Computer-use Task Execution on Thunderbird
57.8Success Rate
ACuRL
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 57.8 | |
2026.02 | 51.1 | |
2026.02 | 51.1 | |
2026.02 | 51.1 | |
2026.02 | 48.9 | |
2026.02 | 48.9 | |
2026.02 | 48.9 | |
2026.02 | 46.7 | |
2026.02 | 46.7 | |
2026.02 | 44.5 | |
2026.02 | 44.5 | |
2026.02 | 44.5 | |
2026.02 | 44.4 | |
2026.02 | 42.2 | |
2026.02 | 42.2 | |
2026.02 | 42.2 | |
2026.02 | 40 | |
2026.02 | 37.8 | |
2026.02 | 35.5 |