Factual Knowledge on MMLU
81.04EMGPT-4o-mini
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-4o-minizero-shot-CoT=true, pass@1=true2026.01 | 81.04 | 0.53 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive stronger US (gpt-4o-mini)2026.01 | 62.51 | 0.77 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=self-play2026.01 | 60.8 | 0.73 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive2026.01 | 60.21 | 0.76 | |
| Reasoning Basezero-shot-CoT=true, pass@1=true2026.01 | 60.12 | 1.15 |