List your company

Step-wise Verification on WeMath

63.9Macro F1TIM-PRM
50.27653.81357.3560.887Nov 28, 2025

Evaluation results

MethodLinks
TIM-PRMModel Type=Open-source, Number of Parameters=8B2025.1163.9
GPT-4oModel Type=Proprietary2025.1163.3
Qwen3-VLModel Type=Open-source, Number of Parameters=8B2025.1162.7
Qwen2.5-VLModel Type=Open-source, Number of Parameters=72B2025.1162.3
Gemini-2.0-FlashModel Type=Proprietary2025.1158.7
GPT-4o-MiniModel Type=Proprietary2025.1158.5
Qwen3-VLModel Type=Open-source, Number of Parameters=2B2025.1158.3
TIM-PRMModel Type=Open-source, Number of Parameters=2B2025.1158
MiniCPM-V2.6Model Type=Open-source, Number of Parameters=8B2025.1157.4
LLaVA-OVModel Type=Open-source, Number of Parameters=72B2025.1157.3
MM-PRMModel Type=Open-source, Number of Parameters=8B2025.1156.5
VisualPRMModel Type=Open-source, Number of Parameters=8B2025.1155.1
Qwen2.5-VLModel Type=Open-source, Number of Parameters=7B2025.1154.2
LLaVA-OVModel Type=Open-source, Number of Parameters=7B2025.1152.5
InternVL2.5Model Type=Open-source, Number of Parameters=38B2025.1152.5
InternVL2.5Model Type=Open-source, Number of Parameters=78B2025.1152.5
InternVL2.5Model Type=Open-source, Number of Parameters=26B2025.1151.4
InternVL2.5Model Type=Open-source, Number of Parameters=8B2025.1150.8