GUI Agent Task Completion on DataScope V3
3.1Success Rate (SR)
GPT-5.2+ UIIns
Updated 25d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 3.1 | 9.3 | 13.2 | |
2026.06 | 3.1 | 6.3 | 8.2 | |
2026.06 | 0 | 2.6 | 4.4 | |
2026.06 | 0 | 1.6 | 1.5 | |
2026.06 | 0 | 1.6 | 1.5 | |
2026.06 | 0 | 0 | 0.7 | |
2026.06 | 0 | 2.6 | 5 | |
2026.06 | 0 | 3.7 | 4.2 | |
2026.06 | 0 | 0 | 0.5 | |
2026.06 | 0 | 1.6 | 1.5 |