Share your thoughts, 1 month free Claude Pro on usSee more

Reward Modeling on RewardBench Chat

96.4Accuracy

Claude-3.5-Sonnet

Updated 1mo ago

Evaluation Results

Method	Links
Claude-3.5-Sonnet 2026.02		96.4
RM-R1-32B (Qwen-2.5-Inst) 2026.02		95.3
RM-R1-32B (DeepSeek-Dist) 2026.02		95.3
Gemini-2.5-Flash 2026.02		95
RRM-32B 2026.02		94.7
JudgeLRM-7B 2026.02		92.1
RM-R1-14B (DeepSeek-Dist) 2026.02		90.3
Rubric-ARM-voting@5 2026.02		90.3
Rubric-RM-voting@5 2026.02		89.9
API (direct Judge) 2026.02		89.6
Rubric-ARM 2026.02		89.4
Rubric-RM 2026.02		88.2
RM-R1-7B (DeepSeek-Dist) 2026.02		85.3
RM-R1-7B (Qwen-2.5-Inst) 2026.02		83
API (Rubric+Judge) 2026.02		79.6
RRM-7B 2026.02		77.7
Qwen-3-8B (Rubric+Judge) 2026.02		73.9
RM-R1-14B (Qwen-2.5-Inst) 2026.02		73.5