Hallucination Evaluation on AMBER Generative Task
67.1Coverage
GPT-4V
Updated 8d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.05 | 67.1 | 30.7 | 2.6 | 4.6 | |
2026.05 | 56.1 | 19.4 | 1.4 | 3.4 | |
2026.05 | 55.7 | 22.5 | 1.9 | 4.1 | |
2026.05 | 53.8 | 45.8 | 5.6 | 11 | |
2026.05 | 53.2 | 18.5 | 1.6 | 3.5 | |
2026.05 | 52.6 | 30.4 | 3.2 | 6.4 | |
2026.05 | 52.4 | 24.5 | 2.4 | 4.4 | |
2026.05 | 51.5 | 16.6 | 1.3 | 3.3 | |
2026.05 | 50.5 | 39.1 | 4.6 | 8.5 | |
2026.05 | 50.3 | 16.1 | 1 | 3 | |
2026.05 | 50.2 | 37.3 | 4.3 | 8.8 | |
2026.05 | 49.7 | 27.3 | 2.7 | 5.6 | |
2026.04 | 49.2 | 23.4 | 1.2 | - | |
2026.04 | 48.5 | 22.2 | 1.3 | - | |
2026.05 | 47.9 | 11.6 | 0.9 | 2.2 | |
2026.05 | 47.3 | 13.4 | 1.2 | 2.1 | |
2026.05 | 46.1 | 25.1 | 2.1 | 6.3 | |
2026.05 | 45.9 | 32.1 | 4.1 | 8.1 | |
2026.04 | 45 | 31.8 | 2.6 | - | |
2026.04 | 44.5 | 31 | 2.2 | - | |
2026.04 | 44.4 | 31.8 | 2.6 | - | |
2026.04 | 42.4 | 31 | 2.2 | - | |
2026.04 | 41.5 | 36.3 | 3.1 | - | |
2026.04 | 40.5 | 5.6 | 0.4 | - | |
2026.04 | 39.6 | 10.4 | 0.5 | - | |
2026.04 | 38 | 44.5 | 31 | - |