thunder-research-group/SNU_Ko-LAMBADA
Viewer
•
Updated
•
2.26k
•
72
SNU Thunder-LLM Korean Benchmark Suite
-
-
thunder-research-group/SNU_Ko-WinoGrande
Viewer • Updated • 1.27k • 68 -
thunder-research-group/SNU_Ko-ARC
Viewer • Updated • 3.54k • 72 -
thunder-research-group/SNU_Ko-GSM8K
Viewer • Updated • 1.32k • 132 • 1 -
thunder-research-group/SNU_Ko-IFEval
Viewer • Updated • 841 • 21 -
thunder-research-group/SNU_Ko-EQ-Bench
Viewer • Updated • 171 • 13
skt/kobest_v1
Viewer • Updated • 23.4k • 3.13k • 54Note We use hellaswag > test set for evaluation
-
HAERAE-HUB/KMMLU
Viewer • Updated • 244k • 9.59k • 96
HYU-NLP/KR-HumanEval
Viewer • Updated • 328 • 13Note We use v1 for evaluation
-
LGCNS/KorQuAD_2.0
Viewer • Updated • 93.7k • 108 • 2 -
thunder-research-group/SNU_Ko-MuSR
Viewer • Updated • 750 • 8