List your company

Mathematical Proof Construction on IMOProofBench

90.85Mean ScoreGPT-5.5
64.8571.678.3585.1Jun 11, 2026

Evaluation results

MethodLinks
GPT-5.5Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-5.42026.0690.85
Gemini 3.1 ProSearch Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-5.42026.0675.71
M3Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-5.42026.0667.4
Opus 4.7Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-5.42026.0665.85