Document Question Answering on MMLongBench-Doc
65.8Accuracy
Human Baseline
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.01 | 65.8 | 66 | - | |
2026.01 | 57.3 | 54.1 | - | |
2026.01 | 57 | 56.8 | 67.6 | |
2026.01 | 56.3 | 55.3 | 65.9 | |
2026.01 | 54.4 | 53.9 | 65.3 | |
2026.01 | 52.3 | 50.8 | 59.2 | |
2026.01 | 51.8 | 49.1 | - | |
2026.01 | 48.4 | 49.2 | 59.4 | |
2026.01 | 47.4 | - | - | |
2026.01 | 42.8 | 44.9 | - | |
2026.01 | 42.8 | - | - | |
2026.01 | 42 | - | - | |
2026.01 | 39.6 | 37.2 | - | |
2026.01 | 38.1 | 38.3 | - | |
2026.01 | 32.2 | 30.8 | - | |
2026.01 | 31.4 | 36.5 | - | |
2026.01 | 30.1 | 30.5 | - | |
2026.01 | 29 | 27.8 | - | |
2026.01 | - | - | 58.1 | |
2026.01 | - | - | 58.6 | |
2026.01 | - | - | 56.6 | |
2026.01 | - | - | 63.3 | |
2026.01 | - | - | 67.6 |