List your company

Step-wise Verification on MMMU, MathVision, MathVerse-VO, DynaMath, WeMath Overall

62.3Macro F1Gemini-2.0-Flash
43.68448.51753.3558.183Nov 28, 2025

Evaluation results

MethodLinks
Gemini-2.0-FlashModel Type=Proprietary2025.1162.3
TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.1161.7
Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.1161.1
Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.1160.5
GPT-4oModel Type=Proprietary2025.1160.3
TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.1160.3
GPT-4o-MiniModel Type=Proprietary2025.1157.9
VisualPRMModel Type=Open-source, Number of Parameters=8B2025.1155.9
MM-PRMModel Type=Open-source, Number of Parameters=8B2025.1155.5
InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.1152.6
LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.1152.3
Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.1151.1
Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.1151
InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.1150.8
MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.1150.4
InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.1149.2
InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.1148
LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.1144.4