List your company

Reward Modeling on RewardBench English

91.01AccuracyDIBJudge-Qwen3-8B
68.109274.05468085.9454Mar 11, 2026

Evaluation results

MethodLinks
DIBJudge-Qwen3-8BBackbone=Qwen3-8B2026.0391.01
DIBJudge-Qwen3-4BBackbone=Qwen3-4B2026.0390.32
mR3-Qwen3-8BModel Category=Multilingual Open Reward Models2026.0390.1
mR3-Qwen3-4BModel Category=Multilingual Open Reward Models2026.0389.75
Nemotron-Multi-49BModel Category=Multilingual Open Reward Models2026.0389.71
Gemini-2.5-FlashModel Category=Proprietary Models2026.0388.83
Qwen3-8BModel Category=General Open Models2026.0388.81
Think-as-Locals 7BModel Category=Multilingual Open Reward Models2026.0388.79
Qwen3-4BModel Category=General Open Models2026.0387.54
GPT-4oModel Category=Proprietary Models2026.0385.96
Qwen2.5-7B-InstructModel Category=General Open Models2026.0378.59
M-PROMETHEUS 7BModel Category=Multilingual Open Reward Models2026.0376.69
M-PROMETHEUS 3BModel Category=Multilingual Open Reward Models2026.0369.79
Qwen2.5-3B-InstructModel Category=General Open Models2026.0368.99