List your company

Missing Premise Test on MIP-MATH

25AccuracyPIR
6.987211.663616.3421.0164Jan 29, 2026

Evaluation results

MethodLinks
PIRzero-shot-CoT=true, pass@1=true, mode=interactive2026.01251.38
PIRzero-shot-CoT=true, pass@1=true, mode=interactive stronger US (gpt-4o-mini)2026.01251.47
GPT-4o-minizero-shot-CoT=true, pass@1=true2026.0113.761.47
PIRzero-shot-CoT=true, pass@1=true, mode=self-play2026.0113.461.79
Reasoning Basezero-shot-CoT=true, pass@1=true2026.017.683.71