| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| OpenBookQA 1.0 (test) | TituLLM-3b-v2.0 | Accuracy35 | 33 | 1mo ago | |
| OpenBookQA | T-Free | Normalized Log Accuracy89.4 | 12 | 23d ago | |
| OpenBookQA | Score43.36 | 6 | 17d ago | ||
| RealtimeQA December 16, 2022 | EM55 | 6 | 1mo ago | ||
| OBQA | Dual | Normalized PLL Score12.8 | 4 | 1mo ago |