Abstention on ABSTAINEQA HM3D-380
71.1F1 Score
SEMANTIC FLIP
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 71.1 | 66.84 | 81.58 | 52.11 | |
2026.06 | 67.46 | 56.84 | 89.47 | 24.21 | |
2026.06 | 67.41 | 53.95 | 95.26 | 12.63 | |
2026.06 | 30.99 | 56.54 | 19.6 | 93.44 |
SEMANTIC FLIP
| Method | Links | ||||
|---|---|---|---|---|---|
2026.06 | 71.1 | 66.84 | 81.58 | 52.11 | |
2026.06 | 67.46 | 56.84 | 89.47 | 24.21 | |
2026.06 | 67.41 | 53.95 | 95.26 | 12.63 | |
2026.06 | 30.99 | 56.54 | 19.6 | 93.44 |