Multi-image Reasoning on MIRB
63.57Accuracy
Qwen2.5-VL
Updated 3d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 63.57 | - | |
2026.02 | 63.05 | - | |
2026.01 | 60.8 | - | |
2026.01 | 60.7 | - | |
2025.03 | 60.67 | - | |
2026.01 | 60.2 | - | |
2026.01 | 58.2 | - | |
2026.02 | 57.59 | - | |
2026.02 | 57.38 | - | |
2025.03 | 57.15 | - | |
2026.02 | 56.45 | - | |
2026.02 | 56.45 | - | |
2026.01 | 55.7 | - | |
2025.03 | 55.68 | - | |
2026.02 | 55.21 | - | |
2026.01 | 55.2 | - | |
2026.02 | 54.9 | - | |
2025.03 | 54.59 | - | |
2026.01 | 54.4 | - | |
2026.01 | 53.1 | - | |
2026.02 | 52.63 | - | |
2026.01 | 52.5 | - | |
2026.02 | 52.32 | - | |
2026.01 | 51.2 | - | |
2025.03 | 51.15 | - | |
2026.01 | 51 | - | |
2025.03 | 50.36 | - | |
2025.03 | 48.83 | - | |
2026.01 | 48.6 | - | |
2026.01 | 48.3 | - | |
2026.02 | 48.19 | - | |
2026.02 | 47.88 | - | |
2026.01 | 47.2 | - | |
2026.02 | 46.96 | - | |
2026.01 | 46.7 | - | |
2025.03 | 46.58 | - | |
2025.03 | 46.19 | - | |
2026.01 | 45.9 | - | |
2026.02 | 44.38 | - | |
2025.03 | 42.66 | - | |
2026.01 | 41.2 | - | |
2026.02 | 40.25 | - | |
2026.01 | 39.3 | - | |
2026.02 | 38.49 | - | |
2026.01 | 37.7 | - | |
2026.01 | 36.5 | - | |
2026.01 | 36 | - | |
2026.01 | 34.8 | - | |
2026.01 | 32.8 | - | |
2026.02 | 32.3 | - | |
2026.01 | 31.8 | - | |
2026.02 | 31.79 | - | |
| 30.6 | - | ||
2026.01 | 29.8 | - | |
2026.01 | 28.8 | - | |
2026.01 | 28.5 | - | |
| 28.5 | - | ||
2026.01 | 25 | - | |
2026.01 | 24.3 | - | |
2025.03 | 19.13 | - | |
2024.12 | - | 31.5 | |
2024.12 | - | 35.6 | |
2024.12 | - | 32.1 | |
2024.12 | - | 36.4 | |
2024.12 | - | 39.9 | |
2024.12 | - | 51.7 | |
2024.12 | - | 50 | |
2024.12 | - | 52.5 | |
2024.12 | - | 50.3 | |
2024.12 | - | 53.7 | |
2024.12 | - | 55.7 | |
2024.12 | - | 55.2 | |
2024.12 | - | 61.2 | |
2024.12 | - | 53.1 | |
2024.12 | - | 58.2 | |
2024.12 | - | 61.1 |