List your company

STEM Reasoning on MathVision

69.96AccuracyCodePercept-32B-S1
50.938455.876760.81565.7533Mar 11, 2026

Evaluation results

MethodLinks
CodePercept-32B-S1LLM Solver=Qwen3-235A22-Thinking2026.0369.96
Gemini2.5-ProLLM Solver=Qwen3-30A3-Thinking2026.0366.8
CodePercept-8B-S1LLM Solver=Qwen3-235A22-Thinking2026.0366.45
CodePercept-4B-S1LLM Solver=Qwen3-235A22-Thinking2026.0364.71
Qwen3-VL-32B-InstructLLM Solver=Qwen3-235A22-Thinking2026.0362.66
CodePercept-32B-S1LLM Solver=Qwen3-30A3-Thinking2026.0362.27
Qwen3-VL-235A22B-InstructLLM Solver=Qwen3-30A3-Thinking2026.0360.43
GPT5-ThinkingLLM Solver=Qwen3-30A3-Thinking2026.0360.03
Qwen3-VL-4B-InstructLLM Solver=Qwen3-235A22-Thinking2026.0359.8
Qwen3-VL-8B-InstructLLM Solver=Qwen3-235A22-Thinking2026.0359.67
Claude-Opus 4.1-ThinkingLLM Solver=Qwen3-30A3-Thinking2026.0359.61
CodePercept-8B-S1LLM Solver=Qwen3-30A3-Thinking2026.0359.31
Qwen3-VL-32B-InstructLLM Solver=Qwen3-30A3-Thinking2026.0358.55
CodePercept-4B-S1LLM Solver=Qwen3-30A3-Thinking2026.0357.63
Qwen3-VL-8B-InstructLLM Solver=Qwen3-30A3-Thinking2026.0354.37
Qwen3-VL-4B-InstructLLM Solver=Qwen3-30A3-Thinking2026.0354.21
Qwen2.5-VL-72BLLM Solver=Qwen3-30A3-Thinking2026.0354.14
KeyeVL1.5-8BLLM Solver=Qwen3-30A3-Thinking2026.0354.11
GLM-4.1V-9BLLM Solver=Qwen3-30A3-Thinking2026.0353.75
Qwen3-VL-30A3B-InstructLLM Solver=Qwen3-30A3-Thinking2026.0353.59
InternVL3.5-8BLLM Solver=Qwen3-30A3-Thinking2026.0353.32
MiniCPM-V-4.5LLM Solver=Qwen3-30A3-Thinking2026.0353.15
Intern-S1-8BLLM Solver=Qwen3-30A3-Thinking2026.0351.67