Windows Agent Task Completion on WindowsAgentArena (original)
2.3Office Success RatePC Agent-E
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| PC Agent-EBase Model=Qwen2.5-VL-72B2025.05 | 2.3 | 33.1 | 70.6 | 37.5 | 33.3 | 25 | 27.9 | |
| NAVIFramework=GPT-4V + Omniparser2025.05 | 0 | 27.3 | 33.3 | 27.3 | 30.3 | 8.3 | 19.5 |