List your company

Step-wise Verification on MMMU

59.2Macro F1Qwen2.5-VL
44.32848.18952.0555.911Nov 28, 2025

Evaluation results

MethodLinks
Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.1159.2
Gemini-2.0-FlashModel Type=Proprietary2025.1158.5
TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.1158.3
Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.1156.6
GPT-4oModel Type=Proprietary2025.1156.3
TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.1155.8
VisualPRMModel Type=Open-source, Number of Parameters=8B2025.1154.9
GPT-4o-MiniModel Type=Proprietary2025.1153.6
Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.1153.1
InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.1152
InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.1151.5
MM-PRMModel Type=Open-source, Number of Parameters=8B2025.1151.2
Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.1150.4
InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.1148.8
InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.1147.1
LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.1146.1
LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.1145.7
MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.1144.9