| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TRAIL SWEBench 31 traces | RAFFLES | Precision45.16 | 16 | 1mo ago | |
| TRAIL (GAIA) 117 traces | SAFARI | Precision63.25 | 16 | 1mo ago | |
| Who&When Hand (58 traces) | RAFFLES | Top Accuracy31 | 16 | 1mo ago | |
| Who&When Algo (126 traces) | RAFFLES | Accuracy49.2 | 16 | 1mo ago |