List your company

Visual Mathematical Reasoning on DynaMath

81.42AccuracyGemini2.5-Pro
17.959234.434650.9167.3854Jan 5, 2026Jan 15, 2026Jan 26, 2026Feb 6, 2026Feb 17, 2026Feb 28, 2026Mar 11, 2026

Evaluation results

MethodLinks
Gemini2.5-ProLLM Solver=Qwen3-30A3-Thinking [53]2026.0381.42
CodePercept-32B-S1LLM Solver=Qwen3-235A22-Thinking [53]2026.0379.5
CodePercept-32B-S1LLM Solver=Qwen3-30A3-Thinking [53]2026.0377.41
Qwen3-VL-235A22B-InstructLLM Solver=Qwen3-30A3-Thinking [53]2026.0377.39
Qwen3-VL-32B-InstructLLM Solver=Qwen3-30A3-Thinking [53]2026.0375.78
Qwen3-VL-32B-InstructLLM Solver=Qwen3-235A22-Thinking [53]2026.0375.54
CodePercept-8B-S1LLM Solver=Qwen3-235A22-Thinking [53]2026.0375.05
Qwen3-VL-8B-InstructLLM Solver=Qwen3-235A22-Thinking [53]2026.0373.69
Claude-Opus 4.1-ThinkingLLM Solver=Qwen3-30A3-Thinking [53]2026.0373.25
CodePercept-8B-S1LLM Solver=Qwen3-30A3-Thinking [53]2026.0373.2
CodePercept-4B-S1LLM Solver=Qwen3-235A22-Thinking [53]2026.0372.4
Qwen3-VL-8B-InstructLLM Solver=Qwen3-30A3-Thinking [53]2026.0372.19
Qwen3-VL-30A3B-InstructLLM Solver=Qwen3-30A3-Thinking [53]2026.0371.67
CodePercept-4B-S1LLM Solver=Qwen3-30A3-Thinking [53]2026.0371.38
Qwen3-VL-4B-InstructLLM Solver=Qwen3-235A22-Thinking [53]2026.0371.22
GPT5-ThinkingLLM Solver=Qwen3-30A3-Thinking [53]2026.0371
Qwen3-VL-4B-InstructLLM Solver=Qwen3-30A3-Thinking [53]2026.0369.4
Qwen2.5-VL-72BLLM Solver=Qwen3-30A3-Thinking [53]2026.0368.28
InternVL3.5-8BLLM Solver=Qwen3-30A3-Thinking [53]2026.0368.12
GLM-4.1V-9BLLM Solver=Qwen3-30A3-Thinking [53]2026.0366.17
MiniCPM-V-4.5LLM Solver=Qwen3-30A3-Thinking [53]2026.0365.44
Intern-S1-8BLLM Solver=Qwen3-30A3-Thinking [53]2026.0363.61
KeyeVL1.5-8BLLM Solver=Qwen3-30A3-Thinking [53]2026.0362.37
GPT-52026.0160.9
Active-ZeroModel Backbone=Qwen2.5-VL-7B-Instruct2026.0259.04
VisPlayModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.98
VisionZero-CLEVRModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.7
VisionZero-RealWorldModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.62
VisionZero-ChartModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.4
Base ModelModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.26
EvoLMMModel Backbone=Qwen2.5-VL-7B-Instruct2026.0258.06
Gemini-2.5-Pro2026.0156.3
GLM-4.5V2026.0153.9
Active-ZeroModel Backbone=Qwen2.5-VL-3B-Instruct2026.0251.24
VisPlayModel Backbone=Qwen2.5-VL-3B-Instruct2026.0250.02
Base ModelModel Backbone=Qwen2.5-VL-3B-Instruct2026.0246.33
COGFLOWModel Size=7B2026.0146.2
Doubao-1.5-Pro2026.0144.9
GLM-4.1VModel Size=9B2026.0142.5
Claude-3.7-Sonnet2026.0139.7
InternVL3.5Model Size=8B2026.0137.7
Keye-VLModel Size=8B2026.0137.3
InternVL3Model Size=8B2026.0125.5
Qwen2.5-VLModel Size=8B2026.0121
OvisModel Size=8B2026.0120.4