Task Goal Completion on AppWorld Easy normal 57 tasks (test)
73.7Accuracy
LRE
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 73.7 | 5.97 | 0 | |
2026.06 | 59.6 | 4.98 | 0 | |
2026.06 | 57.9 | 6.51 | 0 | |
2026.06 | 57.9 | 4.67 | 3.19 |
LRE
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 73.7 | 5.97 | 0 | |
2026.06 | 59.6 | 4.98 | 0 | |
2026.06 | 57.9 | 6.51 | 0 | |
2026.06 | 57.9 | 4.67 | 3.19 |