Long-context Multi-modal Understanding on MMLongBench
27.49Text Accuracy
VISOR
Updated 6d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.04 | 27.49 | 23.96 | 27.53 | 23.79 | 22.88 | 28.45 | |
2026.04 | 27.14 | 28.64 | 25.13 | 24.83 | 17.8 | 28.34 | |
2026.04 | 26.8 | 27.65 | 24.72 | 22.41 | 19.49 | 27.98 | |
2026.04 | 26.8 | 23.5 | 21.91 | 25.17 | 21.19 | 25.74 | |
2026.04 | 26.8 | 23.96 | 26.97 | 23.45 | 22.03 | 27.86 | |
2026.04 | 26.46 | 23.5 | 22.47 | 28.28 | 16.95 | 26.92 | |
2026.04 | 26.1 | 26.3 | 24.8 | 25.9 | 21.2 | - | |
2026.04 | 24.4 | 23.96 | 21.91 | 24.14 | 20.34 | 25.5 | |
2026.04 | 22.7 | 16.1 | 21.9 | 21.4 | 19.5 | - | |
2026.04 | 19.9 | 13.4 | 12.9 | 11.4 | 10.2 | - | |
2026.04 | 16.84 | 17.97 | 19.1 | 18.28 | 11.86 | 18.42 | |
2026.04 | 13.1 | 14.7 | 15.9 | 4.3 | 7.6 | - | |
2026.04 | 10.1 | 12.4 | 10.2 | 6.2 | 7.1 | - | |
2026.04 | 8.5 | 7.8 | 7.9 | 9.3 | 7.6 | - | |
2026.04 | 7.9 | 6.91 | 5.06 | 8.97 | 7.63 | 8.5 | |
2026.04 | 2.7 | 3.6 | 3.4 | 3.1 | 5.1 | - | |
2026.04 | 2.2 | 4.1 | 5.2 | 4.7 | 4.3 | - |