Web agent task completion on GoBrowse
90.4Success Rate
CATTS (∆, best τ)
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 90.4 | 372,000 | |
2026.02 | 90.2 | 422,000 | |
2026.02 | 88.3 | 443,000 | |
2026.02 | 88 | 481,000 |
CATTS (∆, best τ)
| Method | Links | ||
|---|---|---|---|
2026.02 | 90.4 | 372,000 | |
2026.02 | 90.2 | 422,000 | |
2026.02 | 88.3 | 443,000 | |
2026.02 | 88 | 481,000 |