122
  "visual_reference_evaluation": 439
123
  },
 
129
  "physical_plausibility": 70.2,
130
  "prompt_faithfulness": 50.8,
131
  "rubric_adaptive": 54.7,
132
+ "text_reference_evaluation": 37.6,
133
  "text_rendering": 56.9,
134
  "visual_reference_evaluation": 47.0
135
  },
 
153
  "physical_plausibility": 422,
154
  "prompt_faithfulness": 534,
155
  "rubric_adaptive": 534,
156
+ "text_reference_evaluation": 335,
157
  "text_rendering": 319,
158
  "visual_reference_evaluation": 448
159
  },
 
165
  "physical_plausibility": 65.3,
166
  "prompt_faithfulness": 47.5,
167
  "rubric_adaptive": 51.6,
168
+ "text_reference_evaluation": 33.8,
169
  "text_rendering": 52.0,
170
  "visual_reference_evaluation": 44.0
171
  },
 
189
  "physical_plausibility": 441,
190
  "prompt_faithfulness": 534,
191
  "rubric_adaptive": 534,
192
+ "text_reference_evaluation": 336,
193
  "text_rendering": 353,
194
  "visual_reference_evaluation": 446
195
  },
 
201
  "physical_plausibility": 62.1,
202
  "prompt_faithfulness": 46.1,
203
  "rubric_adaptive": 50.8,
204
+ "text_reference_evaluation": 29.1,
205
  "text_rendering": 48.6,
206
  "visual_reference_evaluation": 41.3
207
  },
 
225
  "physical_plausibility": 445,
226
  "prompt_faithfulness": 534,
227
  "rubric_adaptive": 534,
228
+ "text_reference_evaluation": 343,
229
  "text_rendering": 333,
230
  "visual_reference_evaluation": 436
231
  },
 
237
  "physical_plausibility": 64.5,
238
  "prompt_faithfulness": 41.4,
239
  "rubric_adaptive": 47.1,
240
+ "text_reference_evaluation": 23.7,
241
  "text_rendering": 37.8,
242
  "visual_reference_evaluation": 39.6
243
  },
 
261
  "physical_plausibility": 427,
262
  "prompt_faithfulness": 534,
263
  "rubric_adaptive": 534,
264
+ "text_reference_evaluation": 358,
265
  "text_rendering": 346,
266
  "visual_reference_evaluation": 437
267
  },
 
273
  "physical_plausibility": 63.3,
274
  "prompt_faithfulness": 39.6,
275
  "rubric_adaptive": 44.3,
276
+ "text_reference_evaluation": 18.3,
277
  "text_rendering": 29.3,
278
  "visual_reference_evaluation": 38.4
279
  },
 
297
  "physical_plausibility": 486,
298
  "prompt_faithfulness": 534,
299
  "rubric_adaptive": 534,
300
+ "text_reference_evaluation": 355,
301
  "text_rendering": 328,
302
  "visual_reference_evaluation": 435
303
  },
 
309
  "physical_plausibility": 48.5,
310
  "prompt_faithfulness": 25.9,
311
  "rubric_adaptive": 32.0,
312
+ "text_reference_evaluation": 7.9,
313
  "text_rendering": 11.4,
314
  "visual_reference_evaluation": 25.4
315
  },
 
333
  "physical_plausibility": 440,
334
  "prompt_faithfulness": 534,
335
  "rubric_adaptive": 534,
336
+ "text_reference_evaluation": 365,
337
  "text_rendering": 345,
338
  "visual_reference_evaluation": 436
339
  },
 
345
  "physical_plausibility": 51.2,
346
  "prompt_faithfulness": 23.0,
347
  "rubric_adaptive": 29.1,
348
+ "text_reference_evaluation": 6.6,
349
  "text_rendering": 8.7,
350
  "visual_reference_evaluation": 23.0
351
  },
 
369
  "physical_plausibility": 442,
370
  "prompt_faithfulness": 533,
371
  "rubric_adaptive": 534,
372
+ "text_reference_evaluation": 366,
373
  "text_rendering": 327,
374
  "visual_reference_evaluation": 434
375
  },
 
381
  "physical_plausibility": 48.1,
382
  "prompt_faithfulness": 17.0,
383
  "rubric_adaptive": 23.4,
384
+ "text_reference_evaluation": 3.4,
385
  "text_rendering": 4.5,
386
  "visual_reference_evaluation": 16.3
387
  },
 
405
  "physical_plausibility": 460,
406
  "prompt_faithfulness": 534,
407
  "rubric_adaptive": 534,
408
+ "text_reference_evaluation": 353,
409
  "text_rendering": 313,
410
  "visual_reference_evaluation": 435
411
  },
 
417
  "physical_plausibility": 41.4,
418
  "prompt_faithfulness": 18.4,
419
  "rubric_adaptive": 23.2,
420
+ "text_reference_evaluation": 3.4,
421
  "text_rendering": 4.1,
422
  "visual_reference_evaluation": 19.0
423
  },
 
441
  "physical_plausibility": 473,
442
  "prompt_faithfulness": 534,
443
  "rubric_adaptive": 534,
444
+ "text_reference_evaluation": 449,
445
  "text_rendering": 430,
446
  "visual_reference_evaluation": 506
447
  },
 
453
  "physical_plausibility": 17.3,
454
  "prompt_faithfulness": 6.0,
455
  "rubric_adaptive": 8.1,
456
+ "text_reference_evaluation": 0.9,
457
  "text_rendering": 0.9,
458
  "visual_reference_evaluation": 5.9
459
  },
 
479
  "physical_plausibility": 144,
480
  "prompt_faithfulness": 159,
481
  "rubric_adaptive": 159,
482
+ "text_reference_evaluation": 91,
483
  "text_rendering": 95,
484
  "visual_reference_evaluation": 121
485
  },
 
491
  "physical_plausibility": 75.3,
492
  "prompt_faithfulness": 68.3,
493
  "rubric_adaptive": 71.3,
494
+ "text_reference_evaluation": 50.4,
495
  "text_rendering": 70.9,
496
  "visual_reference_evaluation": 62.4
497
  },
 
515
  "physical_plausibility": 149,
516
  "prompt_faithfulness": 159,
517
  "rubric_adaptive": 159,
518
+ "text_reference_evaluation": 86,
519
  "text_rendering": 78,
520
  "visual_reference_evaluation": 121
521
  },
 
527
  "physical_plausibility": 77.9,
528
  "prompt_faithfulness": 63.1,
529
  "rubric_adaptive": 68.7,
530
+ "text_reference_evaluation": 47.1,
531
  "text_rendering": 61.3,
532
  "visual_reference_evaluation": 59.5
533
  },
 
551
  "physical_plausibility": 136,
552
  "prompt_faithfulness": 153,
553
  "rubric_adaptive": 153,
554
+ "text_reference_evaluation": 90,
555
  "text_rendering": 92,
556
  "visual_reference_evaluation": 121
557
  },
 
563
  "physical_plausibility": 71.3,
564
  "prompt_faithfulness": 63.8,
565
  "rubric_adaptive": 68.1,
566
+ "text_reference_evaluation": 48.0,
567
  "text_rendering": 64.7,
568
  "visual_reference_evaluation": 61.0
569
  },
 
587
  "physical_plausibility": 139,
588
  "prompt_faithfulness": 158,
589
  "rubric_adaptive": 158,
590
+ "text_reference_evaluation": 85,
591
  "text_rendering": 70,
592
  "visual_reference_evaluation": 124
593
  },
 
599
  "physical_plausibility": 71.0,
600
  "prompt_faithfulness": 54.7,
601
  "rubric_adaptive": 62.6,
602
+ "text_reference_evaluation": 45.7,
603
  "text_rendering": 65.5,
604
  "visual_reference_evaluation": 53.2
605
  },
 
623
  "physical_plausibility": 139,
624
  "prompt_faithfulness": 159,
625
  "rubric_adaptive": 159,
626
+ "text_reference_evaluation": 86,
627
  "text_rendering": 73,
628
  "visual_reference_evaluation": 126
629
  },
 
635
  "physical_plausibility": 69.3,
636
  "prompt_faithfulness": 54.8,
637
  "rubric_adaptive": 61.9,
638
+ "text_reference_evaluation": 41.3,
639
  "text_rendering": 60.7,
640
  "visual_reference_evaluation": 53.8
641
  },
 
659
  "physical_plausibility": 141,
660
  "prompt_faithfulness": 159,
661
  "rubric_adaptive": 159,
662
+ "text_reference_evaluation": 88,
663
  "text_rendering": 75,
664
  "visual_reference_evaluation": 121
665
  },
 
671
  "physical_plausibility": 70.7,
672
  "prompt_faithfulness": 51.2,
673
  "rubric_adaptive": 57.5,
674
+ "text_reference_evaluation": 32.0,
675
  "text_rendering": 49.6,
676
  "visual_reference_evaluation": 50.0
677
  },
 
695
  "physical_plausibility": 139,
696
  "prompt_faithfulness": 159,
697
  "rubric_adaptive": 159,
698
+ "text_reference_evaluation": 90,
699
  "text_rendering": 86,
700
  "visual_reference_evaluation": 126
701
  },
 
707
  "physical_plausibility": 70.0,
708
  "prompt_faithfulness": 53.6,
709
  "rubric_adaptive": 58.6,
710
+ "text_reference_evaluation": 35.4,
711
  "text_rendering": 54.5,
712
  "visual_reference_evaluation": 48.3
713
  },
 
731
  "physical_plausibility": 143,
732
  "prompt_faithfulness": 159,
733
  "rubric_adaptive": 159,
734
+ "text_reference_evaluation": 97,
735
  "text_rendering": 79,
736
  "visual_reference_evaluation": 121
737
  },
 
743
  "physical_plausibility": 68.1,
744
  "prompt_faithfulness": 44.5,
745
  "rubric_adaptive": 52.5,
746
+ "text_reference_evaluation": 16.2,
747
  "text_rendering": 20.8,
748
  "visual_reference_evaluation": 42.8
749
  },
 
767
  "physical_plausibility": 153,
768
  "prompt_faithfulness": 159,
769
  "rubric_adaptive": 159,
770
+ "text_reference_evaluation": 92,
771
  "text_rendering": 74,
772
  "visual_reference_evaluation": 121
773
  },
 
779
  "physical_plausibility": 60.1,
780
  "prompt_faithfulness": 38.4,
781
  "rubric_adaptive": 44.8,
782
+ "text_reference_evaluation": 16.1,
783
  "text_rendering": 21.2,
784
  "visual_reference_evaluation": 39.9
785
  },
 
803
  "physical_plausibility": 143,
804
  "prompt_faithfulness": 159,
805
  "rubric_adaptive": 159,
806
+ "text_reference_evaluation": 98,
807
  "text_rendering": 81,
808
  "visual_reference_evaluation": 121
809
  },
 
815
  "physical_plausibility": 60.5,
816
  "prompt_faithfulness": 32.0,
817
  "rubric_adaptive": 39.4,
818
+ "text_reference_evaluation": 9.2,
819
  "text_rendering": 6.8,
820
  "visual_reference_evaluation": 33.3
821
  },
 
839
  "physical_plausibility": 140,
840
  "prompt_faithfulness": 159,
841
  "rubric_adaptive": 159,
842
+ "text_reference_evaluation": 101,
843
  "text_rendering": 79,
844
  "visual_reference_evaluation": 121
845
  },
 
851
  "physical_plausibility": 58.2,
852
  "prompt_faithfulness": 23.3,
853
  "rubric_adaptive": 31.3,
854
+ "text_reference_evaluation": 6.8,
855
  "text_rendering": 4.2,
856
  "visual_reference_evaluation": 22.6
857
  },
 
875
  "physical_plausibility": 142,
876
  "prompt_faithfulness": 159,
877
  "rubric_adaptive": 159,
878
+ "text_reference_evaluation": 98,
879
  "text_rendering": 70,
880
  "visual_reference_evaluation": 121
881
  },
 
887
  "physical_plausibility": 49.4,
888
  "prompt_faithfulness": 24.3,
889
  "rubric_adaptive": 30.4,
890
+ "text_reference_evaluation": 7.3,
891
  "text_rendering": 2.6,
892
  "visual_reference_evaluation": 24.8
893
  },
 
911
  "physical_plausibility": 151,
912
  "prompt_faithfulness": 159,
913
  "rubric_adaptive": 159,
914
+ "text_reference_evaluation": 136,
915
  "text_rendering": 124,
916
  "visual_reference_evaluation": 147
917
  },
 
923
  "physical_plausibility": 19.6,
924
  "prompt_faithfulness": 6.1,
925
  "rubric_adaptive": 8.3,
926
+ "text_reference_evaluation": 0.7,
927
  "text_rendering": 0.7,
928
  "visual_reference_evaluation": 6.3
929
  },
 
949
  "physical_plausibility": 193,
950
  "prompt_faithfulness": 281,
951
  "rubric_adaptive": 281,
952
+ "text_reference_evaluation": 197,
953
  "text_rendering": 226,
954
  "visual_reference_evaluation": 224
955
  },
 
961
  "physical_plausibility": 81.0,
962
  "prompt_faithfulness": 71.9,
963
  "rubric_adaptive": 72.6,
964
+ "text_reference_evaluation": 62.1,
965
  "text_rendering": 78.8,
966
  "visual_reference_evaluation": 67.3
967
  },
 
985
  "physical_plausibility": 221,
986
  "prompt_faithfulness": 281,
987
  "rubric_adaptive": 281,
988
+ "text_reference_evaluation": 202,
989
  "text_rendering": 210,
990
  "visual_reference_evaluation": 223
991
  },
 
997
  "physical_plausibility": 80.9,
998
  "prompt_faithfulness": 62.9,
999
  "rubric_adaptive": 64.5,
1000
+ "text_reference_evaluation": 51.7,
1001
  "text_rendering": 67.1,
1002
  "visual_reference_evaluation": 59.2
1003
  },
 
1021
  "physical_plausibility": 181,
1022
  "prompt_faithfulness": 269,
1023
  "rubric_adaptive": 269,
1024
+ "text_reference_evaluation": 202,
1025
  "text_rendering": 218,
1026
  "visual_reference_evaluation": 221
1027
  },
 
1033
  "physical_plausibility": 76.4,
1034
  "prompt_faithfulness": 63.5,
1035
  "rubric_adaptive": 63.6,
1036
+ "text_reference_evaluation": 47.4,
1037
  "text_rendering": 62.9,
1038
  "visual_reference_evaluation": 57.5
1039
  },
 
1057
  "physical_plausibility": 190,
1058
  "prompt_faithfulness": 277,
1059
  "rubric_adaptive": 277,
1060
+ "text_reference_evaluation": 196,
1061
  "text_rendering": 208,
1062
  "visual_reference_evaluation": 229
1063
  },
 
1069
  "physical_plausibility": 72.5,
1070
  "prompt_faithfulness": 52.2,
1071
  "rubric_adaptive": 53.8,
1072
+ "text_reference_evaluation": 38.4,
1073
  "text_rendering": 58.7,
1074
  "visual_reference_evaluation": 44.8
1075
  },
 
1093
  "physical_plausibility": 199,
1094
  "prompt_faithfulness": 281,
1095
  "rubric_adaptive": 281,
1096
+ "text_reference_evaluation": 203,
1097
  "text_rendering": 203,
1098
  "visual_reference_evaluation": 234
1099
  },
 
1105
  "physical_plausibility": 66.3,
1106
  "prompt_faithfulness": 49.7,
1107
  "rubric_adaptive": 51.8,
1108
+ "text_reference_evaluation": 35.5,
1109
  "text_rendering": 56.2,
1110
  "visual_reference_evaluation": 41.3
1111
  },
 
1129
  "physical_plausibility": 212,
1130
  "prompt_faithfulness": 281,
1131
  "rubric_adaptive": 281,
1132
+ "text_reference_evaluation": 204,
1133
  "text_rendering": 220,
1134
  "visual_reference_evaluation": 233
1135
  },
 
1141
  "physical_plausibility": 62.6,
1142
  "prompt_faithfulness": 42.3,
1143
  "rubric_adaptive": 47.0,
1144
+ "text_reference_evaluation": 27.7,
1145
  "text_rendering": 47.3,
1146
  "visual_reference_evaluation": 35.6
1147
  },
 
1165
  "physical_plausibility": 217,
1166
  "prompt_faithfulness": 280,
1167
  "rubric_adaptive": 281,
1168
+ "text_reference_evaluation": 215,
1169
  "text_rendering": 208,
1170
  "visual_reference_evaluation": 223
1171
  },
 
1177
  "physical_plausibility": 61.5,
1178
  "prompt_faithfulness": 37.7,
1179
  "rubric_adaptive": 42.8,
1180
+ "text_reference_evaluation": 24.1,
1181
  "text_rendering": 35.8,
1182
  "visual_reference_evaluation": 33.5
1183
  },
 
1201
  "physical_plausibility": 205,
1202
  "prompt_faithfulness": 281,
1203
  "rubric_adaptive": 281,
1204
+ "text_reference_evaluation": 220,
1205
  "text_rendering": 216,
1206
  "visual_reference_evaluation": 223
1207
  },
 
1213
  "physical_plausibility": 66.7,
1214
  "prompt_faithfulness": 36.6,
1215
  "rubric_adaptive": 40.3,
1216
+ "text_reference_evaluation": 17.6,
1217
  "text_rendering": 26.9,
1218
  "visual_reference_evaluation": 32.2
1219
  },
 
1237
  "physical_plausibility": 250,
1238
  "prompt_faithfulness": 281,
1239
  "rubric_adaptive": 281,
1240
+ "text_reference_evaluation": 217,
1241
  "text_rendering": 206,
1242
  "visual_reference_evaluation": 223
1243
  },
 
1249
  "physical_plausibility": 44.9,
1250
  "prompt_faithfulness": 20.8,
1251
  "rubric_adaptive": 25.9,
1252
+ "text_reference_evaluation": 8.0,
1253
  "text_rendering": 11.2,
1254
  "visual_reference_evaluation": 18.4
1255
  },
 
1273
  "physical_plausibility": 211,
1274
  "prompt_faithfulness": 281,
1275
  "rubric_adaptive": 281,
1276
+ "text_reference_evaluation": 230,
1277
  "text_rendering": 219,
1278
  "visual_reference_evaluation": 223
1279
  },
 
1285
  "physical_plausibility": 48.6,
1286
  "prompt_faithfulness": 18.1,
1287
  "rubric_adaptive": 23.8,
1288
+ "text_reference_evaluation": 6.9,
1289
  "text_rendering": 7.4,
1290
  "visual_reference_evaluation": 15.7
1291
  },
 
1309
  "physical_plausibility": 211,
1310
  "prompt_faithfulness": 280,
1311
  "rubric_adaptive": 281,
1312
+ "text_reference_evaluation": 230,
1313
  "text_rendering": 203,
1314
  "visual_reference_evaluation": 222
1315
  },
 
1321
  "physical_plausibility": 44.9,
1322
  "prompt_faithfulness": 12.7,
1323
  "rubric_adaptive": 19.3,
1324
+ "text_reference_evaluation": 4.4,
1325
  "text_rendering": 4.1,
1326
  "visual_reference_evaluation": 12.1
1327
  },
 
1345
  "physical_plausibility": 226,
1346
  "prompt_faithfulness": 281,
1347
  "rubric_adaptive": 281,
1348
+ "text_reference_evaluation": 223,
1349
  "text_rendering": 204,
1350
  "visual_reference_evaluation": 223
1351
  },
 
1357
  "physical_plausibility": 34.5,
1358
  "prompt_faithfulness": 11.9,
1359
  "rubric_adaptive": 16.8,
1360
+ "text_reference_evaluation": 3.4,
1361
  "text_rendering": 3.6,
1362
  "visual_reference_evaluation": 11.4
1363
  },
 
1381
  "physical_plausibility": 234,
1382
  "prompt_faithfulness": 281,
1383
  "rubric_adaptive": 281,
1384
+ "text_reference_evaluation": 244,
1385
  "text_rendering": 229,
1386
  "visual_reference_evaluation": 256
1387
  },
 
1393
  "physical_plausibility": 21.2,
1394
  "prompt_faithfulness": 4.2,
1395
  "rubric_adaptive": 6.8,
1396
+ "text_reference_evaluation": 0.5,
1397
  "text_rendering": 0.6,
1398
  "visual_reference_evaluation": 4.8
1399
  },
 
1419
  "physical_plausibility": 23,
1420
  "prompt_faithfulness": 118,
1421
  "rubric_adaptive": 118,
1422
+ "text_reference_evaluation": 114,
1423
  "text_rendering": 110,
1424
  "visual_reference_evaluation": 95
1425
  },
 
1431
  "physical_plausibility": 91.3,
1432
  "prompt_faithfulness": 68.2,
1433
  "rubric_adaptive": 63.6,
1434
+ "text_reference_evaluation": 38.9,
1435
  "text_rendering": 74.1,
1436
  "visual_reference_evaluation": 66.1
1437
  },
 
1455
  "physical_plausibility": 72,
1456
  "prompt_faithfulness": 118,
1457
  "rubric_adaptive": 118,
1458
+ "text_reference_evaluation": 115,
1459
  "text_rendering": 110,
1460
  "visual_reference_evaluation": 95
1461
  },
 
1467
  "physical_plausibility": 85.6,
1468
  "prompt_faithfulness": 58.4,
1469
  "rubric_adaptive": 53.3,
1470
+ "text_reference_evaluation": 30.1,
1471
  "text_rendering": 63.5,
1472
  "visual_reference_evaluation": 53.6
1473
  },
 
1491
  "physical_plausibility": 39,
1492
  "prompt_faithfulness": 118,
1493
  "rubric_adaptive": 118,
1494
+ "text_reference_evaluation": 116,
1495
  "text_rendering": 113,
1496
  "visual_reference_evaluation": 96
1497
  },
 
1503
  "physical_plausibility": 90.2,
1504
  "prompt_faithfulness": 57.5,
1505
  "rubric_adaptive": 53.1,
1506
+ "text_reference_evaluation": 30.3,
1507
  "text_rendering": 55.6,
1508
  "visual_reference_evaluation": 53.3
1509
  },
 
1527
  "physical_plausibility": 20,
1528
  "prompt_faithfulness": 118,
1529
  "rubric_adaptive": 118,
1530
+ "text_reference_evaluation": 116,
1531
  "text_rendering": 115,
1532
  "visual_reference_evaluation": 96
1533
  },
 
1539
  "physical_plausibility": 69.2,
1540
  "prompt_faithfulness": 37.6,
1541
  "rubric_adaptive": 36.8,
1542
+ "text_reference_evaluation": 18.7,
1543
  "text_rendering": 41.3,
1544
  "visual_reference_evaluation": 28.3
1545
  },
 
1563
  "physical_plausibility": 23,
1564
  "prompt_faithfulness": 118,
1565
  "rubric_adaptive": 118,
1566
+ "text_reference_evaluation": 117,
1567
  "text_rendering": 113,
1568
  "visual_reference_evaluation": 96
1569
  },
 
1575
  "physical_plausibility": 74.6,
1576
  "prompt_faithfulness": 36.6,
1577
  "rubric_adaptive": 34.8,
1578
+ "text_reference_evaluation": 18.4,
1579
  "text_rendering": 41.6,
1580
  "visual_reference_evaluation": 28.6
1581
  },
 
1599
  "physical_plausibility": 45,
1600
  "prompt_faithfulness": 118,
1601
  "rubric_adaptive": 118,
1602
+ "text_reference_evaluation": 115,
1603
  "text_rendering": 113,
1604
  "visual_reference_evaluation": 96
1605
  },
 
1611
  "physical_plausibility": 65.2,
1612
  "prompt_faithfulness": 32.9,
1613
  "rubric_adaptive": 31.1,
1614
+ "text_reference_evaluation": 14.1,
1615
  "text_rendering": 37.2,
1616
  "visual_reference_evaluation": 20.1
1617
  },
 
1635
  "physical_plausibility": 55,
1636
  "prompt_faithfulness": 118,
1637
  "rubric_adaptive": 118,
1638
+ "text_reference_evaluation": 116,
1639
  "text_rendering": 112,
1640
  "visual_reference_evaluation": 95
1641
  },
 
1647
  "physical_plausibility": 65.8,
1648
  "prompt_faithfulness": 25.2,
1649
  "rubric_adaptive": 25.2,
1650
+ "text_reference_evaluation": 7.2,
1651
  "text_rendering": 20.2,
1652
  "visual_reference_evaluation": 17.7
1653
  },
 
1671
  "physical_plausibility": 55,
1672
  "prompt_faithfulness": 118,
1673
  "rubric_adaptive": 118,
1674
+ "text_reference_evaluation": 115,
1675
  "text_rendering": 114,
1676
  "visual_reference_evaluation": 95
1677
  },
 
1683
  "physical_plausibility": 59.7,
1684
  "prompt_faithfulness": 21.6,
1685
  "rubric_adaptive": 24.2,
1686
+ "text_reference_evaluation": 8.6,
1687
  "text_rendering": 22.1,
1688
  "visual_reference_evaluation": 17.4
1689
  },
 
1707
  "physical_plausibility": 83,
1708
  "prompt_faithfulness": 118,
1709
  "rubric_adaptive": 118,
1710
+ "text_reference_evaluation": 118,
1711
  "text_rendering": 114,
1712
  "visual_reference_evaluation": 95
1713
  },
 
1719
  "physical_plausibility": 16.1,
1720
  "prompt_faithfulness": 1.3,
1721
  "rubric_adaptive": 4.1,
1722
+ "text_reference_evaluation": 0.3,
1723
  "text_rendering": 0.3,
1724
  "visual_reference_evaluation": 2.3
1725
  },
 
1743
  "physical_plausibility": 59,
1744
  "prompt_faithfulness": 118,
1745
  "rubric_adaptive": 118,
1746
+ "text_reference_evaluation": 118,
1747
  "text_rendering": 117,
1748
  "visual_reference_evaluation": 95
1749
  },
 
1755
  "physical_plausibility": 12.1,
1756
  "prompt_faithfulness": 2.0,
1757
  "rubric_adaptive": 3.3,
1758
+ "text_reference_evaluation": 0.7,
1759
  "text_rendering": 1.1,
1760
  "visual_reference_evaluation": 1.8
1761
  },
 
1779
  "physical_plausibility": 80,
1780
  "prompt_faithfulness": 118,
1781
  "rubric_adaptive": 118,
1782
+ "text_reference_evaluation": 118,
1783
  "text_rendering": 112,
1784
  "visual_reference_evaluation": 96
1785
  },
 
1791
  "physical_plausibility": 11.2,
1792
  "prompt_faithfulness": 1.1,
1793
  "rubric_adaptive": 2.6,
1794
+ "text_reference_evaluation": 0.3,
1795
  "text_rendering": 0.3,
1796
  "visual_reference_evaluation": 1.4
1797
  },
 
1815
  "physical_plausibility": 64,
1816
  "prompt_faithfulness": 117,
1817
  "rubric_adaptive": 118,
1818
+ "text_reference_evaluation": 117,
1819
  "text_rendering": 115,
1820
  "visual_reference_evaluation": 94
1821
  },
 
1827
  "physical_plausibility": 9.4,
1828
  "prompt_faithfulness": 0.4,
1829
  "rubric_adaptive": 2.0,
1830
+ "text_reference_evaluation": 0.0,
1831
  "text_rendering": 0.1,
1832
  "visual_reference_evaluation": 0.9
1833
  },
 
1851
  "physical_plausibility": 69,
1852
  "prompt_faithfulness": 118,
1853
  "rubric_adaptive": 118,
1854
+ "text_reference_evaluation": 117,
1855
  "text_rendering": 112,
1856
  "visual_reference_evaluation": 95
1857
  },
 
1863
  "physical_plausibility": 5.1,
1864
  "prompt_faithfulness": 1.0,
1865
  "rubric_adaptive": 1.8,
1866
+ "text_reference_evaluation": 0.0,
1867
  "text_rendering": 0.0,
1868
  "visual_reference_evaluation": 1.2
1869
  },
 
1889
  "physical_plausibility": 352,
1890
  "prompt_faithfulness": 419,
1891
  "rubric_adaptive": 419,
1892
+ "text_reference_evaluation": 235,
1893
  "text_rendering": 264,
1894
  "visual_reference_evaluation": 352
1895
  },
 
1901
  "physical_plausibility": 70.5,
1902
  "prompt_faithfulness": 63.5,
1903
  "rubric_adaptive": 66.5,
1904
+ "text_reference_evaluation": 47.5,
1905
  "text_rendering": 69.8,
1906
  "visual_reference_evaluation": 60.4
1907
  },
 
1925
  "physical_plausibility": 371,
1926
  "prompt_faithfulness": 419,
1927
  "rubric_adaptive": 419,
1928
+ "text_reference_evaluation": 227,
1929
  "text_rendering": 237,
1930
  "visual_reference_evaluation": 351
1931
  },
 
1937
  "physical_plausibility": 73.2,
1938
  "prompt_faithfulness": 58.9,
1939
  "rubric_adaptive": 64.0,
1940
+ "text_reference_evaluation": 43.5,
1941
  "text_rendering": 62.0,
1942
  "visual_reference_evaluation": 57.1
1943
  },
 
1961
  "physical_plausibility": 323,
1962
  "prompt_faithfulness": 388,
1963
  "rubric_adaptive": 388,
1964
+ "text_reference_evaluation": 224,
1965
  "text_rendering": 237,
1966
  "visual_reference_evaluation": 326
1967
  },
 
1973
  "physical_plausibility": 68.2,
1974
  "prompt_faithfulness": 58.8,
1975
  "rubric_adaptive": 63.1,
1976
+ "text_reference_evaluation": 42.8,
1977
  "text_rendering": 62.1,
1978
  "visual_reference_evaluation": 55.9
1979
  },
 
1997
  "physical_plausibility": 344,
1998
  "prompt_faithfulness": 410,
1999
  "rubric_adaptive": 410,
2000
+ "text_reference_evaluation": 216,
2001
  "text_rendering": 203,
2002
  "visual_reference_evaluation": 347
2003
  },
 
2009
  "physical_plausibility": 65.9,
2010
  "prompt_faithfulness": 44.4,
2011
  "rubric_adaptive": 51.0,
2012
+ "text_reference_evaluation": 30.9,
2013
  "text_rendering": 52.5,
2014
  "visual_reference_evaluation": 40.5
2015
  },
 
2033
  "physical_plausibility": 354,
2034
  "prompt_faithfulness": 419,
2035
  "rubric_adaptive": 419,
2036
+ "text_reference_evaluation": 230,
2037
  "text_rendering": 205,
2038
  "visual_reference_evaluation": 358
2039
  },
 
2045
  "physical_plausibility": 62.5,
2046
  "prompt_faithfulness": 41.9,
2047
  "rubric_adaptive": 48.4,
2048
+ "text_reference_evaluation": 28.1,
2049
  "text_rendering": 48.1,
2050
  "visual_reference_evaluation": 37.3
2051
  },
 
2069
  "physical_plausibility": 366,
2070
  "prompt_faithfulness": 419,
2071
  "rubric_adaptive": 419,
2072
+ "text_reference_evaluation": 224,
2073
  "text_rendering": 241,
2074
  "visual_reference_evaluation": 356
2075
  },
 
2081
  "physical_plausibility": 59.9,
2082
  "prompt_faithfulness": 43.5,
2083
  "rubric_adaptive": 49.4,
2084
+ "text_reference_evaluation": 24.9,
2085
  "text_rendering": 45.3,
2086
  "visual_reference_evaluation": 37.2
2087
  },
 
2105
  "physical_plausibility": 369,
2106
  "prompt_faithfulness": 418,
2107
  "rubric_adaptive": 419,
2108
+ "text_reference_evaluation": 237,
2109
  "text_rendering": 219,
2110
  "visual_reference_evaluation": 348
2111
  },
 
2117
  "physical_plausibility": 63.0,
2118
  "prompt_faithfulness": 40.4,
2119
  "rubric_adaptive": 47.6,
2120
+ "text_reference_evaluation": 21.0,
2121
  "text_rendering": 35.8,
2122
  "visual_reference_evaluation": 36.3
2123
  },
 
2141
  "physical_plausibility": 367,
2142
  "prompt_faithfulness": 419,
2143
  "rubric_adaptive": 419,
2144
+ "text_reference_evaluation": 245,
2145
  "text_rendering": 236,
2146
  "visual_reference_evaluation": 349
2147
  },
 
2153
  "physical_plausibility": 62.0,
2154
  "prompt_faithfulness": 40.2,
2155
  "rubric_adaptive": 46.2,
2156
+ "text_reference_evaluation": 18.5,
2157
  "text_rendering": 29.8,
2158
  "visual_reference_evaluation": 36.4
2159
  },
 
2177
  "physical_plausibility": 388,
2178
  "prompt_faithfulness": 419,
2179
  "rubric_adaptive": 419,
2180
+ "text_reference_evaluation": 244,
2181
  "text_rendering": 212,
2182
  "visual_reference_evaluation": 348
2183
  },
 
2189
  "physical_plausibility": 52.0,
2190
  "prompt_faithfulness": 28.4,
2191
  "rubric_adaptive": 35.2,
2192
+ "text_reference_evaluation": 9.4,
2193
  "text_rendering": 14.9,
2194
  "visual_reference_evaluation": 25.9
2195
  },
 
2213
  "physical_plausibility": 365,
2214
  "prompt_faithfulness": 419,
2215
  "rubric_adaptive": 419,
2216
+ "text_reference_evaluation": 254,
2217
  "text_rendering": 230,
2218
  "visual_reference_evaluation": 348
2219
  },
 
2225
  "physical_plausibility": 53.1,
2226
  "prompt_faithfulness": 23.9,
2227
  "rubric_adaptive": 31.2,
2228
+ "text_reference_evaluation": 6.4,
2229
  "text_rendering": 9.9,
2230
  "visual_reference_evaluation": 21.3
2231
  },
 
2249
  "physical_plausibility": 355,
2250
  "prompt_faithfulness": 418,
2251
  "rubric_adaptive": 419,
2252
+ "text_reference_evaluation": 255,
2253
  "text_rendering": 223,
2254
  "visual_reference_evaluation": 347
2255
  },
 
2261
  "physical_plausibility": 49.9,
2262
  "prompt_faithfulness": 17.6,
2263
  "rubric_adaptive": 25.6,
2264
+ "text_reference_evaluation": 3.8,
2265
  "text_rendering": 5.0,
2266
  "visual_reference_evaluation": 14.6
2267
  },
 
2285
  "physical_plausibility": 373,
2286
  "prompt_faithfulness": 419,
2287
  "rubric_adaptive": 419,
2288
+ "text_reference_evaluation": 245,
2289
  "text_rendering": 213,
2290
  "visual_reference_evaluation": 348
2291
  },
 
2297
  "physical_plausibility": 41.1,
2298
  "prompt_faithfulness": 18.9,
2299
  "rubric_adaptive": 25.4,
2300
+ "text_reference_evaluation": 4.6,
2301
  "text_rendering": 4.5,
2302
  "visual_reference_evaluation": 18.8
2303
  },
 
2321
  "physical_plausibility": 388,
2322
  "prompt_faithfulness": 419,
2323
  "rubric_adaptive": 419,
2324
+ "text_reference_evaluation": 328,
2325
  "text_rendering": 305,
2326
  "visual_reference_evaluation": 402
2327
  },
 
2333
  "physical_plausibility": 21.5,
2334
  "prompt_faithfulness": 6.7,
2335
  "rubric_adaptive": 9.6,
2336
+ "text_reference_evaluation": 0.6,
2337
  "text_rendering": 0.2,
2338
  "visual_reference_evaluation": 6.1
2339
  },
 
2359
  "physical_plausibility": 176,
2360
  "prompt_faithfulness": 273,
2361
  "rubric_adaptive": 273,
2362
+ "text_reference_evaluation": 209,
2363
  "text_rendering": 217,
2364
  "visual_reference_evaluation": 222
2365
  },
 
2371
  "physical_plausibility": 80.2,
2372
  "prompt_faithfulness": 68.9,
2373
  "rubric_adaptive": 69.1,
2374
+ "text_reference_evaluation": 53.5,
2375
  "text_rendering": 73.8,
2376
  "visual_reference_evaluation": 67.1
2377
  },
 
2395
  "physical_plausibility": 215,
2396
  "prompt_faithfulness": 273,
2397
  "rubric_adaptive": 273,
2398
+ "text_reference_evaluation": 207,
2399
  "text_rendering": 208,
2400
  "visual_reference_evaluation": 223
2401
  },
 
2407
  "physical_plausibility": 80.2,
2408
  "prompt_faithfulness": 59.3,
2409
  "rubric_adaptive": 60.3,
2410
+ "text_reference_evaluation": 41.7,
2411
  "text_rendering": 62.4,
2412
  "visual_reference_evaluation": 56.9
2413
  },
 
2431
  "physical_plausibility": 184,
2432
  "prompt_faithfulness": 272,
2433
  "rubric_adaptive": 272,
2434
+ "text_reference_evaluation": 212,
2435
  "text_rendering": 213,
2436
  "visual_reference_evaluation": 226
2437
  },
 
2443
  "physical_plausibility": 74.8,
2444
  "prompt_faithfulness": 58.5,
2445
  "rubric_adaptive": 58.2,
2446
+ "text_reference_evaluation": 39.8,
2447
  "text_rendering": 56.3,
2448
  "visual_reference_evaluation": 56.2
2449
  },
 
2467
  "physical_plausibility": 173,
2468
  "prompt_faithfulness": 271,
2469
  "rubric_adaptive": 271,
2470
+ "text_reference_evaluation": 203,
2471
  "text_rendering": 197,
2472
  "visual_reference_evaluation": 224
2473
  },
 
2479
  "physical_plausibility": 73.4,
2480
  "prompt_faithfulness": 46.1,
2481
  "rubric_adaptive": 48.4,
2482
+ "text_reference_evaluation": 30.8,
2483
  "text_rendering": 48.8,
2484
  "visual_reference_evaluation": 41.5
2485
  },
 
2503
  "physical_plausibility": 179,
2504
  "prompt_faithfulness": 273,
2505
  "rubric_adaptive": 273,
2506
+ "text_reference_evaluation": 206,
2507
  "text_rendering": 194,
2508
  "visual_reference_evaluation": 227
2509
  },
 
2515
  "physical_plausibility": 67.9,
2516
  "prompt_faithfulness": 42.6,
2517
  "rubric_adaptive": 45.5,
2518
+ "text_reference_evaluation": 25.8,
2519
  "text_rendering": 44.5,
2520
  "visual_reference_evaluation": 39.2
2521
  },
 
2539
  "physical_plausibility": 206,
2540
  "prompt_faithfulness": 273,
2541
  "rubric_adaptive": 273,
2542
+ "text_reference_evaluation": 209,
2543
  "text_rendering": 214,
2544
  "visual_reference_evaluation": 227
2545
  },
 
2551
  "physical_plausibility": 60.2,
2552
  "prompt_faithfulness": 37.9,
2553
  "rubric_adaptive": 42.2,
2554
+ "text_reference_evaluation": 20.1,
2555
  "text_rendering": 39.6,
2556
  "visual_reference_evaluation": 32.5
2557
  },
 
2575
  "physical_plausibility": 211,
2576
  "prompt_faithfulness": 273,
2577
  "rubric_adaptive": 273,
2578
+ "text_reference_evaluation": 216,
2579
  "text_rendering": 208,
2580
  "visual_reference_evaluation": 222
2581
  },
 
2587
  "physical_plausibility": 63.7,
2588
  "prompt_faithfulness": 35.2,
2589
  "rubric_adaptive": 38.4,
2590
+ "text_reference_evaluation": 15.6,
2591
  "text_rendering": 28.5,
2592
  "visual_reference_evaluation": 30.7
2593
  },
 
2611
  "physical_plausibility": 202,
2612
  "prompt_faithfulness": 273,
2613
  "rubric_adaptive": 273,
2614
+ "text_reference_evaluation": 217,
2615
  "text_rendering": 212,
2616
  "visual_reference_evaluation": 222
2617
  },
 
2623
  "physical_plausibility": 64.5,
2624
  "prompt_faithfulness": 34.8,
2625
  "rubric_adaptive": 37.4,
2626
+ "text_reference_evaluation": 13.9,
2627
  "text_rendering": 24.5,
2628
  "visual_reference_evaluation": 31.3
2629
  },
 
2647
  "physical_plausibility": 240,
2648
  "prompt_faithfulness": 273,
2649
  "rubric_adaptive": 273,
2650
+ "text_reference_evaluation": 216,
2651
  "text_rendering": 198,
2652
  "visual_reference_evaluation": 222
2653
  },
 
2659
  "physical_plausibility": 39.8,
2660
  "prompt_faithfulness": 16.3,
2661
  "rubric_adaptive": 20.3,
2662
+ "text_reference_evaluation": 1.9,
2663
  "text_rendering": 2.8,
2664
  "visual_reference_evaluation": 16.9
2665
  },
 
2683
  "physical_plausibility": 212,
2684
  "prompt_faithfulness": 273,
2685
  "rubric_adaptive": 273,
2686
+ "text_reference_evaluation": 221,
2687
  "text_rendering": 209,
2688
  "visual_reference_evaluation": 222
2689
  },
 
2695
  "physical_plausibility": 43.9,
2696
  "prompt_faithfulness": 15.8,
2697
  "rubric_adaptive": 19.9,
2698
+ "text_reference_evaluation": 2.9,
2699
  "text_rendering": 2.5,
2700
  "visual_reference_evaluation": 15.7
2701
  },
 
2719
  "physical_plausibility": 215,
2720
  "prompt_faithfulness": 272,
2721
  "rubric_adaptive": 273,
2722
+ "text_reference_evaluation": 222,
2723
  "text_rendering": 202,
2724
  "visual_reference_evaluation": 221
2725
  },
 
2731
  "physical_plausibility": 39.5,
2732
  "prompt_faithfulness": 10.0,
2733
  "rubric_adaptive": 15.1,
2734
+ "text_reference_evaluation": 0.8,
2735
  "text_rendering": 1.6,
2736
  "visual_reference_evaluation": 9.5
2737
  },
 
2755
  "physical_plausibility": 216,
2756
  "prompt_faithfulness": 273,
2757
  "rubric_adaptive": 273,
2758
+ "text_reference_evaluation": 213,
2759
  "text_rendering": 193,
2760
  "visual_reference_evaluation": 222
2761
  },
 
2767
  "physical_plausibility": 34.9,
2768
  "prompt_faithfulness": 12.8,
2769
  "rubric_adaptive": 14.8,
2770
+ "text_reference_evaluation": 0.9,
2771
  "text_rendering": 1.9,
2772
  "visual_reference_evaluation": 12.8
2773
  },
 
2791
  "physical_plausibility": 227,
2792
  "prompt_faithfulness": 273,
2793
  "rubric_adaptive": 273,
2794
+ "text_reference_evaluation": 244,
2795
  "text_rendering": 225,
2796
  "visual_reference_evaluation": 252
2797
  },
 
2803
  "physical_plausibility": 17.6,
2804
  "prompt_faithfulness": 5.1,
2805
  "rubric_adaptive": 6.7,
2806
+ "text_reference_evaluation": 0.5,
2807
  "text_rendering": 1.0,
2808
  "visual_reference_evaluation": 5.1
2809
  },
 
2829
  "physical_plausibility": 23,
2830
  "prompt_faithfulness": 30,
2831
  "rubric_adaptive": 30,
2832
+ "text_reference_evaluation": 21,
2833
  "text_rendering": 23,
2834
  "visual_reference_evaluation": 22
2835
  },
 
2841
  "physical_plausibility": 78.3,
2842
  "prompt_faithfulness": 66.1,
2843
  "rubric_adaptive": 69.0,
2844
+ "text_reference_evaluation": 60.3,
2845
  "text_rendering": 76.1,
2846
  "visual_reference_evaluation": 65.9
2847
  },
 
2865
  "physical_plausibility": 25,
2866
  "prompt_faithfulness": 30,
2867
  "rubric_adaptive": 30,
2868
+ "text_reference_evaluation": 20,
2869
  "text_rendering": 20,
2870
  "visual_reference_evaluation": 21
2871
  },
 
2877
  "physical_plausibility": 78.0,
2878
  "prompt_faithfulness": 52.2,
2879
  "rubric_adaptive": 55.4,
2880
+ "text_reference_evaluation": 46.7,
2881
  "text_rendering": 60.8,
2882
  "visual_reference_evaluation": 51.6
2883
  },
 
2901
  "physical_plausibility": 23,
2902
  "prompt_faithfulness": 30,
2903
  "rubric_adaptive": 30,
2904
+ "text_reference_evaluation": 21,
2905
  "text_rendering": 20,
2906
  "visual_reference_evaluation": 24
2907
  },
 
2913
  "physical_plausibility": 63.8,
2914
  "prompt_faithfulness": 54.4,
2915
  "rubric_adaptive": 56.2,
2916
+ "text_reference_evaluation": 39.7,
2917
  "text_rendering": 66.7,
2918
  "visual_reference_evaluation": 50.7
2919
  },
 
2937
  "physical_plausibility": 23,
2938
  "prompt_faithfulness": 30,
2939
  "rubric_adaptive": 30,
2940
+ "text_reference_evaluation": 22,
2941
  "text_rendering": 19,
2942
  "visual_reference_evaluation": 24
2943
  },
 
2949
  "physical_plausibility": 58.0,
2950
  "prompt_faithfulness": 46.7,
2951
  "rubric_adaptive": 54.6,
2952
+ "text_reference_evaluation": 36.4,
2953
  "text_rendering": 66.7,
2954
  "visual_reference_evaluation": 50.0
2955
  },
 
2973
  "physical_plausibility": 21,
2974
  "prompt_faithfulness": 30,
2975
  "rubric_adaptive": 30,
2976
+ "text_reference_evaluation": 21,
2977
  "text_rendering": 21,
2978
  "visual_reference_evaluation": 24
2979
  },
 
2985
  "physical_plausibility": 60.3,
2986
  "prompt_faithfulness": 45.6,
2987
  "rubric_adaptive": 47.7,
2988
+ "text_reference_evaluation": 38.1,
2989
  "text_rendering": 68.3,
2990
  "visual_reference_evaluation": 40.3
2991
  },
 
3009
  "physical_plausibility": 23,
3010
  "prompt_faithfulness": 30,
3011
  "rubric_adaptive": 30,
3012
+ "text_reference_evaluation": 20,
3013
  "text_rendering": 19,
3014
  "visual_reference_evaluation": 24
3015
  },
 
3021
  "physical_plausibility": 62.3,
3022
  "prompt_faithfulness": 41.1,
3023
  "rubric_adaptive": 46.3,
3024
+ "text_reference_evaluation": 26.7,
3025
  "text_rendering": 57.0,
3026
  "visual_reference_evaluation": 43.1
3027
  },
 
3045
  "physical_plausibility": 22,
3046
  "prompt_faithfulness": 30,
3047
  "rubric_adaptive": 30,
3048
+ "text_reference_evaluation": 22,
3049
  "text_rendering": 20,
3050
  "visual_reference_evaluation": 21
3051
  },
 
3057
  "physical_plausibility": 68.2,
3058
  "prompt_faithfulness": 37.8,
3059
  "rubric_adaptive": 42.2,
3060
+ "text_reference_evaluation": 27.3,
3061
  "text_rendering": 35.0,
3062
  "visual_reference_evaluation": 32.5
3063
  },
 
3081
  "physical_plausibility": 24,
3082
  "prompt_faithfulness": 29,
3083
  "rubric_adaptive": 30,
3084
+ "text_reference_evaluation": 21,
3085
  "text_rendering": 17,
3086
  "visual_reference_evaluation": 21
3087
  },
 
3093
  "physical_plausibility": 64.6,
3094
  "prompt_faithfulness": 40.8,
3095
  "rubric_adaptive": 41.6,
3096
+ "text_reference_evaluation": 28.6,
3097
  "text_rendering": 47.1,
3098
  "visual_reference_evaluation": 37.3
3099
  },
 
3117
  "physical_plausibility": 29,
3118
  "prompt_faithfulness": 30,
3119
  "rubric_adaptive": 30,
3120
+ "text_reference_evaluation": 22,
3121
  "text_rendering": 16,
3122
  "visual_reference_evaluation": 21
3123
  },
 
3129
  "physical_plausibility": 37.9,
3130
  "prompt_faithfulness": 15.6,
3131
  "rubric_adaptive": 22.8,
3132
+ "text_reference_evaluation": 2.3,
3133
  "text_rendering": 8.3,
3134
  "visual_reference_evaluation": 18.3
3135
  },
 
3153
  "physical_plausibility": 23,
3154
  "prompt_faithfulness": 30,
3155
  "rubric_adaptive": 30,
3156
+ "text_reference_evaluation": 23,
3157
  "text_rendering": 19,
3158
  "visual_reference_evaluation": 21
3159
  },
 
3165
  "physical_plausibility": 44.9,
3166
  "prompt_faithfulness": 12.8,
3167
  "rubric_adaptive": 19.0,
3168
+ "text_reference_evaluation": 1.4,
3169
  "text_rendering": 7.0,
3170
  "visual_reference_evaluation": 7.9
3171
  },
 
3189
  "physical_plausibility": 23,
3190
  "prompt_faithfulness": 30,
3191
  "rubric_adaptive": 30,
3192
+ "text_reference_evaluation": 23,
3193
  "text_rendering": 21,
3194
  "visual_reference_evaluation": 21
3195
  },
 
3201
  "physical_plausibility": 34.1,
3202
  "prompt_faithfulness": 14.4,
3203
  "rubric_adaptive": 22.0,
3204
+ "text_reference_evaluation": 2.9,
3205
  "text_rendering": 2.4,
3206
  "visual_reference_evaluation": 15.1
3207
  },
 
3225
  "physical_plausibility": 27,
3226
  "prompt_faithfulness": 30,
3227
  "rubric_adaptive": 30,
3228
+ "text_reference_evaluation": 22,
3229
  "text_rendering": 18,
3230
  "visual_reference_evaluation": 21
3231
  },
 
3237
  "physical_plausibility": 31.5,
3238
  "prompt_faithfulness": 7.8,
3239
  "rubric_adaptive": 10.2,
3240
+ "text_reference_evaluation": 0.8,
3241
  "text_rendering": 5.6,
3242
  "visual_reference_evaluation": 9.5
3243
  },
 
3261
  "physical_plausibility": 28,
3262
  "prompt_faithfulness": 30,
3263
  "rubric_adaptive": 30,
3264
+ "text_reference_evaluation": 24,
3265
  "text_rendering": 20,
3266
  "visual_reference_evaluation": 24
3267
  },
 
3273
  "physical_plausibility": 31.5,
3274
  "prompt_faithfulness": 3.9,
3275
  "rubric_adaptive": 7.9,
3276
+ "text_reference_evaluation": 2.8,
3277
  "text_rendering": 8.3,
3278
  "visual_reference_evaluation": 0.7
3279
  },
 
3299
  "physical_plausibility": 259,
3300
  "prompt_faithfulness": 411,
3301
  "rubric_adaptive": 411,
3302
+ "text_reference_evaluation": 363,
3303
  "text_rendering": 393,
3304
  "visual_reference_evaluation": 299
3305
  },
 
3311
  "physical_plausibility": 86.5,
3312
  "prompt_faithfulness": 73.7,
3313
  "rubric_adaptive": 73.5,
3314
+ "text_reference_evaluation": 58.1,
3315
  "text_rendering": 76.3,
3316
  "visual_reference_evaluation": 70.7
3317
  },
 
3335
  "physical_plausibility": 320,
3336
  "prompt_faithfulness": 411,
3337
  "rubric_adaptive": 411,
3338
+ "text_reference_evaluation": 370,
3339
  "text_rendering": 385,
3340
  "visual_reference_evaluation": 299
3341
  },
 
3347
  "physical_plausibility": 85.3,
3348
  "prompt_faithfulness": 64.7,
3349
  "rubric_adaptive": 65.4,
3350
+ "text_reference_evaluation": 49.1,
3351
  "text_rendering": 65.2,
3352
  "visual_reference_evaluation": 62.5
3353
  },
 
3371
  "physical_plausibility": 270,
3372
  "prompt_faithfulness": 404,
3373
  "rubric_adaptive": 404,
3374
+ "text_reference_evaluation": 373,
3375
  "text_rendering": 388,
3376
  "visual_reference_evaluation": 299
3377
  },
 
3383
  "physical_plausibility": 82.8,
3384
  "prompt_faithfulness": 64.4,
3385
  "rubric_adaptive": 64.2,
3386
+ "text_reference_evaluation": 47.9,
3387
  "text_rendering": 61.0,
3388
  "visual_reference_evaluation": 61.2
3389
  },
 
3407
  "physical_plausibility": 251,
3408
  "prompt_faithfulness": 408,
3409
  "rubric_adaptive": 408,
3410
+ "text_reference_evaluation": 370,
3411
  "text_rendering": 391,
3412
  "visual_reference_evaluation": 303
3413
  },
 
3419
  "physical_plausibility": 80.9,
3420
  "prompt_faithfulness": 51.7,
3421
  "rubric_adaptive": 54.0,
3422
+ "text_reference_evaluation": 35.7,
3423
  "text_rendering": 54.9,
3424
  "visual_reference_evaluation": 46.3
3425
  },
 
3443
  "physical_plausibility": 253,
3444
  "prompt_faithfulness": 411,
3445
  "rubric_adaptive": 411,
3446
+ "text_reference_evaluation": 380,
3447
  "text_rendering": 394,
3448
  "visual_reference_evaluation": 307
3449
  },
 
3455
  "physical_plausibility": 78.2,
3456
  "prompt_faithfulness": 49.2,
3457
  "rubric_adaptive": 51.5,
3458
+ "text_reference_evaluation": 33.8,
3459
  "text_rendering": 53.2,
3460
  "visual_reference_evaluation": 43.4
3461
  },
 
3479
  "physical_plausibility": 291,
3480
  "prompt_faithfulness": 411,
3481
  "rubric_adaptive": 411,
3482
+ "text_reference_evaluation": 376,
3483
  "text_rendering": 399,
3484
  "visual_reference_evaluation": 306
3485
  },
 
3491
  "physical_plausibility": 69.6,
3492
  "prompt_faithfulness": 45.6,
3493
  "rubric_adaptive": 48.5,
3494
+ "text_reference_evaluation": 29.3,
3495
  "text_rendering": 49.1,
3496
  "visual_reference_evaluation": 37.5
3497
  },
 
3515
  "physical_plausibility": 297,
3516
  "prompt_faithfulness": 411,
3517
  "rubric_adaptive": 411,
3518
+ "text_reference_evaluation": 387,
3519
  "text_rendering": 396,
3520
  "visual_reference_evaluation": 298
3521
  },
 
3527
  "physical_plausibility": 70.9,
3528
  "prompt_faithfulness": 38.2,
3529
  "rubric_adaptive": 42.4,
3530
+ "text_reference_evaluation": 23.4,
3531
  "text_rendering": 36.3,
3532
  "visual_reference_evaluation": 33.9
3533
  },
 
3551
  "physical_plausibility": 293,
3552
  "prompt_faithfulness": 411,
3553
  "rubric_adaptive": 411,
3554
+ "text_reference_evaluation": 395,
3555
  "text_rendering": 392,
3556
  "visual_reference_evaluation": 299
3557
  },
 
3563
  "physical_plausibility": 72.9,
3564
  "prompt_faithfulness": 34.3,
3565
  "rubric_adaptive": 37.4,
3566
+ "text_reference_evaluation": 15.5,
3567
  "text_rendering": 26.0,
3568
  "visual_reference_evaluation": 30.5
3569
  },
 
3587
  "physical_plausibility": 354,
3588
  "prompt_faithfulness": 411,
3589
  "rubric_adaptive": 411,
3590
+ "text_reference_evaluation": 398,
3591
  "text_rendering": 402,
3592
  "visual_reference_evaluation": 298
3593
  },
 
3599
  "physical_plausibility": 44.4,
3600
  "prompt_faithfulness": 16.7,
3601
  "rubric_adaptive": 20.9,
3602
+ "text_reference_evaluation": 6.9,
3603
  "text_rendering": 10.9,
3604
  "visual_reference_evaluation": 15.8
3605
  },
 
3623
  "physical_plausibility": 297,
3624
  "prompt_faithfulness": 411,
3625
  "rubric_adaptive": 411,
3626
+ "text_reference_evaluation": 406,
3627
  "text_rendering": 400,
3628
  "visual_reference_evaluation": 298
3629
  },
 
3635
  "physical_plausibility": 49.6,
3636
  "prompt_faithfulness": 14.1,
3637
  "rubric_adaptive": 18.8,
3638
+ "text_reference_evaluation": 5.3,
3639
  "text_rendering": 7.2,
3640
  "visual_reference_evaluation": 12.8
3641
  },
 
3659
  "physical_plausibility": 289,
3660
  "prompt_faithfulness": 410,
3661
  "rubric_adaptive": 411,
3662
+ "text_reference_evaluation": 403,
3663
  "text_rendering": 391,
3664
  "visual_reference_evaluation": 297
3665
  },
 
3671
  "physical_plausibility": 45.8,
3672
  "prompt_faithfulness": 10.1,
3673
  "rubric_adaptive": 15.3,
3674
+ "text_reference_evaluation": 2.7,
3675
  "text_rendering": 3.9,
3676
  "visual_reference_evaluation": 9.3
3677
  },
 
3695
  "physical_plausibility": 319,
3696
  "prompt_faithfulness": 411,
3697
  "rubric_adaptive": 411,
3698
+ "text_reference_evaluation": 406,
3699
  "text_rendering": 390,
3700
  "visual_reference_evaluation": 298
3701
  },
 
3707
  "physical_plausibility": 35.9,
3708
  "prompt_faithfulness": 10.3,
3709
  "rubric_adaptive": 13.7,
3710
+ "text_reference_evaluation": 2.0,
3711
  "text_rendering": 3.4,
3712
  "visual_reference_evaluation": 9.7
3713
  },
 
3731
  "physical_plausibility": 337,
3732
  "prompt_faithfulness": 411,
3733
  "rubric_adaptive": 411,
3734
+ "text_reference_evaluation": 406,
3735
  "text_rendering": 397,
3736
  "visual_reference_evaluation": 369
3737
  },
 
3743
  "physical_plausibility": 14.3,
3744
  "prompt_faithfulness": 2.8,
3745
  "rubric_adaptive": 4.7,
3746
+ "text_reference_evaluation": 0.7,
3747
  "text_rendering": 1.0,
3748
  "visual_reference_evaluation": 3.3
3749
  },
 
3769
  "physical_plausibility": 10,
3770
  "prompt_faithfulness": 38,
3771
  "rubric_adaptive": 38,
3772
+ "text_reference_evaluation": 35,
3773
  "text_rendering": 35,
3774
  "visual_reference_evaluation": 25
3775
  },
 
3781
  "physical_plausibility": 85.0,
3782
  "prompt_faithfulness": 63.2,
3783
  "rubric_adaptive": 57.9,
3784
+ "text_reference_evaluation": 23.3,
3785
  "text_rendering": 68.1,
3786
  "visual_reference_evaluation": 56.7
3787
  },
 
3805
  "physical_plausibility": 29,
3806
  "prompt_faithfulness": 38,
3807
  "rubric_adaptive": 38,
3808
+ "text_reference_evaluation": 36,
3809
  "text_rendering": 36,
3810
  "visual_reference_evaluation": 25
3811
  },
 
3817
  "physical_plausibility": 86.8,
3818
  "prompt_faithfulness": 53.9,
3819
  "rubric_adaptive": 48.5,
3820
+ "text_reference_evaluation": 23.6,
3821
  "text_rendering": 60.6,
3822
  "visual_reference_evaluation": 45.3
3823
  },
 
3841
  "physical_plausibility": 16,
3842
  "prompt_faithfulness": 38,
3843
  "rubric_adaptive": 38,
3844
+ "text_reference_evaluation": 35,
3845
  "text_rendering": 37,
3846
  "visual_reference_evaluation": 27
3847
  },
 
3853
  "physical_plausibility": 89.6,
3854
  "prompt_faithfulness": 56.1,
3855
  "rubric_adaptive": 53.6,
3856
+ "text_reference_evaluation": 24.3,
3857
  "text_rendering": 58.1,
3858
  "visual_reference_evaluation": 46.9
3859
  },
 
3877
  "physical_plausibility": 8,
3878
  "prompt_faithfulness": 38,
3879
  "rubric_adaptive": 38,
3880
+ "text_reference_evaluation": 38,
3881
  "text_rendering": 38,
3882
  "visual_reference_evaluation": 27
3883
  },
 
3889
  "physical_plausibility": 56.2,
3890
  "prompt_faithfulness": 36.0,
3891
  "rubric_adaptive": 32.7,
3892
+ "text_reference_evaluation": 11.0,
3893
  "text_rendering": 40.4,
3894
  "visual_reference_evaluation": 20.4
3895
  },
 
3913
  "physical_plausibility": 11,
3914
  "prompt_faithfulness": 38,
3915
  "rubric_adaptive": 38,
3916
+ "text_reference_evaluation": 38,
3917
  "text_rendering": 35,
3918
  "visual_reference_evaluation": 27
3919
  },
 
3925
  "physical_plausibility": 77.3,
3926
  "prompt_faithfulness": 32.5,
3927
  "rubric_adaptive": 29.2,
3928
+ "text_reference_evaluation": 8.3,
3929
  "text_rendering": 35.2,
3930
  "visual_reference_evaluation": 19.1
3931
  },
 
3949
  "physical_plausibility": 16,
3950
  "prompt_faithfulness": 38,
3951
  "rubric_adaptive": 38,
3952
+ "text_reference_evaluation": 36,
3953
  "text_rendering": 37,
3954
  "visual_reference_evaluation": 27
3955
  },
 
3961
  "physical_plausibility": 55.2,
3962
  "prompt_faithfulness": 35.1,
3963
  "rubric_adaptive": 27.5,
3964
+ "text_reference_evaluation": 9.3,
3965
  "text_rendering": 39.6,
3966
  "visual_reference_evaluation": 9.3
3967
  },
 
3985
  "physical_plausibility": 23,
3986
  "prompt_faithfulness": 38,
3987
  "rubric_adaptive": 38,
3988
+ "text_reference_evaluation": 37,
3989
  "text_rendering": 35,
3990
  "visual_reference_evaluation": 25
3991
  },
 
3997
  "physical_plausibility": 75.4,
3998
  "prompt_faithfulness": 22.4,
3999
  "rubric_adaptive": 21.2,
4000
+ "text_reference_evaluation": 5.4,
4001
  "text_rendering": 19.0,
4002
  "visual_reference_evaluation": 16.7
4003
  },
 
4021
  "physical_plausibility": 20,
4022
  "prompt_faithfulness": 38,
4023
  "rubric_adaptive": 38,
4024
+ "text_reference_evaluation": 36,
4025
  "text_rendering": 38,
4026
  "visual_reference_evaluation": 25
4027
  },
 
4033
  "physical_plausibility": 55.8,
4034
  "prompt_faithfulness": 22.4,
4035
  "rubric_adaptive": 22.0,
4036
+ "text_reference_evaluation": 5.1,
4037
  "text_rendering": 23.2,
4038
  "visual_reference_evaluation": 9.3
4039
  },
 
4057
  "physical_plausibility": 28,
4058
  "prompt_faithfulness": 38,
4059
  "rubric_adaptive": 38,
4060
+ "text_reference_evaluation": 38,
4061
  "text_rendering": 38,
4062
  "visual_reference_evaluation": 25
4063
  },
 
4069
  "physical_plausibility": 28.0,
4070
  "prompt_faithfulness": 3.5,
4071
  "rubric_adaptive": 5.7,
4072
+ "text_reference_evaluation": 1.8,
4073
  "text_rendering": 3.1,
4074
  "visual_reference_evaluation": 4.0
4075
  },
 
4093
  "physical_plausibility": 23,
4094
  "prompt_faithfulness": 38,
4095
  "rubric_adaptive": 38,
4096
+ "text_reference_evaluation": 38,
4097
  "text_rendering": 38,
4098
  "visual_reference_evaluation": 25
4099
  },
 
4105
  "physical_plausibility": 15.2,
4106
  "prompt_faithfulness": 2.6,
4107
  "rubric_adaptive": 3.3,
4108
+ "text_reference_evaluation": 1.3,
4109
  "text_rendering": 1.3,
4110
  "visual_reference_evaluation": 1.3
4111
  },
 
4129
  "physical_plausibility": 20,
4130
  "prompt_faithfulness": 38,
4131
  "rubric_adaptive": 38,
4132
+ "text_reference_evaluation": 38,
4133
  "text_rendering": 38,
4134
  "visual_reference_evaluation": 25
4135
  },
 
4141
  "physical_plausibility": 28.3,
4142
  "prompt_faithfulness": 1.8,
4143
  "rubric_adaptive": 3.8,
4144
+ "text_reference_evaluation": 0.9,
4145
  "text_rendering": 0.9,
4146
  "visual_reference_evaluation": 4.0
4147
  },
 
4165
  "physical_plausibility": 26,
4166
  "prompt_faithfulness": 38,
4167
  "rubric_adaptive": 38,
4168
+ "text_reference_evaluation": 37,
4169
  "text_rendering": 34,
4170
  "visual_reference_evaluation": 25
4171
  },
 
4177
  "physical_plausibility": 18.6,
4178
  "prompt_faithfulness": 0.4,
4179
  "rubric_adaptive": 2.2,
4180
+ "text_reference_evaluation": 0.0,
4181
  "text_rendering": 0.0,
4182
  "visual_reference_evaluation": 0.0
4183
  },
 
4201
  "physical_plausibility": 26,
4202
  "prompt_faithfulness": 38,
4203
  "rubric_adaptive": 38,
4204
+ "text_reference_evaluation": 37,
4205
  "text_rendering": 36,
4206
  "visual_reference_evaluation": 25
4207
  },
 
4213
  "physical_plausibility": 6.4,
4214
  "prompt_faithfulness": 0.4,
4215
  "rubric_adaptive": 1.2,
4216
+ "text_reference_evaluation": 0.0,
4217
  "text_rendering": 0.0,
4218
  "visual_reference_evaluation": 0.7
4219
  },
 
4239
  "physical_plausibility": 24,
4240
  "prompt_faithfulness": 56,
4241
  "rubric_adaptive": 56,
4242
+ "text_reference_evaluation": 51,
4243
  "text_rendering": 53,
4244
  "visual_reference_evaluation": 46
4245
  },
 
4251
  "physical_plausibility": 86.8,
4252
  "prompt_faithfulness": 69.6,
4253
  "rubric_adaptive": 64.9,
4254
+ "text_reference_evaluation": 37.3,
4255
  "text_rendering": 77.0,
4256
  "visual_reference_evaluation": 64.9
4257
  },
 
4275
  "physical_plausibility": 33,
4276
  "prompt_faithfulness": 56,
4277
  "rubric_adaptive": 56,
4278
+ "text_reference_evaluation": 52,
4279
  "text_rendering": 53,
4280
  "visual_reference_evaluation": 46
4281
  },
 
4287
  "physical_plausibility": 81.8,
4288
  "prompt_faithfulness": 59.5,
4289
  "rubric_adaptive": 58.9,
4290
+ "text_reference_evaluation": 32.4,
4291
  "text_rendering": 60.1,
4292
  "visual_reference_evaluation": 51.1
4293
  },
 
4311
  "physical_plausibility": 50,
4312
  "prompt_faithfulness": 56,
4313
  "rubric_adaptive": 56,
4314
+ "text_reference_evaluation": 52,
4315
  "text_rendering": 50,
4316
  "visual_reference_evaluation": 46
4317
  },
 
4323
  "physical_plausibility": 79.7,
4324
  "prompt_faithfulness": 59.4,
4325
  "rubric_adaptive": 52.9,
4326
+ "text_reference_evaluation": 30.4,
4327
  "text_rendering": 59.0,
4328
  "visual_reference_evaluation": 49.6
4329
  },
 
4347
  "physical_plausibility": 25,
4348
  "prompt_faithfulness": 56,
4349
  "rubric_adaptive": 56,
4350
+ "text_reference_evaluation": 54,
4351
  "text_rendering": 53,
4352
  "visual_reference_evaluation": 46
4353
  },
 
4359
  "physical_plausibility": 75.3,
4360
  "prompt_faithfulness": 45.1,
4361
  "rubric_adaptive": 43.3,
4362
+ "text_reference_evaluation": 24.1,
4363
  "text_rendering": 51.9,
4364
  "visual_reference_evaluation": 34.1
4365
  },
 
4383
  "physical_plausibility": 19,
4384
  "prompt_faithfulness": 56,
4385
  "rubric_adaptive": 56,
4386
+ "text_reference_evaluation": 52,
4387
  "text_rendering": 55,
4388
  "visual_reference_evaluation": 46
4389
  },
 
4395
  "physical_plausibility": 71.1,
4396
  "prompt_faithfulness": 45.5,
4397
  "rubric_adaptive": 44.0,
4398
+ "text_reference_evaluation": 24.0,
4399
  "text_rendering": 51.2,
4400
  "visual_reference_evaluation": 35.9
4401
  },
 
4419
  "physical_plausibility": 31,
4420
  "prompt_faithfulness": 56,
4421
  "rubric_adaptive": 56,
4422
+ "text_reference_evaluation": 52,
4423
  "text_rendering": 53,
4424
  "visual_reference_evaluation": 46
4425
  },
 
4431
  "physical_plausibility": 66.7,
4432
  "prompt_faithfulness": 42.3,
4433
  "rubric_adaptive": 39.8,
4434
+ "text_reference_evaluation": 19.6,
4435
  "text_rendering": 49.1,
4436
  "visual_reference_evaluation": 25.7
4437
  },
 
4455
  "physical_plausibility": 34,
4456
  "prompt_faithfulness": 56,
4457
  "rubric_adaptive": 56,
4458
+ "text_reference_evaluation": 52,
4459
  "text_rendering": 55,
4460
  "visual_reference_evaluation": 46
4461
  },
 
4467
  "physical_plausibility": 68.6,
4468
  "prompt_faithfulness": 31.8,
4469
  "rubric_adaptive": 34.3,
4470
+ "text_reference_evaluation": 15.7,
4471
  "text_rendering": 31.5,
4472
  "visual_reference_evaluation": 24.6
4473
  },
 
4491
  "physical_plausibility": 38,
4492
  "prompt_faithfulness": 56,
4493
  "rubric_adaptive": 56,
4494
+ "text_reference_evaluation": 53,
4495
  "text_rendering": 54,
4496
  "visual_reference_evaluation": 46
4497
  },
 
4503
  "physical_plausibility": 64.9,
4504
  "prompt_faithfulness": 27.1,
4505
  "rubric_adaptive": 26.6,
4506
+ "text_reference_evaluation": 7.5,
4507
  "text_rendering": 19.1,
4508
  "visual_reference_evaluation": 21.7
4509
  },
 
4527
  "physical_plausibility": 46,
4528
  "prompt_faithfulness": 56,
4529
  "rubric_adaptive": 56,
4530
+ "text_reference_evaluation": 55,
4531
  "text_rendering": 55,
4532
  "visual_reference_evaluation": 46
4533
  },
 
4539
  "physical_plausibility": 35.5,
4540
  "prompt_faithfulness": 8.0,
4541
  "rubric_adaptive": 13.1,
4542
+ "text_reference_evaluation": 4.8,
4543
  "text_rendering": 5.5,
4544
  "visual_reference_evaluation": 9.4
4545
  },
 
4563
  "physical_plausibility": 39,
4564
  "prompt_faithfulness": 56,
4565
  "rubric_adaptive": 56,
4566
+ "text_reference_evaluation": 55,
4567
  "text_rendering": 52,
4568
  "visual_reference_evaluation": 46
4569
  },
 
4575
  "physical_plausibility": 32.1,
4576
  "prompt_faithfulness": 6.0,
4577
  "rubric_adaptive": 9.1,
4578
+ "text_reference_evaluation": 2.1,
4579
  "text_rendering": 3.8,
4580
  "visual_reference_evaluation": 6.2
4581
  },
 
4599
  "physical_plausibility": 33,
4600
  "prompt_faithfulness": 56,
4601
  "rubric_adaptive": 56,
4602
+ "text_reference_evaluation": 56,
4603
  "text_rendering": 55,
4604
  "visual_reference_evaluation": 46
4605
  },
 
4611
  "physical_plausibility": 29.3,
4612
  "prompt_faithfulness": 3.0,
4613
  "rubric_adaptive": 6.3,
4614
+ "text_reference_evaluation": 1.2,
4615
  "text_rendering": 1.5,
4616
  "visual_reference_evaluation": 4.3
4617
  },
 
4635
  "physical_plausibility": 41,
4636
  "prompt_faithfulness": 56,
4637
  "rubric_adaptive": 56,
4638
+ "text_reference_evaluation": 54,
4639
  "text_rendering": 51,
4640
  "visual_reference_evaluation": 46
4641
  },
 
4647
  "physical_plausibility": 14.6,
4648
  "prompt_faithfulness": 2.7,
4649
  "rubric_adaptive": 5.2,
4650
+ "text_reference_evaluation": 0.3,
4651
  "text_rendering": 0.3,
4652
  "visual_reference_evaluation": 3.6
4653
  },
 
4671
  "physical_plausibility": 46,
4672
  "prompt_faithfulness": 56,
4673
  "rubric_adaptive": 56,
4674
+ "text_reference_evaluation": 54,
4675
  "text_rendering": 53,
4676
  "visual_reference_evaluation": 47
4677
  },
 
4683
  "physical_plausibility": 14.5,
4684
  "prompt_faithfulness": 1.8,
4685
  "rubric_adaptive": 2.9,
4686
+ "text_reference_evaluation": 0.0,
4687
  "text_rendering": 0.0,
4688
  "visual_reference_evaluation": 2.1
4689
  },
 
4709
  "physical_plausibility": 27,
4710
  "prompt_faithfulness": 33,
4711
  "rubric_adaptive": 33,
4712
+ "text_reference_evaluation": 18,
4713
  "text_rendering": 21,
4714
  "visual_reference_evaluation": 25
4715
  },
 
4721
  "physical_plausibility": 78.4,
4722
  "prompt_faithfulness": 67.2,
4723
  "rubric_adaptive": 68.6,
4724
+ "text_reference_evaluation": 44.4,
4725
  "text_rendering": 78.6,
4726
  "visual_reference_evaluation": 66.0
4727
  },
 
4745
  "physical_plausibility": 28,
4746
  "prompt_faithfulness": 33,
4747
  "rubric_adaptive": 33,
4748
+ "text_reference_evaluation": 16,
4749
  "text_rendering": 14,
4750
  "visual_reference_evaluation": 25
4751
  },
 
4757
  "physical_plausibility": 84.5,
4758
  "prompt_faithfulness": 58.1,
4759
  "rubric_adaptive": 62.7,
4760
+ "text_reference_evaluation": 46.9,
4761
  "text_rendering": 63.1,
4762
  "visual_reference_evaluation": 51.3
4763
  },
 
4772
  "overall_9": 67.1,
4773
  "type": "Commercial"
4774
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4775
  {
4776
  "component_counts": {
4777
  "ai_naturalness": 33,
 
4781
  "physical_plausibility": 24,
4782
  "prompt_faithfulness": 33,
4783
  "rubric_adaptive": 33,
4784
+ "text_reference_evaluation": 16,
4785
  "text_rendering": 15,
4786
  "visual_reference_evaluation": 26
4787
  },
 
4793
  "physical_plausibility": 75.0,
4794
  "prompt_faithfulness": 60.6,
4795
  "rubric_adaptive": 64.4,
4796
+ "text_reference_evaluation": 41.7,
4797
  "text_rendering": 60.0,
4798
  "visual_reference_evaluation": 56.4
4799
  },
 
4817
  "physical_plausibility": 23,
4818
  "prompt_faithfulness": 31,
4819
  "rubric_adaptive": 31,
4820
+ "text_reference_evaluation": 20,
4821
  "text_rendering": 18,
4822
  "visual_reference_evaluation": 28
4823
  },
 
4829
  "physical_plausibility": 64.5,
4830
  "prompt_faithfulness": 59.7,
4831
  "rubric_adaptive": 62.2,
4832
+ "text_reference_evaluation": 45.0,
4833
  "text_rendering": 75.9,
4834
  "visual_reference_evaluation": 60.7
4835
  },
 
4844
  "overall_9": 65.2,
4845
  "type": "Commercial"
4846
  },
4847
+ {
4848
+ "component_counts": {
4849
+ "ai_naturalness": 33,
4850
+ "checklist": 33,
4851
+ "composition_and_aesthetics": 33,
4852
+ "image_quality": 33,
4853
+ "physical_plausibility": 28,
4854
+ "prompt_faithfulness": 33,
4855
+ "rubric_adaptive": 33,
4856
+ "text_reference_evaluation": 20,
4857
+ "text_rendering": 15,
4858
+ "visual_reference_evaluation": 30
4859
+ },
4860
+ "components": {
4861
+ "ai_naturalness": 65.2,
4862
+ "checklist": 59.8,
4863
+ "composition_and_aesthetics": 75.8,
4864
+ "image_quality": 75.8,
4865
+ "physical_plausibility": 79.2,
4866
+ "prompt_faithfulness": 51.5,
4867
+ "rubric_adaptive": 58.2,
4868
+ "text_reference_evaluation": 40.8,
4869
+ "text_rendering": 78.9,
4870
+ "visual_reference_evaluation": 56.1
4871
+ },
4872
+ "coverage": 1.0,
4873
+ "display_name": "Qwen-Image-2",
4874
+ "missing_policy": "zero_fill",
4875
+ "model_id": "qwen2",
4876
+ "n_included": 33,
4877
+ "n_scored": 33,
4878
+ "n_total": 33,
4879
+ "overall_10": 63.9,
4880
+ "overall_9": 65.6,
4881
+ "type": "Commercial"
4882
+ },
4883
  {
4884
  "component_counts": {
4885
  "ai_naturalness": 33,
 
4889
  "physical_plausibility": 26,
4890
  "prompt_faithfulness": 33,
4891
  "rubric_adaptive": 33,
4892
+ "text_reference_evaluation": 18,
4893
  "text_rendering": 15,
4894
  "visual_reference_evaluation": 30
4895
  },
 
4901
  "physical_plausibility": 75.0,
4902
  "prompt_faithfulness": 51.5,
4903
  "rubric_adaptive": 55.8,
4904
+ "text_reference_evaluation": 41.7,
4905
  "text_rendering": 75.6,
4906
  "visual_reference_evaluation": 54.4
4907
  },
 
4925
  "physical_plausibility": 24,
4926
  "prompt_faithfulness": 33,
4927
  "rubric_adaptive": 33,
4928
+ "text_reference_evaluation": 16,
4929
  "text_rendering": 19,
4930
  "visual_reference_evaluation": 30
4931
  },
 
4937
  "physical_plausibility": 72.2,
4938
  "prompt_faithfulness": 52.5,
4939
  "rubric_adaptive": 58.6,
4940
+ "text_reference_evaluation": 38.5,
4941
  "text_rendering": 61.4,
4942
  "visual_reference_evaluation": 51.1
4943
  },
 
4961
  "physical_plausibility": 23,
4962
  "prompt_faithfulness": 33,
4963
  "rubric_adaptive": 33,
4964
+ "text_reference_evaluation": 22,
4965
  "text_rendering": 14,
4966
  "visual_reference_evaluation": 25
4967
  },
 
4973
  "physical_plausibility": 70.3,
4974
  "prompt_faithfulness": 43.4,
4975
  "rubric_adaptive": 49.2,
4976
+ "text_reference_evaluation": 26.5,
4977
  "text_rendering": 35.7,
4978
  "visual_reference_evaluation": 34.7
4979
  },
 
4997
  "physical_plausibility": 31,
4998
  "prompt_faithfulness": 33,
4999
  "rubric_adaptive": 33,
5000
+ "text_reference_evaluation": 21,
5001
  "text_rendering": 13,
5002
  "visual_reference_evaluation": 25
5003
  },
 
5009
  "physical_plausibility": 55.9,
5010
  "prompt_faithfulness": 22.0,
5011
  "rubric_adaptive": 29.3,
5012
+ "text_reference_evaluation": 7.1,
5013
  "text_rendering": 3.8,
5014
  "visual_reference_evaluation": 28.7
5015
  },
 
5033
  "physical_plausibility": 24,
5034
  "prompt_faithfulness": 33,
5035
  "rubric_adaptive": 33,
5036
+ "text_reference_evaluation": 21,
5037
  "text_rendering": 16,
5038
  "visual_reference_evaluation": 26
5039
  },
 
5045
  "physical_plausibility": 61.8,
5046
  "prompt_faithfulness": 20.7,
5047
  "rubric_adaptive": 29.2,
5048
+ "text_reference_evaluation": 7.1,
5049
  "text_rendering": 4.2,
5050
  "visual_reference_evaluation": 22.4
5051
  },
 
5069
  "physical_plausibility": 23,
5070
  "prompt_faithfulness": 33,
5071
  "rubric_adaptive": 33,
5072
+ "text_reference_evaluation": 22,
5073
  "text_rendering": 16,
5074
  "visual_reference_evaluation": 25
5075
  },
 
5081
  "physical_plausibility": 58.7,
5082
  "prompt_faithfulness": 13.1,
5083
  "rubric_adaptive": 23.1,
5084
+ "text_reference_evaluation": 2.3,
5085
  "text_rendering": 2.1,
5086
  "visual_reference_evaluation": 13.3
5087
  },
 
5105
  "physical_plausibility": 30,
5106
  "prompt_faithfulness": 33,
5107
  "rubric_adaptive": 33,
5108
+ "text_reference_evaluation": 20,
5109
  "text_rendering": 13,
5110
  "visual_reference_evaluation": 25
5111
  },
 
5117
  "physical_plausibility": 43.9,
5118
  "prompt_faithfulness": 17.7,
5119
  "rubric_adaptive": 22.6,
5120
+ "text_reference_evaluation": 6.7,
5121
  "text_rendering": 1.3,
5122
  "visual_reference_evaluation": 18.0
5123
  },
 
5141
  "physical_plausibility": 28,
5142
  "prompt_faithfulness": 33,
5143
  "rubric_adaptive": 33,
5144
+ "text_reference_evaluation": 22,
5145
  "text_rendering": 15,
5146
  "visual_reference_evaluation": 26
5147
  },
 
5153
  "physical_plausibility": 51.2,
5154
  "prompt_faithfulness": 14.6,
5155
  "rubric_adaptive": 21.6,
5156
+ "text_reference_evaluation": 6.1,
5157
  "text_rendering": 3.3,
5158
  "visual_reference_evaluation": 15.4
5159
  },
 
5179
  "physical_plausibility": 117,
5180
  "prompt_faithfulness": 185,
5181
  "rubric_adaptive": 185,
5182
+ "text_reference_evaluation": 133,
5183
  "text_rendering": 164,
5184
  "visual_reference_evaluation": 150
5185
  },
 
5191
  "physical_plausibility": 86.8,
5192
  "prompt_faithfulness": 76.1,
5193
  "rubric_adaptive": 75.5,
5194
+ "text_reference_evaluation": 59.3,
5195
  "text_rendering": 79.8,
5196
  "visual_reference_evaluation": 74.4
5197
  },
 
5215
  "physical_plausibility": 142,
5216
  "prompt_faithfulness": 185,
5217
  "rubric_adaptive": 185,
5218
+ "text_reference_evaluation": 139,
5219
  "text_rendering": 158,
5220
  "visual_reference_evaluation": 150
5221
  },
 
5227
  "physical_plausibility": 86.9,
5228
  "prompt_faithfulness": 66.1,
5229
  "rubric_adaptive": 67.7,
5230
+ "text_reference_evaluation": 52.5,
5231
  "text_rendering": 70.6,
5232
  "visual_reference_evaluation": 65.6
5233
  },
 
5251
  "physical_plausibility": 123,
5252
  "prompt_faithfulness": 180,
5253
  "rubric_adaptive": 180,
5254
+ "text_reference_evaluation": 140,
5255
  "text_rendering": 157,
5256
  "visual_reference_evaluation": 151
5257
  },
 
5263
  "physical_plausibility": 80.2,
5264
  "prompt_faithfulness": 63.4,
5265
  "rubric_adaptive": 64.8,
5266
+ "text_reference_evaluation": 50.0,
5267
  "text_rendering": 64.2,
5268
  "visual_reference_evaluation": 61.9
5269
  },
 
5287
  "physical_plausibility": 119,
5288
  "prompt_faithfulness": 183,
5289
  "rubric_adaptive": 183,
5290
+ "text_reference_evaluation": 137,
5291
  "text_rendering": 148,
5292
  "visual_reference_evaluation": 154
5293
  },
 
5299
  "physical_plausibility": 76.8,
5300
  "prompt_faithfulness": 51.4,
5301
  "rubric_adaptive": 54.2,
5302
+ "text_reference_evaluation": 39.2,
5303
  "text_rendering": 58.6,
5304
  "visual_reference_evaluation": 47.3
5305
  },
 
5323
  "physical_plausibility": 119,
5324
  "prompt_faithfulness": 185,
5325
  "rubric_adaptive": 185,
5326
+ "text_reference_evaluation": 147,
5327
  "text_rendering": 148,
5328
  "visual_reference_evaluation": 156
5329
  },
 
5335
  "physical_plausibility": 73.7,
5336
  "prompt_faithfulness": 49.0,
5337
  "rubric_adaptive": 52.4,
5338
+ "text_reference_evaluation": 37.6,
5339
  "text_rendering": 54.8,
5340
  "visual_reference_evaluation": 44.4
5341
  },
 
5359
  "physical_plausibility": 134,
5360
  "prompt_faithfulness": 185,
5361
  "rubric_adaptive": 185,
5362
+ "text_reference_evaluation": 142,
5363
  "text_rendering": 154,
5364
  "visual_reference_evaluation": 156
5365
  },
 
5371
  "physical_plausibility": 68.7,
5372
  "prompt_faithfulness": 45.5,
5373
  "rubric_adaptive": 49.4,
5374
+ "text_reference_evaluation": 32.0,
5375
  "text_rendering": 51.9,
5376
  "visual_reference_evaluation": 41.6
5377
  },
 
5395
  "physical_plausibility": 136,
5396
  "prompt_faithfulness": 185,
5397
  "rubric_adaptive": 185,
5398
+ "text_reference_evaluation": 149,
5399
  "text_rendering": 148,
5400
  "visual_reference_evaluation": 150
5401
  },
 
5407
  "physical_plausibility": 67.2,
5408
  "prompt_faithfulness": 37.8,
5409
  "rubric_adaptive": 43.8,
5410
+ "text_reference_evaluation": 24.8,
5411
  "text_rendering": 37.3,
5412
  "visual_reference_evaluation": 38.8
5413
  },
 
5431
  "physical_plausibility": 129,
5432
  "prompt_faithfulness": 185,
5433
  "rubric_adaptive": 185,
5434
+ "text_reference_evaluation": 153,
5435
  "text_rendering": 153,
5436
  "visual_reference_evaluation": 150
5437
  },
 
5443
  "physical_plausibility": 74.2,
5444
  "prompt_faithfulness": 36.8,
5445
  "rubric_adaptive": 41.1,
5446
+ "text_reference_evaluation": 18.8,
5447
  "text_rendering": 26.6,
5448
  "visual_reference_evaluation": 37.7
5449
  },
 
5467
  "physical_plausibility": 156,
5468
  "prompt_faithfulness": 185,
5469
  "rubric_adaptive": 185,
5470
+ "text_reference_evaluation": 150,
5471
  "text_rendering": 153,
5472
  "visual_reference_evaluation": 150
5473
  },
 
5479
  "physical_plausibility": 47.1,
5480
  "prompt_faithfulness": 18.9,
5481
  "rubric_adaptive": 24.3,
5482
+ "text_reference_evaluation": 8.4,
5483
  "text_rendering": 10.7,
5484
  "visual_reference_evaluation": 20.4
5485
  },
 
5503
  "physical_plausibility": 134,
5504
  "prompt_faithfulness": 185,
5505
  "rubric_adaptive": 185,
5506
+ "text_reference_evaluation": 159,
5507
  "text_rendering": 157,
5508
  "visual_reference_evaluation": 150
5509
  },
 
5515
  "physical_plausibility": 50.1,
5516
  "prompt_faithfulness": 17.2,
5517
  "rubric_adaptive": 22.6,
5518
+ "text_reference_evaluation": 5.8,
5519
  "text_rendering": 9.1,
5520
  "visual_reference_evaluation": 20.2
5521
  },
 
5539
  "physical_plausibility": 131,
5540
  "prompt_faithfulness": 184,
5541
  "rubric_adaptive": 185,
5542
+ "text_reference_evaluation": 157,
5543
  "text_rendering": 148,
5544
  "visual_reference_evaluation": 149
5545
  },
 
5551
  "physical_plausibility": 50.0,
5552
  "prompt_faithfulness": 12.1,
5553
  "rubric_adaptive": 18.1,
5554
+ "text_reference_evaluation": 3.5,
5555
  "text_rendering": 3.7,
5556
  "visual_reference_evaluation": 15.7
5557
  },
 
5575
  "physical_plausibility": 148,
5576
  "prompt_faithfulness": 185,
5577
  "rubric_adaptive": 185,
5578
+ "text_reference_evaluation": 153,
5579
  "text_rendering": 149,
5580
  "visual_reference_evaluation": 150
5581
  },
 
5587
  "physical_plausibility": 35.8,
5588
  "prompt_faithfulness": 10.7,
5589
  "rubric_adaptive": 14.6,
5590
+ "text_reference_evaluation": 1.5,
5591
  "text_rendering": 1.7,
5592
  "visual_reference_evaluation": 12.8
5593
  },
 
5611
  "physical_plausibility": 151,
5612
  "prompt_faithfulness": 185,
5613
  "rubric_adaptive": 185,
5614
+ "text_reference_evaluation": 161,
5615
  "text_rendering": 159,
5616
  "visual_reference_evaluation": 169
5617
  },
 
5623
  "physical_plausibility": 22.0,
5624
  "prompt_faithfulness": 6.3,
5625
  "rubric_adaptive": 9.5,
5626
+ "text_reference_evaluation": 1.3,
5627
  "text_rendering": 1.2,
5628
  "visual_reference_evaluation": 6.3
5629
  },
public/data/leaderboard_by_stratum.json CHANGED
@@ -9,6 +9,7 @@
9
  "physical_plausibility": 558,
10
  "prompt_faithfulness": 751,
11
  "rubric_adaptive": 751,
 
12
  "text_rendering": 544,
13
  "visual_reference_evaluation": 599
14
  },
@@ -20,6 +21,7 @@
20
  "physical_plausibility": 76.7,
21
  "prompt_faithfulness": 69.4,
22
  "rubric_adaptive": 70.8,
 
23
  "text_rendering": 75.4,
24
  "visual_reference_evaluation": 65.7
25
  },
@@ -43,6 +45,7 @@
43
  "physical_plausibility": 627,
44
  "prompt_faithfulness": 751,
45
  "rubric_adaptive": 751,
 
46
  "text_rendering": 500,
47
  "visual_reference_evaluation": 598
48
  },
@@ -54,6 +57,7 @@
54
  "physical_plausibility": 78.4,
55
  "prompt_faithfulness": 62.3,
56
  "rubric_adaptive": 65.1,
 
57
  "text_rendering": 66.3,
58
  "visual_reference_evaluation": 59.8
59
  },
@@ -77,6 +81,7 @@
77
  "physical_plausibility": 539,
78
  "prompt_faithfulness": 717,
79
  "rubric_adaptive": 717,
 
80
  "text_rendering": 517,
81
  "visual_reference_evaluation": 582
82
  },
@@ -88,6 +93,7 @@
88
  "physical_plausibility": 73.1,
89
  "prompt_faithfulness": 62.0,
90
  "rubric_adaptive": 64.1,
 
91
  "text_rendering": 63.4,
92
  "visual_reference_evaluation": 58.9
93
  },
@@ -111,6 +117,7 @@
111
  "physical_plausibility": 544,
112
  "prompt_faithfulness": 742,
113
  "rubric_adaptive": 742,
 
114
  "text_rendering": 471,
115
  "visual_reference_evaluation": 606
116
  },
@@ -122,6 +129,7 @@
122
  "physical_plausibility": 71.7,
123
  "prompt_faithfulness": 50.0,
124
  "rubric_adaptive": 54.2,
 
125
  "text_rendering": 56.7,
126
  "visual_reference_evaluation": 46.2
127
  },
@@ -145,6 +153,7 @@
145
  "physical_plausibility": 561,
146
  "prompt_faithfulness": 751,
147
  "rubric_adaptive": 751,
 
148
  "text_rendering": 467,
149
  "visual_reference_evaluation": 617
150
  },
@@ -156,6 +165,7 @@
156
  "physical_plausibility": 67.9,
157
  "prompt_faithfulness": 47.3,
158
  "rubric_adaptive": 51.9,
 
159
  "text_rendering": 54.0,
160
  "visual_reference_evaluation": 43.2
161
  },
@@ -179,6 +189,7 @@
179
  "physical_plausibility": 593,
180
  "prompt_faithfulness": 751,
181
  "rubric_adaptive": 751,
 
182
  "text_rendering": 518,
183
  "visual_reference_evaluation": 615
184
  },
@@ -190,6 +201,7 @@
190
  "physical_plausibility": 64.0,
191
  "prompt_faithfulness": 45.9,
192
  "rubric_adaptive": 50.2,
 
193
  "text_rendering": 48.9,
194
  "visual_reference_evaluation": 39.9
195
  },
@@ -213,6 +225,7 @@
213
  "physical_plausibility": 604,
214
  "prompt_faithfulness": 750,
215
  "rubric_adaptive": 751,
 
216
  "text_rendering": 483,
217
  "visual_reference_evaluation": 596
218
  },
@@ -224,6 +237,7 @@
224
  "physical_plausibility": 65.6,
225
  "prompt_faithfulness": 41.6,
226
  "rubric_adaptive": 47.2,
 
227
  "text_rendering": 38.1,
228
  "visual_reference_evaluation": 38.4
229
  },
@@ -247,6 +261,7 @@
247
  "physical_plausibility": 594,
248
  "prompt_faithfulness": 751,
249
  "rubric_adaptive": 751,
 
250
  "text_rendering": 498,
251
  "visual_reference_evaluation": 597
252
  },
@@ -258,6 +273,7 @@
258
  "physical_plausibility": 66.0,
259
  "prompt_faithfulness": 39.1,
260
  "rubric_adaptive": 44.0,
 
261
  "text_rendering": 28.9,
262
  "visual_reference_evaluation": 36.4
263
  },
@@ -281,6 +297,7 @@
281
  "physical_plausibility": 676,
282
  "prompt_faithfulness": 751,
283
  "rubric_adaptive": 751,
 
284
  "text_rendering": 475,
285
  "visual_reference_evaluation": 595
286
  },
@@ -292,6 +309,7 @@
292
  "physical_plausibility": 48.6,
293
  "prompt_faithfulness": 24.5,
294
  "rubric_adaptive": 30.5,
 
295
  "text_rendering": 11.3,
296
  "visual_reference_evaluation": 23.8
297
  },
@@ -315,6 +333,7 @@
315
  "physical_plausibility": 599,
316
  "prompt_faithfulness": 751,
317
  "rubric_adaptive": 751,
 
318
  "text_rendering": 501,
319
  "visual_reference_evaluation": 596
320
  },
@@ -326,6 +345,7 @@
326
  "physical_plausibility": 51.5,
327
  "prompt_faithfulness": 21.7,
328
  "rubric_adaptive": 27.9,
 
329
  "text_rendering": 8.4,
330
  "visual_reference_evaluation": 21.1
331
  },
@@ -349,6 +369,7 @@
349
  "physical_plausibility": 597,
350
  "prompt_faithfulness": 750,
351
  "rubric_adaptive": 751,
 
352
  "text_rendering": 483,
353
  "visual_reference_evaluation": 594
354
  },
@@ -360,6 +381,7 @@
360
  "physical_plausibility": 49.0,
361
  "prompt_faithfulness": 16.0,
362
  "rubric_adaptive": 22.9,
 
363
  "text_rendering": 4.7,
364
  "visual_reference_evaluation": 15.1
365
  },
@@ -383,6 +405,7 @@
383
  "physical_plausibility": 631,
384
  "prompt_faithfulness": 751,
385
  "rubric_adaptive": 751,
 
386
  "text_rendering": 465,
387
  "visual_reference_evaluation": 595
388
  },
@@ -394,6 +417,7 @@
394
  "physical_plausibility": 40.4,
395
  "prompt_faithfulness": 16.7,
396
  "rubric_adaptive": 21.8,
 
397
  "text_rendering": 3.5,
398
  "visual_reference_evaluation": 16.8
399
  },
@@ -417,6 +441,7 @@
417
  "physical_plausibility": 656,
418
  "prompt_faithfulness": 751,
419
  "rubric_adaptive": 751,
 
420
  "text_rendering": 596,
421
  "visual_reference_evaluation": 688
422
  },
@@ -428,6 +453,7 @@
428
  "physical_plausibility": 20.0,
429
  "prompt_faithfulness": 6.0,
430
  "rubric_adaptive": 8.7,
 
431
  "text_rendering": 1.2,
432
  "visual_reference_evaluation": 6.0
433
  },
@@ -453,6 +479,7 @@
453
  "physical_plausibility": 94,
454
  "prompt_faithfulness": 100,
455
  "rubric_adaptive": 100,
 
456
  "text_rendering": 33,
457
  "visual_reference_evaluation": 92
458
  },
@@ -464,6 +491,7 @@
464
  "physical_plausibility": 78.2,
465
  "prompt_faithfulness": 72.8,
466
  "rubric_adaptive": 78.1,
 
467
  "text_rendering": 85.9,
468
  "visual_reference_evaluation": 67.8
469
  },
@@ -487,6 +515,7 @@
487
  "physical_plausibility": 95,
488
  "prompt_faithfulness": 100,
489
  "rubric_adaptive": 100,
 
490
  "text_rendering": 32,
491
  "visual_reference_evaluation": 93
492
  },
@@ -498,6 +527,7 @@
498
  "physical_plausibility": 73.9,
499
  "prompt_faithfulness": 70.8,
500
  "rubric_adaptive": 75.6,
 
501
  "text_rendering": 67.7,
502
  "visual_reference_evaluation": 64.3
503
  },
@@ -521,6 +551,7 @@
521
  "physical_plausibility": 90,
522
  "prompt_faithfulness": 97,
523
  "rubric_adaptive": 97,
 
524
  "text_rendering": 33,
525
  "visual_reference_evaluation": 89
526
  },
@@ -532,6 +563,7 @@
532
  "physical_plausibility": 70.9,
533
  "prompt_faithfulness": 69.2,
534
  "rubric_adaptive": 74.2,
 
535
  "text_rendering": 71.2,
536
  "visual_reference_evaluation": 61.9
537
  },
@@ -555,6 +587,7 @@
555
  "physical_plausibility": 96,
556
  "prompt_faithfulness": 100,
557
  "rubric_adaptive": 100,
 
558
  "text_rendering": 23,
559
  "visual_reference_evaluation": 92
560
  },
@@ -566,6 +599,7 @@
566
  "physical_plausibility": 72.0,
567
  "prompt_faithfulness": 66.3,
568
  "rubric_adaptive": 73.2,
 
569
  "text_rendering": 76.1,
570
  "visual_reference_evaluation": 59.4
571
  },
@@ -589,6 +623,7 @@
589
  "physical_plausibility": 96,
590
  "prompt_faithfulness": 100,
591
  "rubric_adaptive": 100,
 
592
  "text_rendering": 26,
593
  "visual_reference_evaluation": 91
594
  },
@@ -600,6 +635,7 @@
600
  "physical_plausibility": 71.5,
601
  "prompt_faithfulness": 63.2,
602
  "rubric_adaptive": 69.9,
 
603
  "text_rendering": 76.9,
604
  "visual_reference_evaluation": 60.1
605
  },
@@ -623,6 +659,7 @@
623
  "physical_plausibility": 95,
624
  "prompt_faithfulness": 100,
625
  "rubric_adaptive": 100,
 
626
  "text_rendering": 30,
627
  "visual_reference_evaluation": 92
628
  },
@@ -634,6 +671,7 @@
634
  "physical_plausibility": 73.9,
635
  "prompt_faithfulness": 61.7,
636
  "rubric_adaptive": 70.6,
 
637
  "text_rendering": 71.1,
638
  "visual_reference_evaluation": 56.7
639
  },
@@ -657,6 +695,7 @@
657
  "physical_plausibility": 93,
658
  "prompt_faithfulness": 100,
659
  "rubric_adaptive": 100,
 
660
  "text_rendering": 23,
661
  "visual_reference_evaluation": 92
662
  },
@@ -668,6 +707,7 @@
668
  "physical_plausibility": 73.8,
669
  "prompt_faithfulness": 62.8,
670
  "rubric_adaptive": 70.8,
 
671
  "text_rendering": 63.0,
672
  "visual_reference_evaluation": 56.7
673
  },
@@ -691,6 +731,7 @@
691
  "physical_plausibility": 96,
692
  "prompt_faithfulness": 100,
693
  "rubric_adaptive": 100,
 
694
  "text_rendering": 37,
695
  "visual_reference_evaluation": 92
696
  },
@@ -702,6 +743,7 @@
702
  "physical_plausibility": 71.4,
703
  "prompt_faithfulness": 64.5,
704
  "rubric_adaptive": 71.0,
 
705
  "text_rendering": 68.0,
706
  "visual_reference_evaluation": 55.8
707
  },
@@ -725,6 +767,7 @@
725
  "physical_plausibility": 92,
726
  "prompt_faithfulness": 100,
727
  "rubric_adaptive": 100,
 
728
  "text_rendering": 30,
729
  "visual_reference_evaluation": 92
730
  },
@@ -736,6 +779,7 @@
736
  "physical_plausibility": 68.5,
737
  "prompt_faithfulness": 59.7,
738
  "rubric_adaptive": 67.5,
 
739
  "text_rendering": 42.8,
740
  "visual_reference_evaluation": 53.8
741
  },
@@ -759,6 +803,7 @@
759
  "physical_plausibility": 96,
760
  "prompt_faithfulness": 100,
761
  "rubric_adaptive": 100,
 
762
  "text_rendering": 25,
763
  "visual_reference_evaluation": 92
764
  },
@@ -770,6 +815,7 @@
770
  "physical_plausibility": 66.7,
771
  "prompt_faithfulness": 51.3,
772
  "rubric_adaptive": 59.8,
 
773
  "text_rendering": 31.3,
774
  "visual_reference_evaluation": 43.7
775
  },
@@ -793,6 +839,7 @@
793
  "physical_plausibility": 95,
794
  "prompt_faithfulness": 100,
795
  "rubric_adaptive": 100,
 
796
  "text_rendering": 24,
797
  "visual_reference_evaluation": 92
798
  },
@@ -804,6 +851,7 @@
804
  "physical_plausibility": 63.5,
805
  "prompt_faithfulness": 39.3,
806
  "rubric_adaptive": 51.8,
 
807
  "text_rendering": 13.2,
808
  "visual_reference_evaluation": 32.6
809
  },
@@ -827,6 +875,7 @@
827
  "physical_plausibility": 95,
828
  "prompt_faithfulness": 100,
829
  "rubric_adaptive": 100,
 
830
  "text_rendering": 29,
831
  "visual_reference_evaluation": 92
832
  },
@@ -838,6 +887,7 @@
838
  "physical_plausibility": 60.4,
839
  "prompt_faithfulness": 39.2,
840
  "rubric_adaptive": 49.1,
 
841
  "text_rendering": 18.4,
842
  "visual_reference_evaluation": 34.8
843
  },
@@ -861,6 +911,7 @@
861
  "physical_plausibility": 100,
862
  "prompt_faithfulness": 100,
863
  "rubric_adaptive": 100,
 
864
  "text_rendering": 100,
865
  "visual_reference_evaluation": 100
866
  },
@@ -872,6 +923,7 @@
872
  "physical_plausibility": 0.0,
873
  "prompt_faithfulness": 0.0,
874
  "rubric_adaptive": 0.0,
 
875
  "text_rendering": 0.0,
876
  "visual_reference_evaluation": 0.0
877
  },
@@ -897,6 +949,7 @@
897
  "physical_plausibility": 463,
898
  "prompt_faithfulness": 651,
899
  "rubric_adaptive": 651,
 
900
  "text_rendering": 512,
901
  "visual_reference_evaluation": 506
902
  },
@@ -908,6 +961,7 @@
908
  "physical_plausibility": 77.3,
909
  "prompt_faithfulness": 69.2,
910
  "rubric_adaptive": 70.1,
 
911
  "text_rendering": 75.9,
912
  "visual_reference_evaluation": 66.0
913
  },
@@ -931,6 +985,7 @@
931
  "physical_plausibility": 533,
932
  "prompt_faithfulness": 651,
933
  "rubric_adaptive": 651,
 
934
  "text_rendering": 467,
935
  "visual_reference_evaluation": 506
936
  },
@@ -942,6 +997,7 @@
942
  "physical_plausibility": 78.5,
943
  "prompt_faithfulness": 60.7,
944
  "rubric_adaptive": 63.1,
 
945
  "text_rendering": 65.0,
946
  "visual_reference_evaluation": 58.3
947
  },
@@ -965,6 +1021,7 @@
965
  "physical_plausibility": 449,
966
  "prompt_faithfulness": 620,
967
  "rubric_adaptive": 620,
 
968
  "text_rendering": 484,
969
  "visual_reference_evaluation": 493
970
  },
@@ -976,6 +1033,7 @@
976
  "physical_plausibility": 73.6,
977
  "prompt_faithfulness": 60.8,
978
  "rubric_adaptive": 62.5,
 
979
  "text_rendering": 62.8,
980
  "visual_reference_evaluation": 58.3
981
  },
@@ -999,6 +1057,7 @@
999
  "physical_plausibility": 448,
1000
  "prompt_faithfulness": 642,
1001
  "rubric_adaptive": 642,
 
1002
  "text_rendering": 445,
1003
  "visual_reference_evaluation": 515
1004
  },
@@ -1010,6 +1069,7 @@
1010
  "physical_plausibility": 71.8,
1011
  "prompt_faithfulness": 47.9,
1012
  "rubric_adaptive": 51.8,
 
1013
  "text_rendering": 55.5,
1014
  "visual_reference_evaluation": 43.8
1015
  },
@@ -1033,6 +1093,7 @@
1033
  "physical_plausibility": 465,
1034
  "prompt_faithfulness": 651,
1035
  "rubric_adaptive": 651,
 
1036
  "text_rendering": 444,
1037
  "visual_reference_evaluation": 525
1038
  },
@@ -1044,6 +1105,7 @@
1044
  "physical_plausibility": 67.1,
1045
  "prompt_faithfulness": 44.4,
1046
  "rubric_adaptive": 48.7,
 
1047
  "text_rendering": 52.9,
1048
  "visual_reference_evaluation": 40.3
1049
  },
@@ -1067,6 +1129,7 @@
1067
  "physical_plausibility": 497,
1068
  "prompt_faithfulness": 651,
1069
  "rubric_adaptive": 651,
 
1070
  "text_rendering": 481,
1071
  "visual_reference_evaluation": 523
1072
  },
@@ -1078,6 +1141,7 @@
1078
  "physical_plausibility": 62.6,
1079
  "prompt_faithfulness": 43.1,
1080
  "rubric_adaptive": 47.0,
 
1081
  "text_rendering": 47.5,
1082
  "visual_reference_evaluation": 37.1
1083
  },
@@ -1101,6 +1165,7 @@
1101
  "physical_plausibility": 509,
1102
  "prompt_faithfulness": 650,
1103
  "rubric_adaptive": 651,
 
1104
  "text_rendering": 453,
1105
  "visual_reference_evaluation": 504
1106
  },
@@ -1112,6 +1177,7 @@
1112
  "physical_plausibility": 64.0,
1113
  "prompt_faithfulness": 38.5,
1114
  "rubric_adaptive": 43.6,
 
1115
  "text_rendering": 35.9,
1116
  "visual_reference_evaluation": 35.1
1117
  },
@@ -1135,6 +1201,7 @@
1135
  "physical_plausibility": 502,
1136
  "prompt_faithfulness": 651,
1137
  "rubric_adaptive": 651,
 
1138
  "text_rendering": 468,
1139
  "visual_reference_evaluation": 505
1140
  },
@@ -1146,6 +1213,7 @@
1146
  "physical_plausibility": 65.5,
1147
  "prompt_faithfulness": 36.0,
1148
  "rubric_adaptive": 40.4,
 
1149
  "text_rendering": 28.0,
1150
  "visual_reference_evaluation": 33.2
1151
  },
@@ -1169,6 +1237,7 @@
1169
  "physical_plausibility": 583,
1170
  "prompt_faithfulness": 651,
1171
  "rubric_adaptive": 651,
 
1172
  "text_rendering": 452,
1173
  "visual_reference_evaluation": 503
1174
  },
@@ -1180,6 +1249,7 @@
1180
  "physical_plausibility": 44.6,
1181
  "prompt_faithfulness": 18.6,
1182
  "rubric_adaptive": 24.3,
 
1183
  "text_rendering": 8.7,
1184
  "visual_reference_evaluation": 17.7
1185
  },
@@ -1203,6 +1273,7 @@
1203
  "physical_plausibility": 503,
1204
  "prompt_faithfulness": 651,
1205
  "rubric_adaptive": 651,
 
1206
  "text_rendering": 476,
1207
  "visual_reference_evaluation": 504
1208
  },
@@ -1214,6 +1285,7 @@
1214
  "physical_plausibility": 48.6,
1215
  "prompt_faithfulness": 17.2,
1216
  "rubric_adaptive": 23.1,
 
1217
  "text_rendering": 7.2,
1218
  "visual_reference_evaluation": 16.9
1219
  },
@@ -1237,6 +1309,7 @@
1237
  "physical_plausibility": 502,
1238
  "prompt_faithfulness": 650,
1239
  "rubric_adaptive": 651,
 
1240
  "text_rendering": 459,
1241
  "visual_reference_evaluation": 502
1242
  },
@@ -1248,6 +1321,7 @@
1248
  "physical_plausibility": 46.2,
1249
  "prompt_faithfulness": 12.4,
1250
  "rubric_adaptive": 18.4,
 
1251
  "text_rendering": 4.2,
1252
  "visual_reference_evaluation": 11.9
1253
  },
@@ -1271,6 +1345,7 @@
1271
  "physical_plausibility": 536,
1272
  "prompt_faithfulness": 651,
1273
  "rubric_adaptive": 651,
 
1274
  "text_rendering": 436,
1275
  "visual_reference_evaluation": 503
1276
  },
@@ -1282,6 +1357,7 @@
1282
  "physical_plausibility": 36.8,
1283
  "prompt_faithfulness": 13.3,
1284
  "rubric_adaptive": 17.6,
 
1285
  "text_rendering": 2.5,
1286
  "visual_reference_evaluation": 13.5
1287
  },
@@ -1305,6 +1381,7 @@
1305
  "physical_plausibility": 556,
1306
  "prompt_faithfulness": 651,
1307
  "rubric_adaptive": 651,
 
1308
  "text_rendering": 496,
1309
  "visual_reference_evaluation": 588
1310
  },
@@ -1316,6 +1393,7 @@
1316
  "physical_plausibility": 23.7,
1317
  "prompt_faithfulness": 6.9,
1318
  "rubric_adaptive": 10.0,
 
1319
  "text_rendering": 1.4,
1320
  "visual_reference_evaluation": 7.0
1321
  },
@@ -1341,6 +1419,7 @@
1341
  "physical_plausibility": 158,
1342
  "prompt_faithfulness": 264,
1343
  "rubric_adaptive": 264,
 
1344
  "text_rendering": 252,
1345
  "visual_reference_evaluation": 173
1346
  },
@@ -1352,6 +1431,7 @@
1352
  "physical_plausibility": 89.1,
1353
  "prompt_faithfulness": 69.3,
1354
  "rubric_adaptive": 67.8,
 
1355
  "text_rendering": 70.1,
1356
  "visual_reference_evaluation": 66.7
1357
  },
@@ -1375,6 +1455,7 @@
1375
  "physical_plausibility": 214,
1376
  "prompt_faithfulness": 264,
1377
  "rubric_adaptive": 264,
 
1378
  "text_rendering": 244,
1379
  "visual_reference_evaluation": 173
1380
  },
@@ -1386,6 +1467,7 @@
1386
  "physical_plausibility": 86.2,
1387
  "prompt_faithfulness": 60.1,
1388
  "rubric_adaptive": 59.8,
 
1389
  "text_rendering": 59.6,
1390
  "visual_reference_evaluation": 54.4
1391
  },
@@ -1409,6 +1491,7 @@
1409
  "physical_plausibility": 171,
1410
  "prompt_faithfulness": 264,
1411
  "rubric_adaptive": 264,
 
1412
  "text_rendering": 248,
1413
  "visual_reference_evaluation": 172
1414
  },
@@ -1420,6 +1503,7 @@
1420
  "physical_plausibility": 85.0,
1421
  "prompt_faithfulness": 60.9,
1422
  "rubric_adaptive": 59.3,
 
1423
  "text_rendering": 57.0,
1424
  "visual_reference_evaluation": 54.8
1425
  },
@@ -1443,6 +1527,7 @@
1443
  "physical_plausibility": 155,
1444
  "prompt_faithfulness": 264,
1445
  "rubric_adaptive": 264,
 
1446
  "text_rendering": 249,
1447
  "visual_reference_evaluation": 172
1448
  },
@@ -1454,6 +1539,7 @@
1454
  "physical_plausibility": 83.1,
1455
  "prompt_faithfulness": 48.0,
1456
  "rubric_adaptive": 48.5,
 
1457
  "text_rendering": 47.3,
1458
  "visual_reference_evaluation": 37.1
1459
  },
@@ -1477,6 +1563,7 @@
1477
  "physical_plausibility": 157,
1478
  "prompt_faithfulness": 264,
1479
  "rubric_adaptive": 264,
 
1480
  "text_rendering": 244,
1481
  "visual_reference_evaluation": 172
1482
  },
@@ -1488,6 +1575,7 @@
1488
  "physical_plausibility": 80.4,
1489
  "prompt_faithfulness": 45.0,
1490
  "rubric_adaptive": 46.4,
 
1491
  "text_rendering": 45.4,
1492
  "visual_reference_evaluation": 34.4
1493
  },
@@ -1511,6 +1599,7 @@
1511
  "physical_plausibility": 189,
1512
  "prompt_faithfulness": 264,
1513
  "rubric_adaptive": 264,
 
1514
  "text_rendering": 256,
1515
  "visual_reference_evaluation": 172
1516
  },
@@ -1522,6 +1611,7 @@
1522
  "physical_plausibility": 69.6,
1523
  "prompt_faithfulness": 40.5,
1524
  "rubric_adaptive": 42.2,
 
1525
  "text_rendering": 41.4,
1526
  "visual_reference_evaluation": 27.2
1527
  },
@@ -1545,6 +1635,7 @@
1545
  "physical_plausibility": 197,
1546
  "prompt_faithfulness": 264,
1547
  "rubric_adaptive": 264,
 
1548
  "text_rendering": 250,
1549
  "visual_reference_evaluation": 172
1550
  },
@@ -1556,6 +1647,7 @@
1556
  "physical_plausibility": 72.3,
1557
  "prompt_faithfulness": 33.6,
1558
  "rubric_adaptive": 36.7,
 
1559
  "text_rendering": 30.1,
1560
  "visual_reference_evaluation": 24.0
1561
  },
@@ -1579,6 +1671,7 @@
1579
  "physical_plausibility": 188,
1580
  "prompt_faithfulness": 264,
1581
  "rubric_adaptive": 264,
 
1582
  "text_rendering": 254,
1583
  "visual_reference_evaluation": 172
1584
  },
@@ -1590,6 +1683,7 @@
1590
  "physical_plausibility": 75.5,
1591
  "prompt_faithfulness": 32.5,
1592
  "rubric_adaptive": 33.7,
 
1593
  "text_rendering": 22.1,
1594
  "visual_reference_evaluation": 25.0
1595
  },
@@ -1613,6 +1707,7 @@
1613
  "physical_plausibility": 233,
1614
  "prompt_faithfulness": 264,
1615
  "rubric_adaptive": 264,
 
1616
  "text_rendering": 253,
1617
  "visual_reference_evaluation": 172
1618
  },
@@ -1624,6 +1719,7 @@
1624
  "physical_plausibility": 44.3,
1625
  "prompt_faithfulness": 13.8,
1626
  "rubric_adaptive": 17.5,
 
1627
  "text_rendering": 5.4,
1628
  "visual_reference_evaluation": 10.4
1629
  },
@@ -1647,6 +1743,7 @@
1647
  "physical_plausibility": 198,
1648
  "prompt_faithfulness": 264,
1649
  "rubric_adaptive": 264,
 
1650
  "text_rendering": 254,
1651
  "visual_reference_evaluation": 172
1652
  },
@@ -1658,6 +1755,7 @@
1658
  "physical_plausibility": 48.7,
1659
  "prompt_faithfulness": 12.4,
1660
  "rubric_adaptive": 16.2,
 
1661
  "text_rendering": 3.9,
1662
  "visual_reference_evaluation": 9.9
1663
  },
@@ -1681,6 +1779,7 @@
1681
  "physical_plausibility": 201,
1682
  "prompt_faithfulness": 263,
1683
  "rubric_adaptive": 264,
 
1684
  "text_rendering": 249,
1685
  "visual_reference_evaluation": 171
1686
  },
@@ -1692,6 +1791,7 @@
1692
  "physical_plausibility": 44.6,
1693
  "prompt_faithfulness": 9.1,
1694
  "rubric_adaptive": 13.6,
 
1695
  "text_rendering": 2.8,
1696
  "visual_reference_evaluation": 7.2
1697
  },
@@ -1715,6 +1815,7 @@
1715
  "physical_plausibility": 203,
1716
  "prompt_faithfulness": 264,
1717
  "rubric_adaptive": 264,
 
1718
  "text_rendering": 244,
1719
  "visual_reference_evaluation": 172
1720
  },
@@ -1726,6 +1827,7 @@
1726
  "physical_plausibility": 37.8,
1727
  "prompt_faithfulness": 9.9,
1728
  "rubric_adaptive": 12.4,
 
1729
  "text_rendering": 1.6,
1730
  "visual_reference_evaluation": 9.3
1731
  },
@@ -1749,6 +1851,7 @@
1749
  "physical_plausibility": 216,
1750
  "prompt_faithfulness": 264,
1751
  "rubric_adaptive": 264,
 
1752
  "text_rendering": 249,
1753
  "visual_reference_evaluation": 239
1754
  },
@@ -1760,6 +1863,7 @@
1760
  "physical_plausibility": 8.1,
1761
  "prompt_faithfulness": 0.6,
1762
  "rubric_adaptive": 1.7,
 
1763
  "text_rendering": 0.0,
1764
  "visual_reference_evaluation": 0.1
1765
  },
@@ -1785,6 +1889,7 @@
1785
  "physical_plausibility": 305,
1786
  "prompt_faithfulness": 387,
1787
  "rubric_adaptive": 387,
 
1788
  "text_rendering": 260,
1789
  "visual_reference_evaluation": 333
1790
  },
@@ -1796,6 +1901,7 @@
1796
  "physical_plausibility": 71.2,
1797
  "prompt_faithfulness": 69.2,
1798
  "rubric_adaptive": 71.7,
 
1799
  "text_rendering": 81.5,
1800
  "visual_reference_evaluation": 65.7
1801
  },
@@ -1819,6 +1925,7 @@
1819
  "physical_plausibility": 319,
1820
  "prompt_faithfulness": 387,
1821
  "rubric_adaptive": 387,
 
1822
  "text_rendering": 223,
1823
  "visual_reference_evaluation": 333
1824
  },
@@ -1830,6 +1937,7 @@
1830
  "physical_plausibility": 73.3,
1831
  "prompt_faithfulness": 61.1,
1832
  "rubric_adaptive": 65.4,
 
1833
  "text_rendering": 70.8,
1834
  "visual_reference_evaluation": 60.4
1835
  },
@@ -1853,6 +1961,7 @@
1853
  "physical_plausibility": 278,
1854
  "prompt_faithfulness": 356,
1855
  "rubric_adaptive": 356,
 
1856
  "text_rendering": 236,
1857
  "visual_reference_evaluation": 321
1858
  },
@@ -1864,6 +1973,7 @@
1864
  "physical_plausibility": 66.5,
1865
  "prompt_faithfulness": 60.8,
1866
  "rubric_adaptive": 64.9,
 
1867
  "text_rendering": 69.0,
1868
  "visual_reference_evaluation": 60.2
1869
  },
@@ -1887,6 +1997,7 @@
1887
  "physical_plausibility": 293,
1888
  "prompt_faithfulness": 378,
1889
  "rubric_adaptive": 378,
 
1890
  "text_rendering": 196,
1891
  "visual_reference_evaluation": 343
1892
  },
@@ -1898,6 +2009,7 @@
1898
  "physical_plausibility": 65.8,
1899
  "prompt_faithfulness": 47.9,
1900
  "rubric_adaptive": 54.1,
 
1901
  "text_rendering": 66.0,
1902
  "visual_reference_evaluation": 47.2
1903
  },
@@ -1921,6 +2033,7 @@
1921
  "physical_plausibility": 308,
1922
  "prompt_faithfulness": 387,
1923
  "rubric_adaptive": 387,
 
1924
  "text_rendering": 200,
1925
  "visual_reference_evaluation": 353
1926
  },
@@ -1932,6 +2045,7 @@
1932
  "physical_plausibility": 60.3,
1933
  "prompt_faithfulness": 44.0,
1934
  "rubric_adaptive": 50.2,
 
1935
  "text_rendering": 62.0,
1936
  "visual_reference_evaluation": 43.2
1937
  },
@@ -1955,6 +2069,7 @@
1955
  "physical_plausibility": 308,
1956
  "prompt_faithfulness": 387,
1957
  "rubric_adaptive": 387,
 
1958
  "text_rendering": 225,
1959
  "visual_reference_evaluation": 351
1960
  },
@@ -1966,6 +2081,7 @@
1966
  "physical_plausibility": 58.3,
1967
  "prompt_faithfulness": 44.8,
1968
  "rubric_adaptive": 50.3,
 
1969
  "text_rendering": 54.4,
1970
  "visual_reference_evaluation": 41.9
1971
  },
@@ -1989,6 +2105,7 @@
1989
  "physical_plausibility": 312,
1990
  "prompt_faithfulness": 386,
1991
  "rubric_adaptive": 387,
 
1992
  "text_rendering": 203,
1993
  "visual_reference_evaluation": 332
1994
  },
@@ -2000,6 +2117,7 @@
2000
  "physical_plausibility": 58.8,
2001
  "prompt_faithfulness": 41.9,
2002
  "rubric_adaptive": 48.3,
 
2003
  "text_rendering": 43.2,
2004
  "visual_reference_evaluation": 40.8
2005
  },
@@ -2023,6 +2141,7 @@
2023
  "physical_plausibility": 314,
2024
  "prompt_faithfulness": 387,
2025
  "rubric_adaptive": 387,
 
2026
  "text_rendering": 214,
2027
  "visual_reference_evaluation": 333
2028
  },
@@ -2034,6 +2153,7 @@
2034
  "physical_plausibility": 59.5,
2035
  "prompt_faithfulness": 38.4,
2036
  "rubric_adaptive": 45.0,
 
2037
  "text_rendering": 35.0,
2038
  "visual_reference_evaluation": 37.4
2039
  },
@@ -2057,6 +2177,7 @@
2057
  "physical_plausibility": 350,
2058
  "prompt_faithfulness": 387,
2059
  "rubric_adaptive": 387,
 
2060
  "text_rendering": 199,
2061
  "visual_reference_evaluation": 331
2062
  },
@@ -2068,6 +2189,7 @@
2068
  "physical_plausibility": 44.8,
2069
  "prompt_faithfulness": 21.9,
2070
  "rubric_adaptive": 29.0,
 
2071
  "text_rendering": 12.8,
2072
  "visual_reference_evaluation": 21.6
2073
  },
@@ -2091,6 +2213,7 @@
2091
  "physical_plausibility": 305,
2092
  "prompt_faithfulness": 387,
2093
  "rubric_adaptive": 387,
 
2094
  "text_rendering": 222,
2095
  "visual_reference_evaluation": 332
2096
  },
@@ -2102,6 +2225,7 @@
2102
  "physical_plausibility": 48.5,
2103
  "prompt_faithfulness": 20.4,
2104
  "rubric_adaptive": 27.7,
 
2105
  "text_rendering": 11.0,
2106
  "visual_reference_evaluation": 20.6
2107
  },
@@ -2125,6 +2249,7 @@
2125
  "physical_plausibility": 301,
2126
  "prompt_faithfulness": 387,
2127
  "rubric_adaptive": 387,
 
2128
  "text_rendering": 210,
2129
  "visual_reference_evaluation": 331
2130
  },
@@ -2136,6 +2261,7 @@
2136
  "physical_plausibility": 47.3,
2137
  "prompt_faithfulness": 14.7,
2138
  "rubric_adaptive": 21.7,
 
2139
  "text_rendering": 6.0,
2140
  "visual_reference_evaluation": 14.3
2141
  },
@@ -2159,6 +2285,7 @@
2159
  "physical_plausibility": 333,
2160
  "prompt_faithfulness": 387,
2161
  "rubric_adaptive": 387,
 
2162
  "text_rendering": 192,
2163
  "visual_reference_evaluation": 331
2164
  },
@@ -2170,6 +2297,7 @@
2170
  "physical_plausibility": 36.2,
2171
  "prompt_faithfulness": 15.5,
2172
  "rubric_adaptive": 21.2,
 
2173
  "text_rendering": 3.6,
2174
  "visual_reference_evaluation": 15.7
2175
  },
@@ -2193,6 +2321,7 @@
2193
  "physical_plausibility": 340,
2194
  "prompt_faithfulness": 387,
2195
  "rubric_adaptive": 387,
 
2196
  "text_rendering": 247,
2197
  "visual_reference_evaluation": 349
2198
  },
@@ -2204,6 +2333,7 @@
2204
  "physical_plausibility": 33.5,
2205
  "prompt_faithfulness": 11.2,
2206
  "rubric_adaptive": 15.7,
 
2207
  "text_rendering": 2.8,
2208
  "visual_reference_evaluation": 11.7
2209
  },
 
9
  "physical_plausibility": 558,
10
  "prompt_faithfulness": 751,
11
  "rubric_adaptive": 751,
12
+ "text_reference_evaluation": 486,
13
  "text_rendering": 544,
14
  "visual_reference_evaluation": 599
15
  },
 
21
  "physical_plausibility": 76.7,
22
  "prompt_faithfulness": 69.4,
23
  "rubric_adaptive": 70.8,
24
+ "text_reference_evaluation": 54.6,
25
  "text_rendering": 75.4,
26
  "visual_reference_evaluation": 65.7
27
  },
 
45
  "physical_plausibility": 627,
46
  "prompt_faithfulness": 751,
47
  "rubric_adaptive": 751,
48
+ "text_reference_evaluation": 480,
49
  "text_rendering": 500,
50
  "visual_reference_evaluation": 598
51
  },
 
57
  "physical_plausibility": 78.4,
58
  "prompt_faithfulness": 62.3,
59
  "rubric_adaptive": 65.1,
60
+ "text_reference_evaluation": 47.4,
61
  "text_rendering": 66.3,
62
  "visual_reference_evaluation": 59.8
63
  },
 
81
  "physical_plausibility": 539,
82
  "prompt_faithfulness": 717,
83
  "rubric_adaptive": 717,
84
+ "text_reference_evaluation": 487,
85
  "text_rendering": 517,
86
  "visual_reference_evaluation": 582
87
  },
 
93
  "physical_plausibility": 73.1,
94
  "prompt_faithfulness": 62.0,
95
  "rubric_adaptive": 64.1,
96
+ "text_reference_evaluation": 46.0,
97
  "text_rendering": 63.4,
98
  "visual_reference_evaluation": 58.9
99
  },
 
117
  "physical_plausibility": 544,
118
  "prompt_faithfulness": 742,
119
  "rubric_adaptive": 742,
120
+ "text_reference_evaluation": 473,
121
  "text_rendering": 471,
122
  "visual_reference_evaluation": 606
123
  },
 
129
  "physical_plausibility": 71.7,
130
  "prompt_faithfulness": 50.0,
131
  "rubric_adaptive": 54.2,
132
+ "text_reference_evaluation": 35.7,
133
  "text_rendering": 56.7,
134
  "visual_reference_evaluation": 46.2
135
  },
 
153
  "physical_plausibility": 561,
154
  "prompt_faithfulness": 751,
155
  "rubric_adaptive": 751,
156
+ "text_reference_evaluation": 492,
157
  "text_rendering": 467,
158
  "visual_reference_evaluation": 617
159
  },
 
165
  "physical_plausibility": 67.9,
166
  "prompt_faithfulness": 47.3,
167
  "rubric_adaptive": 51.9,
168
+ "text_reference_evaluation": 33.1,
169
  "text_rendering": 54.0,
170
  "visual_reference_evaluation": 43.2
171
  },
 
189
  "physical_plausibility": 593,
190
  "prompt_faithfulness": 751,
191
  "rubric_adaptive": 751,
192
+ "text_reference_evaluation": 486,
193
  "text_rendering": 518,
194
  "visual_reference_evaluation": 615
195
  },
 
201
  "physical_plausibility": 64.0,
202
  "prompt_faithfulness": 45.9,
203
  "rubric_adaptive": 50.2,
204
+ "text_reference_evaluation": 28.2,
205
  "text_rendering": 48.9,
206
  "visual_reference_evaluation": 39.9
207
  },
 
225
  "physical_plausibility": 604,
226
  "prompt_faithfulness": 750,
227
  "rubric_adaptive": 751,
228
+ "text_reference_evaluation": 501,
229
  "text_rendering": 483,
230
  "visual_reference_evaluation": 596
231
  },
 
237
  "physical_plausibility": 65.6,
238
  "prompt_faithfulness": 41.6,
239
  "rubric_adaptive": 47.2,
240
+ "text_reference_evaluation": 23.4,
241
  "text_rendering": 38.1,
242
  "visual_reference_evaluation": 38.4
243
  },
 
261
  "physical_plausibility": 594,
262
  "prompt_faithfulness": 751,
263
  "rubric_adaptive": 751,
264
+ "text_reference_evaluation": 522,
265
  "text_rendering": 498,
266
  "visual_reference_evaluation": 597
267
  },
 
273
  "physical_plausibility": 66.0,
274
  "prompt_faithfulness": 39.1,
275
  "rubric_adaptive": 44.0,
276
+ "text_reference_evaluation": 17.8,
277
  "text_rendering": 28.9,
278
  "visual_reference_evaluation": 36.4
279
  },
 
297
  "physical_plausibility": 676,
298
  "prompt_faithfulness": 751,
299
  "rubric_adaptive": 751,
300
+ "text_reference_evaluation": 516,
301
  "text_rendering": 475,
302
  "visual_reference_evaluation": 595
303
  },
 
309
  "physical_plausibility": 48.6,
310
  "prompt_faithfulness": 24.5,
311
  "rubric_adaptive": 30.5,
312
+ "text_reference_evaluation": 7.7,
313
  "text_rendering": 11.3,
314
  "visual_reference_evaluation": 23.8
315
  },
 
333
  "physical_plausibility": 599,
334
  "prompt_faithfulness": 751,
335
  "rubric_adaptive": 751,
336
+ "text_reference_evaluation": 536,
337
  "text_rendering": 501,
338
  "visual_reference_evaluation": 596
339
  },
 
345
  "physical_plausibility": 51.5,
346
  "prompt_faithfulness": 21.7,
347
  "rubric_adaptive": 27.9,
348
+ "text_reference_evaluation": 6.6,
349
  "text_rendering": 8.4,
350
  "visual_reference_evaluation": 21.1
351
  },
 
369
  "physical_plausibility": 597,
370
  "prompt_faithfulness": 750,
371
  "rubric_adaptive": 751,
372
+ "text_reference_evaluation": 537,
373
  "text_rendering": 483,
374
  "visual_reference_evaluation": 594
375
  },
 
381
  "physical_plausibility": 49.0,
382
  "prompt_faithfulness": 16.0,
383
  "rubric_adaptive": 22.9,
384
+ "text_reference_evaluation": 3.6,
385
  "text_rendering": 4.7,
386
  "visual_reference_evaluation": 15.1
387
  },
 
405
  "physical_plausibility": 631,
406
  "prompt_faithfulness": 751,
407
  "rubric_adaptive": 751,
408
+ "text_reference_evaluation": 521,
409
  "text_rendering": 465,
410
  "visual_reference_evaluation": 595
411
  },
 
417
  "physical_plausibility": 40.4,
418
  "prompt_faithfulness": 16.7,
419
  "rubric_adaptive": 21.8,
420
+ "text_reference_evaluation": 3.5,
421
  "text_rendering": 3.5,
422
  "visual_reference_evaluation": 16.8
423
  },
 
441
  "physical_plausibility": 656,
442
  "prompt_faithfulness": 751,
443
  "rubric_adaptive": 751,
444
+ "text_reference_evaluation": 630,
445
  "text_rendering": 596,
446
  "visual_reference_evaluation": 688
447
  },
 
453
  "physical_plausibility": 20.0,
454
  "prompt_faithfulness": 6.0,
455
  "rubric_adaptive": 8.7,
456
+ "text_reference_evaluation": 1.2,
457
  "text_rendering": 1.2,
458
  "visual_reference_evaluation": 6.0
459
  },
 
479
  "physical_plausibility": 94,
480
  "prompt_faithfulness": 100,
481
  "rubric_adaptive": 100,
482
+ "text_reference_evaluation": 35,
483
  "text_rendering": 33,
484
  "visual_reference_evaluation": 92
485
  },
 
491
  "physical_plausibility": 78.2,
492
  "prompt_faithfulness": 72.8,
493
  "rubric_adaptive": 78.1,
494
+ "text_reference_evaluation": 59.5,
495
  "text_rendering": 85.9,
496
  "visual_reference_evaluation": 67.8
497
  },
 
515
  "physical_plausibility": 95,
516
  "prompt_faithfulness": 100,
517
  "rubric_adaptive": 100,
518
+ "text_reference_evaluation": 38,
519
  "text_rendering": 32,
520
  "visual_reference_evaluation": 93
521
  },
 
527
  "physical_plausibility": 73.9,
528
  "prompt_faithfulness": 70.8,
529
  "rubric_adaptive": 75.6,
530
+ "text_reference_evaluation": 48.2,
531
  "text_rendering": 67.7,
532
  "visual_reference_evaluation": 64.3
533
  },
 
551
  "physical_plausibility": 90,
552
  "prompt_faithfulness": 97,
553
  "rubric_adaptive": 97,
554
+ "text_reference_evaluation": 33,
555
  "text_rendering": 33,
556
  "visual_reference_evaluation": 89
557
  },
 
563
  "physical_plausibility": 70.9,
564
  "prompt_faithfulness": 69.2,
565
  "rubric_adaptive": 74.2,
566
+ "text_reference_evaluation": 47.0,
567
  "text_rendering": 71.2,
568
  "visual_reference_evaluation": 61.9
569
  },
 
587
  "physical_plausibility": 96,
588
  "prompt_faithfulness": 100,
589
  "rubric_adaptive": 100,
590
+ "text_reference_evaluation": 34,
591
  "text_rendering": 23,
592
  "visual_reference_evaluation": 92
593
  },
 
599
  "physical_plausibility": 72.0,
600
  "prompt_faithfulness": 66.3,
601
  "rubric_adaptive": 73.2,
602
+ "text_reference_evaluation": 45.1,
603
  "text_rendering": 76.1,
604
  "visual_reference_evaluation": 59.4
605
  },
 
623
  "physical_plausibility": 96,
624
  "prompt_faithfulness": 100,
625
  "rubric_adaptive": 100,
626
+ "text_reference_evaluation": 37,
627
  "text_rendering": 26,
628
  "visual_reference_evaluation": 91
629
  },
 
635
  "physical_plausibility": 71.5,
636
  "prompt_faithfulness": 63.2,
637
  "rubric_adaptive": 69.9,
638
+ "text_reference_evaluation": 47.7,
639
  "text_rendering": 76.9,
640
  "visual_reference_evaluation": 60.1
641
  },
 
659
  "physical_plausibility": 95,
660
  "prompt_faithfulness": 100,
661
  "rubric_adaptive": 100,
662
+ "text_reference_evaluation": 38,
663
  "text_rendering": 30,
664
  "visual_reference_evaluation": 92
665
  },
 
671
  "physical_plausibility": 73.9,
672
  "prompt_faithfulness": 61.7,
673
  "rubric_adaptive": 70.6,
674
+ "text_reference_evaluation": 45.2,
675
  "text_rendering": 71.1,
676
  "visual_reference_evaluation": 56.7
677
  },
 
695
  "physical_plausibility": 93,
696
  "prompt_faithfulness": 100,
697
  "rubric_adaptive": 100,
698
+ "text_reference_evaluation": 38,
699
  "text_rendering": 23,
700
  "visual_reference_evaluation": 92
701
  },
 
707
  "physical_plausibility": 73.8,
708
  "prompt_faithfulness": 62.8,
709
  "rubric_adaptive": 70.8,
710
+ "text_reference_evaluation": 41.2,
711
  "text_rendering": 63.0,
712
  "visual_reference_evaluation": 56.7
713
  },
 
731
  "physical_plausibility": 96,
732
  "prompt_faithfulness": 100,
733
  "rubric_adaptive": 100,
734
+ "text_reference_evaluation": 35,
735
  "text_rendering": 37,
736
  "visual_reference_evaluation": 92
737
  },
 
743
  "physical_plausibility": 71.4,
744
  "prompt_faithfulness": 64.5,
745
  "rubric_adaptive": 71.0,
746
+ "text_reference_evaluation": 43.3,
747
  "text_rendering": 68.0,
748
  "visual_reference_evaluation": 55.8
749
  },
 
767
  "physical_plausibility": 92,
768
  "prompt_faithfulness": 100,
769
  "rubric_adaptive": 100,
770
+ "text_reference_evaluation": 40,
771
  "text_rendering": 30,
772
  "visual_reference_evaluation": 92
773
  },
 
779
  "physical_plausibility": 68.5,
780
  "prompt_faithfulness": 59.7,
781
  "rubric_adaptive": 67.5,
782
+ "text_reference_evaluation": 26.2,
783
  "text_rendering": 42.8,
784
  "visual_reference_evaluation": 53.8
785
  },
 
803
  "physical_plausibility": 96,
804
  "prompt_faithfulness": 100,
805
  "rubric_adaptive": 100,
806
+ "text_reference_evaluation": 42,
807
  "text_rendering": 25,
808
  "visual_reference_evaluation": 92
809
  },
 
815
  "physical_plausibility": 66.7,
816
  "prompt_faithfulness": 51.3,
817
  "rubric_adaptive": 59.8,
818
+ "text_reference_evaluation": 22.2,
819
  "text_rendering": 31.3,
820
  "visual_reference_evaluation": 43.7
821
  },
 
839
  "physical_plausibility": 95,
840
  "prompt_faithfulness": 100,
841
  "rubric_adaptive": 100,
842
+ "text_reference_evaluation": 40,
843
  "text_rendering": 24,
844
  "visual_reference_evaluation": 92
845
  },
 
851
  "physical_plausibility": 63.5,
852
  "prompt_faithfulness": 39.3,
853
  "rubric_adaptive": 51.8,
854
+ "text_reference_evaluation": 19.6,
855
  "text_rendering": 13.2,
856
  "visual_reference_evaluation": 32.6
857
  },
 
875
  "physical_plausibility": 95,
876
  "prompt_faithfulness": 100,
877
  "rubric_adaptive": 100,
878
+ "text_reference_evaluation": 42,
879
  "text_rendering": 29,
880
  "visual_reference_evaluation": 92
881
  },
 
887
  "physical_plausibility": 60.4,
888
  "prompt_faithfulness": 39.2,
889
  "rubric_adaptive": 49.1,
890
+ "text_reference_evaluation": 21.4,
891
  "text_rendering": 18.4,
892
  "visual_reference_evaluation": 34.8
893
  },
 
911
  "physical_plausibility": 100,
912
  "prompt_faithfulness": 100,
913
  "rubric_adaptive": 100,
914
+ "text_reference_evaluation": 100,
915
  "text_rendering": 100,
916
  "visual_reference_evaluation": 100
917
  },
 
923
  "physical_plausibility": 0.0,
924
  "prompt_faithfulness": 0.0,
925
  "rubric_adaptive": 0.0,
926
+ "text_reference_evaluation": 0.0,
927
  "text_rendering": 0.0,
928
  "visual_reference_evaluation": 0.0
929
  },
 
949
  "physical_plausibility": 463,
950
  "prompt_faithfulness": 651,
951
  "rubric_adaptive": 651,
952
+ "text_reference_evaluation": 448,
953
  "text_rendering": 512,
954
  "visual_reference_evaluation": 506
955
  },
 
961
  "physical_plausibility": 77.3,
962
  "prompt_faithfulness": 69.2,
963
  "rubric_adaptive": 70.1,
964
+ "text_reference_evaluation": 55.1,
965
  "text_rendering": 75.9,
966
  "visual_reference_evaluation": 66.0
967
  },
 
985
  "physical_plausibility": 533,
986
  "prompt_faithfulness": 651,
987
  "rubric_adaptive": 651,
988
+ "text_reference_evaluation": 445,
989
  "text_rendering": 467,
990
  "visual_reference_evaluation": 506
991
  },
 
997
  "physical_plausibility": 78.5,
998
  "prompt_faithfulness": 60.7,
999
  "rubric_adaptive": 63.1,
1000
+ "text_reference_evaluation": 46.4,
1001
  "text_rendering": 65.0,
1002
  "visual_reference_evaluation": 58.3
1003
  },
 
1021
  "physical_plausibility": 449,
1022
  "prompt_faithfulness": 620,
1023
  "rubric_adaptive": 620,
1024
+ "text_reference_evaluation": 454,
1025
  "text_rendering": 484,
1026
  "visual_reference_evaluation": 493
1027
  },
 
1033
  "physical_plausibility": 73.6,
1034
  "prompt_faithfulness": 60.8,
1035
  "rubric_adaptive": 62.5,
1036
+ "text_reference_evaluation": 46.0,
1037
  "text_rendering": 62.8,
1038
  "visual_reference_evaluation": 58.3
1039
  },
 
1057
  "physical_plausibility": 448,
1058
  "prompt_faithfulness": 642,
1059
  "rubric_adaptive": 642,
1060
+ "text_reference_evaluation": 436,
1061
  "text_rendering": 445,
1062
  "visual_reference_evaluation": 515
1063
  },
 
1069
  "physical_plausibility": 71.8,
1070
  "prompt_faithfulness": 47.9,
1071
  "rubric_adaptive": 51.8,
1072
+ "text_reference_evaluation": 34.7,
1073
  "text_rendering": 55.5,
1074
  "visual_reference_evaluation": 43.8
1075
  },
 
1093
  "physical_plausibility": 465,
1094
  "prompt_faithfulness": 651,
1095
  "rubric_adaptive": 651,
1096
+ "text_reference_evaluation": 458,
1097
  "text_rendering": 444,
1098
  "visual_reference_evaluation": 525
1099
  },
 
1105
  "physical_plausibility": 67.1,
1106
  "prompt_faithfulness": 44.4,
1107
  "rubric_adaptive": 48.7,
1108
+ "text_reference_evaluation": 32.2,
1109
  "text_rendering": 52.9,
1110
  "visual_reference_evaluation": 40.3
1111
  },
 
1129
  "physical_plausibility": 497,
1130
  "prompt_faithfulness": 651,
1131
  "rubric_adaptive": 651,
1132
+ "text_reference_evaluation": 451,
1133
  "text_rendering": 481,
1134
  "visual_reference_evaluation": 523
1135
  },
 
1141
  "physical_plausibility": 62.6,
1142
  "prompt_faithfulness": 43.1,
1143
  "rubric_adaptive": 47.0,
1144
+ "text_reference_evaluation": 27.0,
1145
  "text_rendering": 47.5,
1146
  "visual_reference_evaluation": 37.1
1147
  },
 
1165
  "physical_plausibility": 509,
1166
  "prompt_faithfulness": 650,
1167
  "rubric_adaptive": 651,
1168
+ "text_reference_evaluation": 463,
1169
  "text_rendering": 453,
1170
  "visual_reference_evaluation": 504
1171
  },
 
1177
  "physical_plausibility": 64.0,
1178
  "prompt_faithfulness": 38.5,
1179
  "rubric_adaptive": 43.6,
1180
+ "text_reference_evaluation": 21.6,
1181
  "text_rendering": 35.9,
1182
  "visual_reference_evaluation": 35.1
1183
  },
 
1201
  "physical_plausibility": 502,
1202
  "prompt_faithfulness": 651,
1203
  "rubric_adaptive": 651,
1204
+ "text_reference_evaluation": 482,
1205
  "text_rendering": 468,
1206
  "visual_reference_evaluation": 505
1207
  },
 
1213
  "physical_plausibility": 65.5,
1214
  "prompt_faithfulness": 36.0,
1215
  "rubric_adaptive": 40.4,
1216
+ "text_reference_evaluation": 17.1,
1217
  "text_rendering": 28.0,
1218
  "visual_reference_evaluation": 33.2
1219
  },
 
1237
  "physical_plausibility": 583,
1238
  "prompt_faithfulness": 651,
1239
  "rubric_adaptive": 651,
1240
+ "text_reference_evaluation": 478,
1241
  "text_rendering": 452,
1242
  "visual_reference_evaluation": 503
1243
  },
 
1249
  "physical_plausibility": 44.6,
1250
  "prompt_faithfulness": 18.6,
1251
  "rubric_adaptive": 24.3,
1252
+ "text_reference_evaluation": 5.0,
1253
  "text_rendering": 8.7,
1254
  "visual_reference_evaluation": 17.7
1255
  },
 
1273
  "physical_plausibility": 503,
1274
  "prompt_faithfulness": 651,
1275
  "rubric_adaptive": 651,
1276
+ "text_reference_evaluation": 494,
1277
  "text_rendering": 476,
1278
  "visual_reference_evaluation": 504
1279
  },
 
1285
  "physical_plausibility": 48.6,
1286
  "prompt_faithfulness": 17.2,
1287
  "rubric_adaptive": 23.1,
1288
+ "text_reference_evaluation": 5.3,
1289
  "text_rendering": 7.2,
1290
  "visual_reference_evaluation": 16.9
1291
  },
 
1309
  "physical_plausibility": 502,
1310
  "prompt_faithfulness": 650,
1311
  "rubric_adaptive": 651,
1312
+ "text_reference_evaluation": 497,
1313
  "text_rendering": 459,
1314
  "visual_reference_evaluation": 502
1315
  },
 
1321
  "physical_plausibility": 46.2,
1322
  "prompt_faithfulness": 12.4,
1323
  "rubric_adaptive": 18.4,
1324
+ "text_reference_evaluation": 2.3,
1325
  "text_rendering": 4.2,
1326
  "visual_reference_evaluation": 11.9
1327
  },
 
1345
  "physical_plausibility": 536,
1346
  "prompt_faithfulness": 651,
1347
  "rubric_adaptive": 651,
1348
+ "text_reference_evaluation": 479,
1349
  "text_rendering": 436,
1350
  "visual_reference_evaluation": 503
1351
  },
 
1357
  "physical_plausibility": 36.8,
1358
  "prompt_faithfulness": 13.3,
1359
  "rubric_adaptive": 17.6,
1360
+ "text_reference_evaluation": 1.9,
1361
  "text_rendering": 2.5,
1362
  "visual_reference_evaluation": 13.5
1363
  },
 
1381
  "physical_plausibility": 556,
1382
  "prompt_faithfulness": 651,
1383
  "rubric_adaptive": 651,
1384
+ "text_reference_evaluation": 530,
1385
  "text_rendering": 496,
1386
  "visual_reference_evaluation": 588
1387
  },
 
1393
  "physical_plausibility": 23.7,
1394
  "prompt_faithfulness": 6.9,
1395
  "rubric_adaptive": 10.0,
1396
+ "text_reference_evaluation": 1.4,
1397
  "text_rendering": 1.4,
1398
  "visual_reference_evaluation": 7.0
1399
  },
 
1419
  "physical_plausibility": 158,
1420
  "prompt_faithfulness": 264,
1421
  "rubric_adaptive": 264,
1422
+ "text_reference_evaluation": 254,
1423
  "text_rendering": 252,
1424
  "visual_reference_evaluation": 173
1425
  },
 
1431
  "physical_plausibility": 89.1,
1432
  "prompt_faithfulness": 69.3,
1433
  "rubric_adaptive": 67.8,
1434
+ "text_reference_evaluation": 48.5,
1435
  "text_rendering": 70.1,
1436
  "visual_reference_evaluation": 66.7
1437
  },
 
1455
  "physical_plausibility": 214,
1456
  "prompt_faithfulness": 264,
1457
  "rubric_adaptive": 264,
1458
+ "text_reference_evaluation": 255,
1459
  "text_rendering": 244,
1460
  "visual_reference_evaluation": 173
1461
  },
 
1467
  "physical_plausibility": 86.2,
1468
  "prompt_faithfulness": 60.1,
1469
  "rubric_adaptive": 59.8,
1470
+ "text_reference_evaluation": 39.5,
1471
  "text_rendering": 59.6,
1472
  "visual_reference_evaluation": 54.4
1473
  },
 
1491
  "physical_plausibility": 171,
1492
  "prompt_faithfulness": 264,
1493
  "rubric_adaptive": 264,
1494
+ "text_reference_evaluation": 260,
1495
  "text_rendering": 248,
1496
  "visual_reference_evaluation": 172
1497
  },
 
1503
  "physical_plausibility": 85.0,
1504
  "prompt_faithfulness": 60.9,
1505
  "rubric_adaptive": 59.3,
1506
+ "text_reference_evaluation": 39.5,
1507
  "text_rendering": 57.0,
1508
  "visual_reference_evaluation": 54.8
1509
  },
 
1527
  "physical_plausibility": 155,
1528
  "prompt_faithfulness": 264,
1529
  "rubric_adaptive": 264,
1530
+ "text_reference_evaluation": 258,
1531
  "text_rendering": 249,
1532
  "visual_reference_evaluation": 172
1533
  },
 
1539
  "physical_plausibility": 83.1,
1540
  "prompt_faithfulness": 48.0,
1541
  "rubric_adaptive": 48.5,
1542
+ "text_reference_evaluation": 29.7,
1543
  "text_rendering": 47.3,
1544
  "visual_reference_evaluation": 37.1
1545
  },
 
1563
  "physical_plausibility": 157,
1564
  "prompt_faithfulness": 264,
1565
  "rubric_adaptive": 264,
1566
+ "text_reference_evaluation": 258,
1567
  "text_rendering": 244,
1568
  "visual_reference_evaluation": 172
1569
  },
 
1575
  "physical_plausibility": 80.4,
1576
  "prompt_faithfulness": 45.0,
1577
  "rubric_adaptive": 46.4,
1578
+ "text_reference_evaluation": 26.2,
1579
  "text_rendering": 45.4,
1580
  "visual_reference_evaluation": 34.4
1581
  },
 
1599
  "physical_plausibility": 189,
1600
  "prompt_faithfulness": 264,
1601
  "rubric_adaptive": 264,
1602
+ "text_reference_evaluation": 257,
1603
  "text_rendering": 256,
1604
  "visual_reference_evaluation": 172
1605
  },
 
1611
  "physical_plausibility": 69.6,
1612
  "prompt_faithfulness": 40.5,
1613
  "rubric_adaptive": 42.2,
1614
+ "text_reference_evaluation": 22.4,
1615
  "text_rendering": 41.4,
1616
  "visual_reference_evaluation": 27.2
1617
  },
 
1635
  "physical_plausibility": 197,
1636
  "prompt_faithfulness": 264,
1637
  "rubric_adaptive": 264,
1638
+ "text_reference_evaluation": 260,
1639
  "text_rendering": 250,
1640
  "visual_reference_evaluation": 172
1641
  },
 
1647
  "physical_plausibility": 72.3,
1648
  "prompt_faithfulness": 33.6,
1649
  "rubric_adaptive": 36.7,
1650
+ "text_reference_evaluation": 16.3,
1651
  "text_rendering": 30.1,
1652
  "visual_reference_evaluation": 24.0
1653
  },
 
1671
  "physical_plausibility": 188,
1672
  "prompt_faithfulness": 264,
1673
  "rubric_adaptive": 264,
1674
+ "text_reference_evaluation": 261,
1675
  "text_rendering": 254,
1676
  "visual_reference_evaluation": 172
1677
  },
 
1683
  "physical_plausibility": 75.5,
1684
  "prompt_faithfulness": 32.5,
1685
  "rubric_adaptive": 33.7,
1686
+ "text_reference_evaluation": 12.1,
1687
  "text_rendering": 22.1,
1688
  "visual_reference_evaluation": 25.0
1689
  },
 
1707
  "physical_plausibility": 233,
1708
  "prompt_faithfulness": 264,
1709
  "rubric_adaptive": 264,
1710
+ "text_reference_evaluation": 264,
1711
  "text_rendering": 253,
1712
  "visual_reference_evaluation": 172
1713
  },
 
1719
  "physical_plausibility": 44.3,
1720
  "prompt_faithfulness": 13.8,
1721
  "rubric_adaptive": 17.5,
1722
+ "text_reference_evaluation": 3.5,
1723
  "text_rendering": 5.4,
1724
  "visual_reference_evaluation": 10.4
1725
  },
 
1743
  "physical_plausibility": 198,
1744
  "prompt_faithfulness": 264,
1745
  "rubric_adaptive": 264,
1746
+ "text_reference_evaluation": 263,
1747
  "text_rendering": 254,
1748
  "visual_reference_evaluation": 172
1749
  },
 
1755
  "physical_plausibility": 48.7,
1756
  "prompt_faithfulness": 12.4,
1757
  "rubric_adaptive": 16.2,
1758
+ "text_reference_evaluation": 3.6,
1759
  "text_rendering": 3.9,
1760
  "visual_reference_evaluation": 9.9
1761
  },
 
1779
  "physical_plausibility": 201,
1780
  "prompt_faithfulness": 263,
1781
  "rubric_adaptive": 264,
1782
+ "text_reference_evaluation": 262,
1783
  "text_rendering": 249,
1784
  "visual_reference_evaluation": 171
1785
  },
 
1791
  "physical_plausibility": 44.6,
1792
  "prompt_faithfulness": 9.1,
1793
  "rubric_adaptive": 13.6,
1794
+ "text_reference_evaluation": 1.7,
1795
  "text_rendering": 2.8,
1796
  "visual_reference_evaluation": 7.2
1797
  },
 
1815
  "physical_plausibility": 203,
1816
  "prompt_faithfulness": 264,
1817
  "rubric_adaptive": 264,
1818
+ "text_reference_evaluation": 264,
1819
  "text_rendering": 244,
1820
  "visual_reference_evaluation": 172
1821
  },
 
1827
  "physical_plausibility": 37.8,
1828
  "prompt_faithfulness": 9.9,
1829
  "rubric_adaptive": 12.4,
1830
+ "text_reference_evaluation": 1.1,
1831
  "text_rendering": 1.6,
1832
  "visual_reference_evaluation": 9.3
1833
  },
 
1851
  "physical_plausibility": 216,
1852
  "prompt_faithfulness": 264,
1853
  "rubric_adaptive": 264,
1854
+ "text_reference_evaluation": 264,
1855
  "text_rendering": 249,
1856
  "visual_reference_evaluation": 239
1857
  },
 
1863
  "physical_plausibility": 8.1,
1864
  "prompt_faithfulness": 0.6,
1865
  "rubric_adaptive": 1.7,
1866
+ "text_reference_evaluation": 0.2,
1867
  "text_rendering": 0.0,
1868
  "visual_reference_evaluation": 0.1
1869
  },
 
1889
  "physical_plausibility": 305,
1890
  "prompt_faithfulness": 387,
1891
  "rubric_adaptive": 387,
1892
+ "text_reference_evaluation": 194,
1893
  "text_rendering": 260,
1894
  "visual_reference_evaluation": 333
1895
  },
 
1901
  "physical_plausibility": 71.2,
1902
  "prompt_faithfulness": 69.2,
1903
  "rubric_adaptive": 71.7,
1904
+ "text_reference_evaluation": 63.7,
1905
  "text_rendering": 81.5,
1906
  "visual_reference_evaluation": 65.7
1907
  },
 
1925
  "physical_plausibility": 319,
1926
  "prompt_faithfulness": 387,
1927
  "rubric_adaptive": 387,
1928
+ "text_reference_evaluation": 190,
1929
  "text_rendering": 223,
1930
  "visual_reference_evaluation": 333
1931
  },
 
1937
  "physical_plausibility": 73.3,
1938
  "prompt_faithfulness": 61.1,
1939
  "rubric_adaptive": 65.4,
1940
+ "text_reference_evaluation": 55.6,
1941
  "text_rendering": 70.8,
1942
  "visual_reference_evaluation": 60.4
1943
  },
 
1961
  "physical_plausibility": 278,
1962
  "prompt_faithfulness": 356,
1963
  "rubric_adaptive": 356,
1964
+ "text_reference_evaluation": 194,
1965
  "text_rendering": 236,
1966
  "visual_reference_evaluation": 321
1967
  },
 
1973
  "physical_plausibility": 66.5,
1974
  "prompt_faithfulness": 60.8,
1975
  "rubric_adaptive": 64.9,
1976
+ "text_reference_evaluation": 54.6,
1977
  "text_rendering": 69.0,
1978
  "visual_reference_evaluation": 60.2
1979
  },
 
1997
  "physical_plausibility": 293,
1998
  "prompt_faithfulness": 378,
1999
  "rubric_adaptive": 378,
2000
+ "text_reference_evaluation": 178,
2001
  "text_rendering": 196,
2002
  "visual_reference_evaluation": 343
2003
  },
 
2009
  "physical_plausibility": 65.8,
2010
  "prompt_faithfulness": 47.9,
2011
  "rubric_adaptive": 54.1,
2012
+ "text_reference_evaluation": 41.9,
2013
  "text_rendering": 66.0,
2014
  "visual_reference_evaluation": 47.2
2015
  },
 
2033
  "physical_plausibility": 308,
2034
  "prompt_faithfulness": 387,
2035
  "rubric_adaptive": 387,
2036
+ "text_reference_evaluation": 200,
2037
  "text_rendering": 200,
2038
  "visual_reference_evaluation": 353
2039
  },
 
2045
  "physical_plausibility": 60.3,
2046
  "prompt_faithfulness": 44.0,
2047
  "rubric_adaptive": 50.2,
2048
+ "text_reference_evaluation": 39.9,
2049
  "text_rendering": 62.0,
2050
  "visual_reference_evaluation": 43.2
2051
  },
 
2069
  "physical_plausibility": 308,
2070
  "prompt_faithfulness": 387,
2071
  "rubric_adaptive": 387,
2072
+ "text_reference_evaluation": 194,
2073
  "text_rendering": 225,
2074
  "visual_reference_evaluation": 351
2075
  },
 
2081
  "physical_plausibility": 58.3,
2082
  "prompt_faithfulness": 44.8,
2083
  "rubric_adaptive": 50.3,
2084
+ "text_reference_evaluation": 33.2,
2085
  "text_rendering": 54.4,
2086
  "visual_reference_evaluation": 41.9
2087
  },
 
2105
  "physical_plausibility": 312,
2106
  "prompt_faithfulness": 386,
2107
  "rubric_adaptive": 387,
2108
+ "text_reference_evaluation": 203,
2109
  "text_rendering": 203,
2110
  "visual_reference_evaluation": 332
2111
  },
 
2117
  "physical_plausibility": 58.8,
2118
  "prompt_faithfulness": 41.9,
2119
  "rubric_adaptive": 48.3,
2120
+ "text_reference_evaluation": 28.5,
2121
  "text_rendering": 43.2,
2122
  "visual_reference_evaluation": 40.8
2123
  },
 
2141
  "physical_plausibility": 314,
2142
  "prompt_faithfulness": 387,
2143
  "rubric_adaptive": 387,
2144
+ "text_reference_evaluation": 221,
2145
  "text_rendering": 214,
2146
  "visual_reference_evaluation": 333
2147
  },
 
2153
  "physical_plausibility": 59.5,
2154
  "prompt_faithfulness": 38.4,
2155
  "rubric_adaptive": 45.0,
2156
+ "text_reference_evaluation": 23.0,
2157
  "text_rendering": 35.0,
2158
  "visual_reference_evaluation": 37.4
2159
  },
 
2177
  "physical_plausibility": 350,
2178
  "prompt_faithfulness": 387,
2179
  "rubric_adaptive": 387,
2180
+ "text_reference_evaluation": 214,
2181
  "text_rendering": 199,
2182
  "visual_reference_evaluation": 331
2183
  },
 
2189
  "physical_plausibility": 44.8,
2190
  "prompt_faithfulness": 21.9,
2191
  "rubric_adaptive": 29.0,
2192
+ "text_reference_evaluation": 6.9,
2193
  "text_rendering": 12.8,
2194
  "visual_reference_evaluation": 21.6
2195
  },
 
2213
  "physical_plausibility": 305,
2214
  "prompt_faithfulness": 387,
2215
  "rubric_adaptive": 387,
2216
+ "text_reference_evaluation": 231,
2217
  "text_rendering": 222,
2218
  "visual_reference_evaluation": 332
2219
  },
 
2225
  "physical_plausibility": 48.5,
2226
  "prompt_faithfulness": 20.4,
2227
  "rubric_adaptive": 27.7,
2228
+ "text_reference_evaluation": 7.2,
2229
  "text_rendering": 11.0,
2230
  "visual_reference_evaluation": 20.6
2231
  },
 
2249
  "physical_plausibility": 301,
2250
  "prompt_faithfulness": 387,
2251
  "rubric_adaptive": 387,
2252
+ "text_reference_evaluation": 235,
2253
  "text_rendering": 210,
2254
  "visual_reference_evaluation": 331
2255
  },
 
2261
  "physical_plausibility": 47.3,
2262
  "prompt_faithfulness": 14.7,
2263
  "rubric_adaptive": 21.7,
2264
+ "text_reference_evaluation": 3.0,
2265
  "text_rendering": 6.0,
2266
  "visual_reference_evaluation": 14.3
2267
  },
 
2285
  "physical_plausibility": 333,
2286
  "prompt_faithfulness": 387,
2287
  "rubric_adaptive": 387,
2288
+ "text_reference_evaluation": 215,
2289
  "text_rendering": 192,
2290
  "visual_reference_evaluation": 331
2291
  },
 
2297
  "physical_plausibility": 36.2,
2298
  "prompt_faithfulness": 15.5,
2299
  "rubric_adaptive": 21.2,
2300
+ "text_reference_evaluation": 2.9,
2301
  "text_rendering": 3.6,
2302
  "visual_reference_evaluation": 15.7
2303
  },
 
2321
  "physical_plausibility": 340,
2322
  "prompt_faithfulness": 387,
2323
  "rubric_adaptive": 387,
2324
+ "text_reference_evaluation": 266,
2325
  "text_rendering": 247,
2326
  "visual_reference_evaluation": 349
2327
  },
 
2333
  "physical_plausibility": 33.5,
2334
  "prompt_faithfulness": 11.2,
2335
  "rubric_adaptive": 15.7,
2336
+ "text_reference_evaluation": 2.6,
2337
  "text_rendering": 2.8,
2338
  "visual_reference_evaluation": 11.7
2339
  },
public/data/leaderboard_overall.json CHANGED
@@ -8,6 +8,7 @@
8
  "physical_plausibility": 558,
9
  "prompt_faithfulness": 751,
10
  "rubric_adaptive": 751,
 
11
  "text_rendering": 544,
12
  "visual_reference_evaluation": 599
13
  },
@@ -19,6 +20,7 @@
19
  "physical_plausibility": 76.7,
20
  "prompt_faithfulness": 69.4,
21
  "rubric_adaptive": 70.8,
 
22
  "text_rendering": 75.4,
23
  "visual_reference_evaluation": 65.7
24
  },
@@ -42,6 +44,7 @@
42
  "physical_plausibility": 627,
43
  "prompt_faithfulness": 751,
44
  "rubric_adaptive": 751,
 
45
  "text_rendering": 500,
46
  "visual_reference_evaluation": 598
47
  },
@@ -53,6 +56,7 @@
53
  "physical_plausibility": 78.4,
54
  "prompt_faithfulness": 62.3,
55
  "rubric_adaptive": 65.1,
 
56
  "text_rendering": 66.3,
57
  "visual_reference_evaluation": 59.8
58
  },
@@ -76,6 +80,7 @@
76
  "physical_plausibility": 539,
77
  "prompt_faithfulness": 717,
78
  "rubric_adaptive": 717,
 
79
  "text_rendering": 517,
80
  "visual_reference_evaluation": 582
81
  },
@@ -87,6 +92,7 @@
87
  "physical_plausibility": 73.1,
88
  "prompt_faithfulness": 62.0,
89
  "rubric_adaptive": 64.1,
 
90
  "text_rendering": 63.4,
91
  "visual_reference_evaluation": 58.9
92
  },
@@ -110,6 +116,7 @@
110
  "physical_plausibility": 544,
111
  "prompt_faithfulness": 742,
112
  "rubric_adaptive": 742,
 
113
  "text_rendering": 471,
114
  "visual_reference_evaluation": 606
115
  },
@@ -121,6 +128,7 @@
121
  "physical_plausibility": 71.7,
122
  "prompt_faithfulness": 50.0,
123
  "rubric_adaptive": 54.2,
 
124
  "text_rendering": 56.7,
125
  "visual_reference_evaluation": 46.2
126
  },
@@ -144,6 +152,7 @@
144
  "physical_plausibility": 561,
145
  "prompt_faithfulness": 751,
146
  "rubric_adaptive": 751,
 
147
  "text_rendering": 467,
148
  "visual_reference_evaluation": 617
149
  },
@@ -155,6 +164,7 @@
155
  "physical_plausibility": 67.9,
156
  "prompt_faithfulness": 47.3,
157
  "rubric_adaptive": 51.9,
 
158
  "text_rendering": 54.0,
159
  "visual_reference_evaluation": 43.2
160
  },
@@ -178,6 +188,7 @@
178
  "physical_plausibility": 593,
179
  "prompt_faithfulness": 751,
180
  "rubric_adaptive": 751,
 
181
  "text_rendering": 518,
182
  "visual_reference_evaluation": 615
183
  },
@@ -189,6 +200,7 @@
189
  "physical_plausibility": 64.0,
190
  "prompt_faithfulness": 45.9,
191
  "rubric_adaptive": 50.2,
 
192
  "text_rendering": 48.9,
193
  "visual_reference_evaluation": 39.9
194
  },
@@ -212,6 +224,7 @@
212
  "physical_plausibility": 604,
213
  "prompt_faithfulness": 750,
214
  "rubric_adaptive": 751,
 
215
  "text_rendering": 483,
216
  "visual_reference_evaluation": 596
217
  },
@@ -223,6 +236,7 @@
223
  "physical_plausibility": 65.6,
224
  "prompt_faithfulness": 41.6,
225
  "rubric_adaptive": 47.2,
 
226
  "text_rendering": 38.1,
227
  "visual_reference_evaluation": 38.4
228
  },
@@ -246,6 +260,7 @@
246
  "physical_plausibility": 594,
247
  "prompt_faithfulness": 751,
248
  "rubric_adaptive": 751,
 
249
  "text_rendering": 498,
250
  "visual_reference_evaluation": 597
251
  },
@@ -257,6 +272,7 @@
257
  "physical_plausibility": 66.0,
258
  "prompt_faithfulness": 39.1,
259
  "rubric_adaptive": 44.0,
 
260
  "text_rendering": 28.9,
261
  "visual_reference_evaluation": 36.4
262
  },
@@ -280,6 +296,7 @@
280
  "physical_plausibility": 676,
281
  "prompt_faithfulness": 751,
282
  "rubric_adaptive": 751,
 
283
  "text_rendering": 475,
284
  "visual_reference_evaluation": 595
285
  },
@@ -291,6 +308,7 @@
291
  "physical_plausibility": 48.6,
292
  "prompt_faithfulness": 24.5,
293
  "rubric_adaptive": 30.5,
 
294
  "text_rendering": 11.3,
295
  "visual_reference_evaluation": 23.8
296
  },
@@ -314,6 +332,7 @@
314
  "physical_plausibility": 599,
315
  "prompt_faithfulness": 751,
316
  "rubric_adaptive": 751,
 
317
  "text_rendering": 501,
318
  "visual_reference_evaluation": 596
319
  },
@@ -325,6 +344,7 @@
325
  "physical_plausibility": 51.5,
326
  "prompt_faithfulness": 21.7,
327
  "rubric_adaptive": 27.9,
 
328
  "text_rendering": 8.4,
329
  "visual_reference_evaluation": 21.1
330
  },
@@ -348,6 +368,7 @@
348
  "physical_plausibility": 597,
349
  "prompt_faithfulness": 750,
350
  "rubric_adaptive": 751,
 
351
  "text_rendering": 483,
352
  "visual_reference_evaluation": 594
353
  },
@@ -359,6 +380,7 @@
359
  "physical_plausibility": 49.0,
360
  "prompt_faithfulness": 16.0,
361
  "rubric_adaptive": 22.9,
 
362
  "text_rendering": 4.7,
363
  "visual_reference_evaluation": 15.1
364
  },
@@ -382,6 +404,7 @@
382
  "physical_plausibility": 631,
383
  "prompt_faithfulness": 751,
384
  "rubric_adaptive": 751,
 
385
  "text_rendering": 465,
386
  "visual_reference_evaluation": 595
387
  },
@@ -393,6 +416,7 @@
393
  "physical_plausibility": 40.4,
394
  "prompt_faithfulness": 16.7,
395
  "rubric_adaptive": 21.8,
 
396
  "text_rendering": 3.5,
397
  "visual_reference_evaluation": 16.8
398
  },
@@ -416,6 +440,7 @@
416
  "physical_plausibility": 656,
417
  "prompt_faithfulness": 751,
418
  "rubric_adaptive": 751,
 
419
  "text_rendering": 596,
420
  "visual_reference_evaluation": 688
421
  },
@@ -427,6 +452,7 @@
427
  "physical_plausibility": 20.0,
428
  "prompt_faithfulness": 6.0,
429
  "rubric_adaptive": 8.7,
 
430
  "text_rendering": 1.2,
431
  "visual_reference_evaluation": 6.0
432
  },
 
8
  "physical_plausibility": 558,
9
  "prompt_faithfulness": 751,
10
  "rubric_adaptive": 751,
11
+ "text_reference_evaluation": 486,
12
  "text_rendering": 544,
13
  "visual_reference_evaluation": 599
14
  },
 
20
  "physical_plausibility": 76.7,
21
  "prompt_faithfulness": 69.4,
22
  "rubric_adaptive": 70.8,
23
+ "text_reference_evaluation": 54.6,
24
  "text_rendering": 75.4,
25
  "visual_reference_evaluation": 65.7
26
  },
 
44
  "physical_plausibility": 627,
45
  "prompt_faithfulness": 751,
46
  "rubric_adaptive": 751,
47
+ "text_reference_evaluation": 480,
48
  "text_rendering": 500,
49
  "visual_reference_evaluation": 598
50
  },
 
56
  "physical_plausibility": 78.4,
57
  "prompt_faithfulness": 62.3,
58
  "rubric_adaptive": 65.1,
59
+ "text_reference_evaluation": 47.4,
60
  "text_rendering": 66.3,
61
  "visual_reference_evaluation": 59.8
62
  },
 
80
  "physical_plausibility": 539,
81
  "prompt_faithfulness": 717,
82
  "rubric_adaptive": 717,
83
+ "text_reference_evaluation": 487,
84
  "text_rendering": 517,
85
  "visual_reference_evaluation": 582
86
  },
 
92
  "physical_plausibility": 73.1,
93
  "prompt_faithfulness": 62.0,
94
  "rubric_adaptive": 64.1,
95
+ "text_reference_evaluation": 46.0,
96
  "text_rendering": 63.4,
97
  "visual_reference_evaluation": 58.9
98
  },
 
116
  "physical_plausibility": 544,
117
  "prompt_faithfulness": 742,
118
  "rubric_adaptive": 742,
119
+ "text_reference_evaluation": 473,
120
  "text_rendering": 471,
121
  "visual_reference_evaluation": 606
122
  },
 
128
  "physical_plausibility": 71.7,
129
  "prompt_faithfulness": 50.0,
130
  "rubric_adaptive": 54.2,
131
+ "text_reference_evaluation": 35.7,
132
  "text_rendering": 56.7,
133
  "visual_reference_evaluation": 46.2
134
  },
 
152
  "physical_plausibility": 561,
153
  "prompt_faithfulness": 751,
154
  "rubric_adaptive": 751,
155
+ "text_reference_evaluation": 492,
156
  "text_rendering": 467,
157
  "visual_reference_evaluation": 617
158
  },
 
164
  "physical_plausibility": 67.9,
165
  "prompt_faithfulness": 47.3,
166
  "rubric_adaptive": 51.9,
167
+ "text_reference_evaluation": 33.1,
168
  "text_rendering": 54.0,
169
  "visual_reference_evaluation": 43.2
170
  },
 
188
  "physical_plausibility": 593,
189
  "prompt_faithfulness": 751,
190
  "rubric_adaptive": 751,
191
+ "text_reference_evaluation": 486,
192
  "text_rendering": 518,
193
  "visual_reference_evaluation": 615
194
  },
 
200
  "physical_plausibility": 64.0,
201
  "prompt_faithfulness": 45.9,
202
  "rubric_adaptive": 50.2,
203
+ "text_reference_evaluation": 28.2,
204
  "text_rendering": 48.9,
205
  "visual_reference_evaluation": 39.9
206
  },
 
224
  "physical_plausibility": 604,
225
  "prompt_faithfulness": 750,
226
  "rubric_adaptive": 751,
227
+ "text_reference_evaluation": 501,
228
  "text_rendering": 483,
229
  "visual_reference_evaluation": 596
230
  },
 
236
  "physical_plausibility": 65.6,
237
  "prompt_faithfulness": 41.6,
238
  "rubric_adaptive": 47.2,
239
+ "text_reference_evaluation": 23.4,
240
  "text_rendering": 38.1,
241
  "visual_reference_evaluation": 38.4
242
  },
 
260
  "physical_plausibility": 594,
261
  "prompt_faithfulness": 751,
262
  "rubric_adaptive": 751,
263
+ "text_reference_evaluation": 522,
264
  "text_rendering": 498,
265
  "visual_reference_evaluation": 597
266
  },
 
272
  "physical_plausibility": 66.0,
273
  "prompt_faithfulness": 39.1,
274
  "rubric_adaptive": 44.0,
275
+ "text_reference_evaluation": 17.8,
276
  "text_rendering": 28.9,
277
  "visual_reference_evaluation": 36.4
278
  },
 
296
  "physical_plausibility": 676,
297
  "prompt_faithfulness": 751,
298
  "rubric_adaptive": 751,
299
+ "text_reference_evaluation": 516,
300
  "text_rendering": 475,
301
  "visual_reference_evaluation": 595
302
  },
 
308
  "physical_plausibility": 48.6,
309
  "prompt_faithfulness": 24.5,
310
  "rubric_adaptive": 30.5,
311
+ "text_reference_evaluation": 7.7,
312
  "text_rendering": 11.3,
313
  "visual_reference_evaluation": 23.8
314
  },
 
332
  "physical_plausibility": 599,
333
  "prompt_faithfulness": 751,
334
  "rubric_adaptive": 751,
335
+ "text_reference_evaluation": 536,
336
  "text_rendering": 501,
337
  "visual_reference_evaluation": 596
338
  },
 
344
  "physical_plausibility": 51.5,
345
  "prompt_faithfulness": 21.7,
346
  "rubric_adaptive": 27.9,
347
+ "text_reference_evaluation": 6.6,
348
  "text_rendering": 8.4,
349
  "visual_reference_evaluation": 21.1
350
  },
 
368
  "physical_plausibility": 597,
369
  "prompt_faithfulness": 750,
370
  "rubric_adaptive": 751,
371
+ "text_reference_evaluation": 537,
372
  "text_rendering": 483,
373
  "visual_reference_evaluation": 594
374
  },
 
380
  "physical_plausibility": 49.0,
381
  "prompt_faithfulness": 16.0,
382
  "rubric_adaptive": 22.9,
383
+ "text_reference_evaluation": 3.6,
384
  "text_rendering": 4.7,
385
  "visual_reference_evaluation": 15.1
386
  },
 
404
  "physical_plausibility": 631,
405
  "prompt_faithfulness": 751,
406
  "rubric_adaptive": 751,
407
+ "text_reference_evaluation": 521,
408
  "text_rendering": 465,
409
  "visual_reference_evaluation": 595
410
  },
 
416
  "physical_plausibility": 40.4,
417
  "prompt_faithfulness": 16.7,
418
  "rubric_adaptive": 21.8,
419
+ "text_reference_evaluation": 3.5,
420
  "text_rendering": 3.5,
421
  "visual_reference_evaluation": 16.8
422
  },
 
440
  "physical_plausibility": 656,
441
  "prompt_faithfulness": 751,
442
  "rubric_adaptive": 751,
443
+ "text_reference_evaluation": 630,
444
  "text_rendering": 596,
445
  "visual_reference_evaluation": 688
446
  },
 
452
  "physical_plausibility": 20.0,
453
  "prompt_faithfulness": 6.0,
454
  "rubric_adaptive": 8.7,
455
+ "text_reference_evaluation": 1.2,
456
  "text_rendering": 1.2,
457
  "visual_reference_evaluation": 6.0
458
  },
public/data/manifest.json CHANGED
@@ -88,7 +88,6 @@
88
  },
89
  "schema_version": "1.0.0",
90
  "scoring": {
91
- "excluded_public_component": "text_reference_evaluation",
92
  "missing_policy_default": "zero_fill",
93
  "missing_policy_exceptions": [
94
  "qwen_image_2_pro",
@@ -117,6 +116,8 @@
117
  "physical_plausibility",
118
  "visual_reference_evaluation"
119
  ],
 
 
120
  "public_rounding_decimals": 1,
121
  "scale_public": [
122
  0,
 
88
  },
89
  "schema_version": "1.0.0",
90
  "scoring": {
 
91
  "missing_policy_default": "zero_fill",
92
  "missing_policy_exceptions": [
93
  "qwen_image_2_pro",
 
116
  "physical_plausibility",
117
  "visual_reference_evaluation"
118
  ],
119
+ "overall_9_excluded_component": "text_reference_evaluation",
120
+ "primary_metric": "overall_10",
121
  "public_rounding_decimals": 1,
122
  "scale_public": [
123
  0,
scripts/build_leaderboard_data.py CHANGED
@@ -14,7 +14,7 @@ from pathlib import Path
14
  from typing import Any, Callable
15
 
16
 
17
- PUBLIC_COMPONENTS = [
18
  "checklist",
19
  "rubric_adaptive",
20
  "prompt_faithfulness",
@@ -25,7 +25,8 @@ PUBLIC_COMPONENTS = [
25
  "physical_plausibility",
26
  "visual_reference_evaluation",
27
  ]
28
- EXCLUDED_PUBLIC_COMPONENT = "text_reference_evaluation"
 
29
 
30
  MODEL_METADATA = {
31
  "bagel": ("Bagel", "Open"),
@@ -154,7 +155,7 @@ def load_score(row_dir: Path, model_id: str, canonical: Any) -> dict[str, Any]:
154
  "lane": "none",
155
  "components_raw_0to3": components,
156
  "overall_10_raw": mean_present(components, list(canonical.COMPONENT_KEYS)),
157
- "overall_9_raw": mean_present(components, PUBLIC_COMPONENTS),
158
  }
159
 
160
 
@@ -217,7 +218,7 @@ def aggregate_group(
217
 
218
  component_scores = {}
219
  component_counts = {}
220
- for component in PUBLIC_COMPONENTS:
221
  values = [
222
  s["components_raw_0to3"][component]
223
  for s in scored
@@ -249,7 +250,7 @@ def aggregate_group(
249
  "component_counts": component_counts,
250
  }
251
  )
252
- return sorted(output, key=lambda row: (-(row["overall_9"] or -1), row["display_name"]))
253
 
254
 
255
  def build_aggregates(records: list[dict[str, Any]], canonical: Any) -> dict[str, Any]:
@@ -312,7 +313,7 @@ def validate(records: list[dict[str, Any]], aggregates: dict[str, Any], canonica
312
  for key, value in components.items():
313
  if value is not None and not 0 <= value <= 3:
314
  errors.append(f"out-of-range score {row['sample_id']} {model_id} {key}={value}")
315
- expected_9 = mean_present(components, PUBLIC_COMPONENTS)
316
  expected_10 = mean_present(components, list(canonical.COMPONENT_KEYS))
317
  if abs(score["overall_9_raw"] - expected_9) > 1e-12 or abs(score["overall_10_raw"] - expected_10) > 1e-12:
318
  errors.append(f"overall recomputation mismatch for {row['sample_id']} {model_id}")
@@ -364,13 +365,14 @@ def main() -> None:
364
  },
365
  "source_commit": source_commit(toolgen_root),
366
  "scoring": {
 
367
  "source": "augmented_parsed_result_ffjudge_pp.json",
368
  "scale_raw": [0, 3],
369
  "scale_public": [0, 100],
370
  "public_rounding_decimals": 1,
371
  "overall_10_components": list(canonical.COMPONENT_KEYS),
372
- "overall_9_components": PUBLIC_COMPONENTS,
373
- "excluded_public_component": EXCLUDED_PUBLIC_COMPONENT,
374
  "missing_policy_default": "zero_fill",
375
  "missing_policy_exceptions": sorted(canonical.SKIP_MISSING_GENS),
376
  },
 
14
  from typing import Any, Callable
15
 
16
 
17
+ OVERALL_9_COMPONENTS = [
18
  "checklist",
19
  "rubric_adaptive",
20
  "prompt_faithfulness",
 
25
  "physical_plausibility",
26
  "visual_reference_evaluation",
27
  ]
28
+ OVERALL_9_EXCLUDED_COMPONENT = "text_reference_evaluation"
29
+ DISPLAY_COMPONENTS = [*OVERALL_9_COMPONENTS, OVERALL_9_EXCLUDED_COMPONENT]
30
 
31
  MODEL_METADATA = {
32
  "bagel": ("Bagel", "Open"),
 
155
  "lane": "none",
156
  "components_raw_0to3": components,
157
  "overall_10_raw": mean_present(components, list(canonical.COMPONENT_KEYS)),
158
+ "overall_9_raw": mean_present(components, OVERALL_9_COMPONENTS),
159
  }
160
 
161
 
 
218
 
219
  component_scores = {}
220
  component_counts = {}
221
+ for component in DISPLAY_COMPONENTS:
222
  values = [
223
  s["components_raw_0to3"][component]
224
  for s in scored
 
250
  "component_counts": component_counts,
251
  }
252
  )
253
+ return sorted(output, key=lambda row: (-(row["overall_10"] or -1), row["display_name"]))
254
 
255
 
256
  def build_aggregates(records: list[dict[str, Any]], canonical: Any) -> dict[str, Any]:
 
313
  for key, value in components.items():
314
  if value is not None and not 0 <= value <= 3:
315
  errors.append(f"out-of-range score {row['sample_id']} {model_id} {key}={value}")
316
+ expected_9 = mean_present(components, OVERALL_9_COMPONENTS)
317
  expected_10 = mean_present(components, list(canonical.COMPONENT_KEYS))
318
  if abs(score["overall_9_raw"] - expected_9) > 1e-12 or abs(score["overall_10_raw"] - expected_10) > 1e-12:
319
  errors.append(f"overall recomputation mismatch for {row['sample_id']} {model_id}")
 
365
  },
366
  "source_commit": source_commit(toolgen_root),
367
  "scoring": {
368
+ "primary_metric": "overall_10",
369
  "source": "augmented_parsed_result_ffjudge_pp.json",
370
  "scale_raw": [0, 3],
371
  "scale_public": [0, 100],
372
  "public_rounding_decimals": 1,
373
  "overall_10_components": list(canonical.COMPONENT_KEYS),
374
+ "overall_9_components": OVERALL_9_COMPONENTS,
375
+ "overall_9_excluded_component": OVERALL_9_EXCLUDED_COMPONENT,
376
  "missing_policy_default": "zero_fill",
377
  "missing_policy_exceptions": sorted(canonical.SKIP_MISSING_GENS),
378
  },
style.css CHANGED
@@ -116,10 +116,43 @@ h1 {
116
  font-weight: 500;
117
  letter-spacing: 0.15em;
118
  text-transform: uppercase;
119
- margin-bottom: 3rem;
120
  display: block;
121
  }
122
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
123
  .intro-container {
124
  max-width: var(--max-width);
125
  margin: 1.5rem auto;
@@ -559,6 +592,20 @@ th.model-column {
559
  color: var(--accent-primary);
560
  }
561
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
562
  /* LLM Row Alignment */
563
  .llm-row {
564
  display: flex;
 
116
  font-weight: 500;
117
  letter-spacing: 0.15em;
118
  text-transform: uppercase;
119
+ margin-bottom: 2rem;
120
  display: block;
121
  }
122
 
123
+ .stat-grid {
124
+ display: grid;
125
+ grid-template-columns: repeat(4, minmax(0, 1fr));
126
+ gap: 0.9rem;
127
+ max-width: 900px;
128
+ margin: 0 auto 2rem;
129
+ }
130
+
131
+ .stat-grid article {
132
+ display: flex;
133
+ flex-direction: column;
134
+ padding: 1.15rem 0.75rem;
135
+ background: var(--glass-bg);
136
+ border: 1px solid var(--glass-border);
137
+ border-radius: 16px;
138
+ box-shadow: 0 12px 30px rgba(15, 23, 42, 0.04);
139
+ }
140
+
141
+ .stat-grid strong {
142
+ color: var(--accent-primary);
143
+ font-size: 1.65rem;
144
+ line-height: 1.1;
145
+ }
146
+
147
+ .stat-grid span {
148
+ margin-top: 0.35rem;
149
+ color: var(--text-secondary);
150
+ font-size: 0.78rem;
151
+ font-weight: 600;
152
+ letter-spacing: 0.04em;
153
+ text-transform: uppercase;
154
+ }
155
+
156
  .intro-container {
157
  max-width: var(--max-width);
158
  margin: 1.5rem auto;
 
592
  color: var(--accent-primary);
593
  }
594
 
595
+ .table-note {
596
+ max-width: var(--max-width);
597
+ margin: 1rem auto 0;
598
+ color: var(--text-secondary);
599
+ font-size: 0.86rem;
600
+ text-align: left;
601
+ }
602
+
603
+ @media (max-width: 720px) {
604
+ .stat-grid {
605
+ grid-template-columns: repeat(2, minmax(0, 1fr));
606
+ }
607
+ }
608
+
609
  /* LLM Row Alignment */
610
  .llm-row {
611
  display: flex;