Multi-image Spatial Reasoning on SPAR-Bench-MV + MindCube-Tiny + MMSI-Bench (test)
51Overall Score
GPT-5.2
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 51 | |
2026.02 | 44.9 | |
2026.02 | 43.6 | |
2026.02 | 40.7 | |
2026.02 | 36.5 | |
2026.02 | 35.5 | |
2026.02 | 35.4 | |
2026.02 | 34.2 | |
2026.02 | 33.8 | |
2026.02 | 33.7 | |
2026.02 | 31.9 | |
2026.02 | 30.7 | |
2026.02 | 30.4 | |
2026.02 | 30.3 | |
2026.02 | 29.4 |