List your company

Mathematical Reasoning on AIME In-Distribution

56.6Initial F1 ScoreAutoPyVerifier
38.08842.89447.752.506Apr 24, 2026

Evaluation results

MethodLinks
AutoPyVerifierVerifier Model=GPT-5.4 mini2026.0456.673.817.2
AutoPyVerifierVerifier Model=Gemini-3.1 Pro2026.0446.762.515.8
AutoPyVerifierVerifier Model=GPT-5.42026.0438.880.141.3
AutoPyVerifierVerifier Model=Gemini-3.1 Fl2026.0438.851.512.7
AutoPyVerifierVerifier Model=Claude Hai-4.52026.0438.873.134.3