Visually Grounded Reasoning on V* Bench
95.7Average Accuracy
o3-0416
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.07 | 95.7 | - | - | |
2025.07 | 91.1 | 94 | 87 | |
2026.03 | 90.6 | 93 | 86.8 | |
2026.03 | 90 | 92.1 | 86.8 | |
2025.07 | 90 | 92.1 | 86.8 | |
2026.03 | 85.9 | 83.5 | 89.5 | |
2026.03 | 85.9 | 86.1 | 85.5 | |
2026.03 | 84.8 | 90.8 | 80.9 | |
2025.07 | 84.8 | 90.8 | 80.9 | |
2026.03 | 84.3 | 82.6 | 86.8 | |
2026.03 | 82.2 | 83.5 | 80.3 | |
2026.03 | 82.2 | 85.3 | 77.6 | |
2026.03 | 80.6 | 83.5 | 76.3 | |
2025.07 | 80.6 | 83.5 | 76.3 | |
2026.03 | 77.5 | 77.4 | 77.6 | |
2026.03 | 76.4 | 75.7 | 77.6 | |
2025.07 | 76.4 | 75.7 | 77.6 | |
2026.02 | 74.9 | 74.8 | 75 | |
2026.03 | 74.3 | 77.4 | 69.7 | |
2025.07 | 74.3 | 77.4 | 69.7 | |
2026.03 | 73.8 | 80.9 | 63.2 | |
2025.07 | 73.8 | 80.9 | 63.2 | |
2026.02 | 72.8 | 73.9 | 71.1 | |
2026.03 | 72.3 | 73 | 71.1 | |
2025.07 | 72.3 | 73 | 71.1 | |
2026.02 | 71.2 | 74.8 | 65.8 | |
2026.02 | 71.2 | 73.9 | 67.1 | |
2026.03 | 70.7 | 73 | 60.5 | |
2025.07 | 70.7 | 73 | 60.5 | |
2026.02 | 68.1 | 73 | 60.5 | |
2026.03 | 66 | - | - | |
2025.07 | 66 | - | - |