Robust GUI Navigation on GUI-RobustEval
55.8Success Rate (Depth 0)Jedi-7B w/ GPT 5.1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Jedi-7B w/ GPT 5.1Model Category=Proprietary Models2026.05 | 55.8 | 44.2 | 32.2 | 29.1 | 34.6 | |
| Qwen3-VL-PlusModel Category=Proprietary Models2026.05 | 55.1 | 46.1 | 36.9 | 33.5 | 65.4 | |
| Qwen3-VL-FlashModel Category=Proprietary Models2026.05 | 54.9 | 44.6 | 34.5 | 32.1 | 63.9 | |
| RoTS-32BModel Category=Open-Source Models2026.05 | 49.7 | 41.8 | 36.5 | 33.2 | 58.8 | |
| Qwen3-VL-8B-InstructModel Category=Open-Source Models2026.05 | 48.1 | 38.7 | 30 | 25 | — | |
| OpenCUA-32BModel Category=Open-Source Models2026.05 | 45.5 | 37.2 | 28.6 | 25.9 | 50.3 | |
| RoTS-7BModel Category=Open-Source Models2026.05 | 43.5 | 36.6 | 30.1 | 26.7 | 51.9 | |
| OpenCUA-7BModel Category=Open-Source Models2026.05 | 40.7 | 30.3 | 23.3 | 19 | 46.3 | |
| UI-TARS1.5-7BModel Category=Open-Source Models2026.05 | 39.6 | 34.2 | 27.8 | 23.3 | 38 | |
| GUI-Owl-7BModel Category=Open-Source Models2026.05 | 28.7 | 15.6 | 8.1 | 10.4 | 5.9 | |
| GPT 5.1Model Category=Proprietary Models2026.05 | 23.4 | 16.5 | 13.1 | 11.2 | 33.9 | |
| Qwen2.5-VL-7B-InstructModel Category=Open-Source Models2026.05 | 5.1 | 3 | 2.9 | 1.3 | — |