OS GUI Agentic Task Execution on OSWorld 361 tasks (Verified)
65.84Average Success Rate
OS-SYMPHONY w/ GPT-5
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.01 | 65.84 | 79.17 | 65.73 | 67.76 | 69.23 | 57.98 | |
2026.01 | 63.61 | 75 | 64.85 | 61.19 | 69.23 | 54.86 | |
2026.01 | 63.41 | 79.17 | 63.91 | 62.56 | 79.59 | 50.91 | |
2026.01 | 62.84 | 70.83 | 72.59 | 61.35 | 63.27 | 49.54 | |
2026.01 | 62.63 | 77.5 | 66.46 | 61.23 | 69.8 | 51.37 | |
2026.01 | 60.76 | 75 | 62.93 | 61.78 | 71.43 | 47.87 | |
2026.01 | 59.93 | 75 | 62.93 | 57.94 | 71.43 | 47.87 | |
2026.01 | 58.05 | 73.68 | 58.17 | 61.39 | 75 | 47.37 | |
2026.01 | 56.39 | 70.83 | 60.65 | 54.09 | 69.39 | 42.37 | |
2026.01 | 53.91 | 66.67 | 63.22 | 52.51 | 83.67 | 24.41 | |
2026.01 | 53.69 | 73.91 | 49.52 | 62.12 | 71.43 | 37.3 | |
2026.01 | 53.1 | 41.67 | 61.11 | 62.12 | 61.22 | 34.13 | |
| 50.23 | 70.83 | 40.97 | 66.04 | 73.08 | 31.22 | ||
2026.01 | 47.58 | 62.5 | 54.62 | 46.67 | 44.9 | 37.04 | |
| 46.86 | 58.33 | 40.94 | 53.54 | 75.1 | 31.24 | ||
2026.01 | 44.91 | 61.13 | 44.73 | 49.95 | 72.58 | 22.16 | |
2026.01 | 41.85 | 41.67 | 50.42 | 55.69 | 51.02 | 14.66 | |
2026.01 | 41 | - | - | - | - | - | |
2026.01 | 40.15 | 50 | 39.28 | 44.87 | 73.47 | 17.2 | |
| 40.11 | 50 | 36.67 | 50.62 | 61.22 | 21.96 | ||
2026.01 | 32.4 | - | - | - | - | - |