Operating System Control on AgentBench OS
34.7Accuracy
OpenHands CodeActAgent
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.10 | 34.7 | |
2025.10 | 27.8 | |
2025.10 | 27.1 | |
2025.10 | 21.5 | |
2025.10 | 20.8 | |
2025.10 | 18.1 | |
2025.10 | 17.4 | |
2025.10 | 9 | |
2025.10 | 9 | |
2025.10 | 8.3 | |
2025.10 | 3.5 | |
2025.10 | 2.8 |