High-Resolution Visual Reasoning on HR-Bench (4K/8K configurations)
81Score (4K)
MAPO
Updated 2d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 81 | 78.6 | 79.8 | |
2026.04 | 78.5 | 77 | 77.8 | |
2026.04 | 78.3 | 76.5 | 77.4 | |
2026.04 | 78.1 | 76.1 | 77.1 | |
2026.04 | 77.9 | 73.8 | 75.9 | |
2026.04 | 77.4 | 76 | 76.7 | |
2026.04 | 77 | 72 | 74.5 | |
2026.04 | 75.4 | 72.8 | 74.1 | |
2025.12 | 75 | 69.75 | 72.38 | |
2026.04 | 74.9 | 71.2 | 73 | |
2026.04 | 74.6 | 72 | 73.3 | |
2026.04 | 74.6 | 71 | 72.8 | |
2026.04 | 74 | 68.2 | 71.1 | |
2025.12 | 73.5 | 71.5 | 72.5 | |
2025.12 | 70.62 | 66.75 | 68.69 | |
2026.05 | 70.5 | 61.88 | 66.19 | |
2026.05 | 70.25 | 61.38 | 65.82 | |
2025.12 | 69.6 | 69.3 | 69.45 | |
2026.05 | 69.25 | 62 | 65.63 | |
2025.12 | 68.75 | 63.25 | 66 | |
2025.12 | 68.5 | 62.25 | 65.38 | |
2026.05 | 68 | 61.75 | 64.88 | |
2026.05 | 67.37 | 60.88 | 64.13 | |
2026.04 | 67.3 | 61.4 | 64.3 | |
2026.05 | 66.63 | 60.25 | 63.44 | |
2026.05 | 63.88 | 55.25 | 59.56 | |
2025.12 | 63 | 59.8 | 61.4 | |
2025.12 | 59 | 59 | 59 | |
2026.05 | 59 | 55.5 | 57.25 | |
2026.05 | 51.13 | 50.13 | 50.63 |