GUI Content Understanding on MMBench-GUI L1 Hard Level
93.33Performance on Windows (GUI L1 Hard)GUI-CIDER-8B
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| GUI-CIDER-8BParameters=8B2026.05 | 93.33 | 90.48 | 94.33 | 92.17 | 88.2 | 93.15 | 91.83 | |
| InternVL3-72BParameters=72B2026.05 | 75.08 | 77.44 | 76.19 | 70.37 | 75.73 | 78.11 | 75.7 | |
| Qwen2.5-VL-72BParameters=72B2026.05 | 70.68 | 68.91 | 70.98 | 57.59 | 53.94 | 68.1 | 64.56 | |
| Qwen-Max-VL2026.05 | 66.64 | 67.59 | 65.8 | 60.23 | 58.78 | 65.34 | 63.69 | |
| GPT-4o2026.05 | 60.69 | 60.38 | 52.42 | 45.27 | 50.93 | 50.83 | 53.49 | |
| UI-TARS-72B-DPOParameters=72B, Training=DPO2026.05 | 31.48 | 35.87 | 24.19 | 36.33 | 58.13 | 19.94 | 35.78 |