Question Answering on TriviaQA (EM, Tokens(k))
81.43EMGPT-4o-mini
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GPT-4o-minizero-shot-CoT=true, pass@1=true2026.01 | 81.43 | 0.69 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive stronger US (gpt-4o-mini)2026.01 | 45.51 | 0.68 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=interactive2026.01 | 25.56 | 0.64 | |
| PIRzero-shot-CoT=true, pass@1=true, mode=self-play2026.01 | 20.12 | 0.9 | |
| Reasoning Basezero-shot-CoT=true, pass@1=true2026.01 | 19.77 | 1.29 |