Missing Premise Test on GSM8K MIP
0.1735AccuracyPIR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive stronger US (gpt-4o-mini)2026.01 | 0.1735 | 0.8 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive2026.01 | 0.1581 | 0.75 | |
| GPT-4o-minizero-shot-CoT=true, pass@1=true2026.01 | 0.1024 | 0.8 | |
| Reasoning Basezero-shot-CoT=true, pass@1=true2026.01 | 0.0859 | 3.07 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=self-play2026.01 | 0.0808 | 0.96 |