List your company

Mathematical Reasoning on AIMO3 competition

43ScoreSTOP
38.8439.924142.08Apr 17, 2026

Evaluation results

MethodLinks
STOPbase_model=GPT-OSS-120B, budget=16→82026.0443
STOPbase_model=GPT-OSS-120B, budget=24→82026.0442
Baseline + Toolbase_model=GPT-OSS-120B2026.0439