List your company

Step-wise Verification on MathVision

61.7Macro F1Qwen3-VL
42.25247.30152.3557.399Nov 28, 2025

Evaluation results

MethodLinks
Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.1161.7
GPT-4oModel Type=Proprietary2025.1160.2
Gemini-2.0-FlashModel Type=Proprietary2025.1160.1
Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.1159
GPT-4o-MiniModel Type=Proprietary2025.1158.9
TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.1158.3
TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.1157.6
VisualPRMModel Type=Open-source, Number of Parameters=8B2025.1156.1
MM-PRMModel Type=Open-source, Number of Parameters=8B2025.1155.4
Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.1151.8
InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.1151.7
MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.1150.9
Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.1150.9
LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.1148.4
InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.1148.4
InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.1147.4
InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.1145.5
LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.1143