High-level planning on VLABench vlm_evaluation 1.0 (test)
85.8AUC
Oracle
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 85.8 | |
2026.06 | 81.92 | |
2026.06 | 81.77 | |
2026.06 | 79.97 | |
2026.06 | 76.99 | |
2026.06 | 59.57 | |
2026.06 | 57.32 | |
2026.06 | 56.34 | |
2026.06 | 55.47 | |
2026.06 | 48.22 | |
2026.06 | 48.22 | |
2026.06 | 47.95 | |
2026.06 | 47.94 | |
2026.06 | 46.6 | |
2026.06 | 46.32 | |
2026.06 | 45.75 | |
2026.06 | 45.64 | |
2026.06 | 44.57 | |
2026.06 | 44.27 | |
2026.06 | 43.62 | |
2026.06 | 42.07 | |
2026.06 | 40.95 | |
2026.06 | 36.05 | |
2026.06 | 32.95 | |
2026.06 | 32.79 |