Negative Query Recognition on CoMET-Bench
68.1Rej.-F1
CoMET-Agent (Gemini 3 Flash)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 68.1 | 5.8 | |
2026.06 | 66.5 | 6.4 | |
2026.06 | 64.7 | 16.8 | |
2026.06 | 61.5 | 51.7 | |
2026.06 | 61 | 9.5 | |
2026.06 | 60.8 | 37.3 | |
2026.06 | 60.6 | 5.3 | |
2026.06 | 57.4 | 8 | |
2026.06 | 52.1 | 5.3 | |
2026.06 | 48.9 | 58.5 | |
2026.06 | 47.2 | 5.9 | |
2026.06 | 40.3 | 9.1 | |
2026.06 | 39.9 | 14.6 | |
2026.06 | 12.1 | 93.5 | |
2026.06 | 9.3 | 2.6 | |
2026.06 | 8.8 | 3.8 | |
2026.06 | 5.6 | 97.1 | |
2026.06 | 2.5 | 98.8 | |
2026.06 | 1.7 | 99.1 | |
2026.06 | 1.2 | 99.4 | |
2026.06 | 0 | 100 |