List your company

Cross-domain Reasoning on ComplexFuncBench In-Distribution

55.6Initial F1AutoPyVerifier
26.58434.11741.6549.183Apr 24, 2026

Evaluation results

MethodLinks
AutoPyVerifierVerifier Model=Gemini-3.1 Pro2026.0455.696.440.8
AutoPyVerifierVerifier Model=Gemini-3.1 Fl2026.0447.984.937
AutoPyVerifierVerifier Model=GPT-5.42026.0430.185.155
AutoPyVerifierVerifier Model=GPT-5.4 mini2026.0427.762.434.7
AutoPyVerifierVerifier Model=Claude Hai-4.52026.0427.75426.3