| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TQA (TriviaQA) (test) | AGAR | F1 Score68.4 | 18 | 1mo ago | |
| SimpleQA | DINCO | ECE7.9 | 18 | 4mo ago | |
| SimpleQA | CheckRLM | F1 Score40 | 14 | 22d ago | |
| SAGE Web Search | Accuracy (Com. Sci.)63.3 | 12 | 4mo ago | ||
| SimpleQA | CO-LMLM-360M-FW | Accuracy21.7 | 11 | 16d ago | |
| PopQA | CO-LMLM-360M-FW | Accuracy50.6 | 11 | 16d ago | |
| TriviaQA | Accuracy45.1 | 11 | 16d ago | ||
| TQA | AGAR | F1 Score77.3 | 9 | 1mo ago | |
| Trivia QA | Rewarding Doubt* | AUROC85.9 | 7 | 2mo ago | |
| Short-form QA Aggregate (Avg.) (test) | VSPO + PRS_short | EM35.93 | 5 | 4mo ago | |
| Bamboogle (test) | VSPO + PRS_short | EM0.3489 | 5 | 4mo ago | |
| Musique (test) | VSPO + PRS_short | EM13.67 | 5 | 4mo ago | |
| 2wiki (test) | PPO + PRS_short | EM26.5 | 5 | 4mo ago | |
| PopQA (test) | VSPO + PRS_short | Exact Match36.34 | 5 | 4mo ago | |
| TriviaQA (test) | VSPO + PRS_short | Exact Match50 | 5 | 4mo ago | |
| Natural Questions (NQ) (test) | VSPO + PRS_short | EM36 | 5 | 4mo ago |