Computer Use on Windows Agent Arena (test)
42.1Success RateUI-TARS 1.5
Evaluation results
| Method | Links | |
|---|---|---|
| UI-TARS 1.52025.05 | 42.1 | |
| Seed 1.5-VL2025.05 | 39.6 | |
| Claude 3.7 Sonnet2025.05 | 38.9 | |
| Kimi VL-A3B2025.05 | 10.4 |
| Method | Links | |
|---|---|---|
| UI-TARS 1.52025.05 | 42.1 | |
| Seed 1.5-VL2025.05 | 39.6 | |
| Claude 3.7 Sonnet2025.05 | 38.9 | |
| Kimi VL-A3B2025.05 | 10.4 |