| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Vicuna Bench (test) | TRACT | Kendall's Tau0.468 | 5 | 1mo ago | |
| FLASK (test) | Kendall's Tau0.385 | 5 | 1mo ago | ||
| Feedback Bench (test) | TRACT | Kendall's Tau0.805 | 5 | 1mo ago | |
| SPLASH (dev) | Feedback Evaluator | MRR0.88 | 3 | 1mo ago | |
| DRS-BENCH IDD | AGENTIC-DRS | Human Score0.742 | 2 | 1mo ago | |
| DRS-BENCH Afixa | AGENTIC-DRS | Human Score73.6 | 2 | 1mo ago | |
| DRS-BENCH Infographic | AGENTIC-DRS | Human Score70.8 | 2 | 1mo ago | |
| DRS-BENCH GDE | AGENTIC-DRS | Human Score0.762 | 2 | 1mo ago |