List your company
ResearchFormerly WizWand

Visual Math Reasoning on MathVision

72ScoreGPT-5-Thinking
14.829.6544.559.35Sep 30, 2025Oct 2, 2025Oct 5, 2025Oct 8, 2025Oct 10, 2025Oct 13, 2025Oct 16, 2025
Updated 6mo ago

Evaluation results

MethodLinks
GPT-5-ThinkingModel Category=Close-source Models2025.0972
Gemini-2.5-ProModel Category=Close-source Models2025.0969.1
QvQ-72B-PreviewModel Category=Open-source Models2025.1034.9
VAPO-Thinker-7BModel Category=Our Models2025.0931.9
R1-OneVision-7BModel Category=Open-source Models2025.0929.9
R1-Onevision-7BModel Category=Reasoning Fine-tuning Methods2025.1029.9
X-REASONERModel Category=Reasoning Fine-tuning Methods2025.1029.6
InternVL3-8BModel Category=Open-source Models2025.1028.6
Vision-R1-7BModel Category=Open-source Models2025.0928.2
DRIFTModel Category=Reasoning Fine-tuning Methods2025.1026.6
VLAA-Thinker-7BModel Category=Open-source Models2025.0926.4
InternVL2.5-8BModel Category=Open-source Models2025.0925.6
SFT BaselineModel Category=Reasoning Fine-tuning Methods2025.1025.1
Qwen2.5-VL-7BModel Category=Open-source Models, Evaluation Source=Reproduced by authors2025.1025
R1-VL-7BModel Category=Reasoning Fine-tuning Methods2025.1024.7
VAPO-Thinker-3BModel Category=Our Models2025.0923.9
Qwen2.5-VL-7BModel Category=Open-source Models2025.0923.2
OpenVLThinker-7BModel Category=Reasoning Fine-tuning Methods2025.1023
Kimi-VL-16BModel Category=Open-source Models2025.1021.8
InternVL2-8BModel Category=Open-source Models2025.1020
Qwen2-VL-7BModel Category=Open-source Models2025.1019.2
InternLM-XComposer2.5Model Category=Open-source Models2025.1017.8
LLaVA-OneVision-7BModel Category=Open-source Models2025.1017.6
InternVL2.5-8BModel Category=Open-source Models2025.1017