List your company

Mathematical Problem Solving on IMOAnswerBench

90.6Mean ScoreGPT-5.5
79.47282.36185.2588.139Jun 11, 2026

Evaluation results

MethodLinks
GPT-5.5Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-OSS-120B2026.0690.6
Gemini 3.1 ProSearch Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-OSS-120B2026.0690
M3Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-OSS-120B2026.0681.56
Opus 4.7Search Strategy=Standalone, Generation temperature=1.0, top-p=0.95, Maximum output length=512K, Judger=GPT-OSS-120B2026.0679.9