Spatial Reasoning on RealWorldQA
69.67Accuracy
Full Model
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 69.67 | |
2026.02 | 69.28 | |
2026.02 | 67.45 | |
2025.12 | 65.9 | |
2025.12 | 62.2 | |
2025.12 | 57.3 | |
2025.12 | 56.25 | |
2026.02 | 55.42 | |
2026.02 | 55.29 | |
2025.12 | 55.28 | |
2025.12 | 55.26 | |
2025.12 | 55.21 | |
2025.12 | 55.12 | |
2026.02 | 54.64 | |
2025.12 | 54.51 | |
2025.12 | 54.5 | |
2025.12 | 54.44 | |
2025.12 | 54.4 | |
2025.12 | 53.5 | |
2025.12 | 53.3 | |
2026.02 | 53.07 | |
2025.12 | 52.94 | |
2025.12 | 52.28 | |
2025.12 | 49.74 | |
2025.12 | 47.3 | |
2025.12 | 47.3 | |
2025.12 | 46.9 | |
2025.12 | 43.2 | |
2025.12 | 42.75 | |
2026.02 | 32.55 | |
2026.02 | 5.23 | |
2026.02 | 0.39 |