List your company

VLM-as-a-Judge on MLLM-as-a-Judge

75.78AccuracyGPT-4o
52.3858.45564.5370.605Apr 20, 2026

Evaluation results

MethodLinks
GPT-4oConfiguration=BIRCH2026.0475.78
Llama-3.2-Vision-90BConfiguration=BIRCH2026.0475.12
Gemini-2.5-FlashConfiguration=BIRCH2026.0473.37
Gemini-2.5-ProConfiguration=BIRCH2026.0473.37
LLaVA-OneVision-1.5-8BConfiguration=BIRCH2026.0471.17
Gemini-2.5-ProConfiguration=Standard Ref2026.0469.21
Gemini-2.5-FlashConfiguration=Standard Ref2026.0468.34
Gemini-2.5-ProConfiguration=Image Caption2026.0468.04
Gemini-2.5-ProConfiguration=Base2026.0467.63
Gemini-2.5-FlashConfiguration=Base2026.0466.92
Gemini-2.5-FlashConfiguration=Image Caption2026.0466.9
Llama-3.2-Vision-90BConfiguration=Image Caption2026.0466.73
GPT-4oConfiguration=Base2026.0466.45
LLaVA-OneVision-1.5-8BConfiguration=Standard Ref2026.0466.21
GPT-4oConfiguration=Image Caption2026.0465.79
LLaVA-OneVision-1.5-8BConfiguration=Image Caption2026.0465.67
LLaVA-OneVision-1.5-8BConfiguration=Base2026.0465.35
Llama-3.2-Vision-90BConfiguration=Base2026.0465.28
GPT-4oConfiguration=Standard Ref2026.0465.14
Llama-3.2-Vision-90BConfiguration=Standard Ref2026.0463.18
Phi-4-multimodalConfiguration=BIRCH2026.0463.11
LLaVA-1.6-34BConfiguration=BIRCH2026.0461.54
LLaVA-1.5-13BConfiguration=BIRCH2026.0459.48
Phi-4-multimodalConfiguration=Base2026.0459.19
Phi-4-multimodalConfiguration=Standard Ref2026.0459.11
Phi-4-multimodalConfiguration=Image Caption2026.0459.07
LLaVA-1.6-34BConfiguration=Base2026.0458.95
LLaVA-1.6-34BConfiguration=Image Caption2026.0458.88
LLaVA-1.6-34BConfiguration=Standard Ref2026.0458.02
LLaVA-1.5-13BConfiguration=Base2026.0456.21
LLaVA-1.5-13BConfiguration=Image Caption2026.0454.69
LLaVA-1.5-13BConfiguration=Standard Ref2026.0453.28