| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WHO&WHEN Algorithm-Generated | CORRECT | Accuracy@038.9 | 19 | 1mo ago | |
| WHO&WHEN Human-Crafted | CORRECT | Acc@017.2 | 19 | 1mo ago | |
| MMLU-Pro | CORRECT | Acc@169.1 | 4 | 1mo ago | |
| Math500 | CORRECT | Top-1 Accuracy57.1 | 4 | 1mo ago | |
| Arc | CORRECT | Top-1 Accuracy80.4 | 4 | 1mo ago | |
| WikiMQA | CORRECT | Acc@144.1 | 4 | 1mo ago | |
| Musique | CORRECT | Accuracy@138.9 | 4 | 1mo ago | |
| HotpotQA | CORRECT | Top-1 Accuracy60.9 | 4 | 1mo ago | |
| WebShop | CORRECT | Tolerant Accuracy (±1 step)24 | 2 | 1mo ago | |
| ALFWorld | CORRECT | Tolerant Accuracy (±1 step)35 | 2 | 1mo ago | |
| GAIA | CORRECT | Tolerant Accuracy (±1 step)46 | 2 | 1mo ago |