Desktop Task Success on macOSWorld
20.3Task Success Rate
RL + corrected reward estimator (rˆt)
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
| 20.3 | ||
| 14.9 | ||
| 14.4 | ||
| 12.9 | ||
2026.06 | 8.4 |
RL + corrected reward estimator (rˆt)
| Method | Links | |
|---|---|---|
| 20.3 | ||
| 14.9 | ||
| 14.4 | ||
| 12.9 | ||
2026.06 | 8.4 |