Trajectory completion judgment on OGRBench MacOS
93.5Accuracy
OS-Themis
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 93.5 | 83.9 | |
2026.06 | 93.5 | 84.9 | |
2026.06 | 92.2 | 84.2 | |
2026.06 | 90.9 | 82.1 | |
2026.06 | 90.9 | 77.4 | |
2026.06 | 90.9 | 80 | |
2026.06 | 90.9 | 80 | |
2026.06 | 89.6 | 79 | |
2026.06 | 89.6 | 73.3 | |
2026.06 | 89.6 | 73.3 | |
2026.06 | 89.6 | 80 | |
2026.06 | 85.7 | 66.7 | |
2026.06 | 85.7 | 71.8 | |
2026.06 | 83.1 | 31.6 | |
2026.06 | 83.1 | 51.9 | |
2026.06 | 81.8 | 22.2 | |
2026.06 | 80.5 | 11.8 | |
2026.06 | 80.5 | 11.8 | |
2026.06 | 80.5 | 65.1 | |
2026.06 | 71.4 | 57.7 |