rubricreward

non-profit

https://rubricreward.github.io

AI & ML interests

R3/R-three/R-cube

Recent Activity

Shoubin submitted a paper 3 days ago

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

Shoubin submitted a paper 11 days ago

VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting

patrickamadeus updated a dataset about 2 months ago

rubricreward/mmr3-synthalign

View all activity

rubricreward 's datasets 171

rubricreward/mmr3-synthalign

Viewer • Updated Feb 10 • 12.4k • 9

rubricreward/mmr3-bpo

Viewer • Updated Feb 10 • 14.4k • 20

rubricreward/mR3-Dataset-100K-EasyToHard

Viewer • Updated Jan 29 • 100k • 142 • 1

rubricreward/m-ArenaHard-v2.0

Viewer • Updated Sep 21, 2025 • 11.5k • 22

rubricreward/reward-bench

Viewer • Updated Sep 18, 2025 • 2.99k • 24

rubricreward/mR3-Dataset-100K-EasyToHard-Truncated

Viewer • Updated Sep 17, 2025 • 99.5k • 55 • 1

rubricreward/PPE-Human-Preference

Viewer • Updated Sep 12, 2025 • 15.5k • 10

rubricreward/mR3-Dataset-100K-StartEng-EasyToHard

Viewer • Updated Sep 7, 2025 • 100k • 33 • 1

rubricreward/mR3-Dataset-100K-StartEng-HardToEasy

Viewer • Updated Sep 7, 2025 • 100k • 85

rubricreward/mR3-Dataset-100K-HardToEasy

Viewer • Updated Sep 7, 2025 • 100k • 14

rubricreward/mR3-Dataset-100K-StartEng

Viewer • Updated Sep 7, 2025 • 100k • 101

rubricreward/mR3-Dataset-100K

Viewer • Updated Sep 7, 2025 • 100k • 19

rubricreward/mR3-Dataset-100K-Truncated

Updated Sep 7, 2025 • 6

rubricreward/mR3-Dataset-Cleaned

Viewer • Updated Sep 7, 2025 • 100k • 40

rubricreward/mR3-Dataset-Filtered3

Viewer • Updated Sep 6, 2025 • 441k • 7

rubricreward/mR3-Dataset-Filtered2

Viewer • Updated Sep 6, 2025 • 645k • 106

rubricreward/PolyGuard-Filtered2

Viewer • Updated Sep 6, 2025 • 518k • 124

rubricreward/mR3-Dataset-Filtered2-no-PolyGuard

Viewer • Updated Sep 4, 2025 • 128k • 5

rubricreward/mR3-Dataset-Filtered1-no-PolyGuard

Viewer • Updated Sep 4, 2025 • 208k • 6

rubricreward/HelpSteer3-Filtered1

Viewer • Updated Sep 4, 2025 • 16.9k • 6

rubricreward/HelpSteer3-tgt_prompt_tgt_thinking-filtered_correct

Viewer • Updated Sep 4, 2025 • 26.6k • 4

rubricreward/HelpSteer3-tgt_prompt_en_thinking-filtered_correct

Viewer • Updated Sep 4, 2025 • 26.3k • 4

rubricreward/HelpSteer3-en_prompt_en_thinking-filtered_correct

Viewer • Updated Sep 4, 2025 • 26.8k • 4 • 1

rubricreward/HelpSteer3-tgt_prompt_tgt_thinking

Viewer • Updated Sep 4, 2025 • 38.5k • 4

rubricreward/HelpSteer3-tgt_prompt_en_thinking

Viewer • Updated Sep 4, 2025 • 38.5k • 5

rubricreward/HelpSteer3-en_prompt_en_thinking

Viewer • Updated Sep 4, 2025 • 38.5k • 10

rubricreward/PolyGuardMix-tgt_prompt_tgt_thinking-filtered_correct

Viewer • Updated Sep 3, 2025 • 2.57M • 5

rubricreward/PolyGuardMix-tgt_prompt_en_thinking-filtered_correct

Viewer • Updated Sep 3, 2025 • 2.62M • 5

rubricreward/PolyGuardMix-en_prompt_en_thinking-filtered_correct

Viewer • Updated Sep 2, 2025 • 2.63M • 4

rubricreward/PolyGuardMix-tgt_prompt_tgt_thinking

Viewer • Updated Sep 2, 2025 • 2.88M • 7