List your company

Multilingual Reward Modeling on MM-Eval Avg. 18 lang

87.53AccuracyDIBJudge-Qwen3-8B
56.808464.784272.7680.7358Mar 11, 2026

Evaluation results

MethodLinks
DIBJudge-Qwen3-8BBackbone=Qwen3-8B2026.0387.53
mR3-Qwen3-8BModel Category=Multilingual Open Reward Models2026.0385.29
DIBJudge-Qwen3-4BBackbone=Qwen3-4B2026.0385.16
mR3-Qwen3-4BModel Category=Multilingual Open Reward Models2026.0382.55
Qwen3-8BModel Category=General Open Models2026.0382.2
Qwen3-4BModel Category=General Open Models2026.0380.85
Gemini-2.5-FlashModel Category=Proprietary Models2026.0377.47
Nemotron-Multi-49BModel Category=Multilingual Open Reward Models2026.0376.31
Think-as-Locals 7BModel Category=Multilingual Open Reward Models2026.0372.95
GPT-4oModel Category=Proprietary Models2026.0371.85
M-PROMETHEUS 7BModel Category=Multilingual Open Reward Models2026.0369.38
Qwen2.5-7B-InstructModel Category=General Open Models2026.0365.64
M-PROMETHEUS 3BModel Category=Multilingual Open Reward Models2026.0364.17
Qwen2.5-3B-InstructModel Category=General Open Models2026.0357.99