GUI navigation on AndroidWorld latest (test)
78.9Success RateXiaomi-GUI-0-30B-A3B
Evaluation Results
| Method | Links | |
|---|---|---|
| Xiaomi-GUI-0-30B-A3Bparameters=30B-A3B2026.06 | 78.9 | |
| UI-Venus-1.5-30B-A3Bparameters=30B-A3B2026.06 | 77.6 | |
| MAI-UI-235B-A22BParas.=235B2025.12 | 76.7 | |
| UI-Venus-1.5-8Bparameters=8B2026.06 | 73.7 | |
| UI-Tars-2Paras.=230B2025.12 | 73.3 | |
| MAI-UI-32BParas.=32B2025.12 | 73.3 | |
| UI-TARS-22026.06 | 73.3 | |
| GUI-Owl-1.5-8B-Thinkingparameters=8B, mode=Thinking2026.06 | 71.6 | |
| Seed1.82025.12 | 70.7 | |
| MAI-UI-8BParas.=8B2025.12 | 70.7 | |
| Seed 1.82026.06 | 70.7 | |
| MAI-UI-8Bparameters=8B2026.06 | 70.7 | |
| GUI-Owl-1.5-32B-Instructparameters=32B, mode=Instruct2026.06 | 69.8 | |
| GUI-Owl-1.5-32B-Thinkingparameters=32B, mode=Thinking2026.06 | 69.8 | |
| Gemini-2.5-Pro2025.12 | 69.7 | |
| GUI-Owl-1.5-8B-Instructparameters=8B, mode=Instruct2026.06 | 69 | |
| Step-GUI-8BParas.=8B2025.12 | 67.7 | |
| Step-GUI-8Bparameters=8B2026.06 | 67.7 | |
| GUI-Owl-7BParas.=7B2025.12 | 66.4 | |
| UI-Venus-Navi-72BPlanner=false, A11y Tree=false, Screenshot=true2026.01 | 65.9 | |
| UI-Venus-72BParas.=72B2025.12 | 65.9 | |
| UI-TARS-1.5Planner=false, A11y Tree=false, Screenshot=true2026.01 | 64.2 | |
| UI-Tars-1.52025.12 | 64.2 | |
| UI-TARS-1.52026.06 | 64.2 | |
| Qwen3-VL-235B-A22BParas.=235B2025.12 | 63.7 | |
| SeedVL-1.5Planner=false, A11y Tree=true, Screenshot=true2026.01 | 62.1 | |
| Seed1.5-VL2025.12 | 62.1 | |
| Qwen3-VL-32BParas.=32B2025.12 | 57.3 | |
| GLM-4.5vPlanner=false, A11y Tree=false, Screenshot=true2026.01 | 57 | |
| OmegaUsePlanner=false, A11y Tree=false, Screenshot=true2026.01 | 55.7 | |
| OpenAI CUA (o3)2026.06 | 52.5 | |
| UI-Venus-Navi-7BPlanner=false, A11y Tree=false, Screenshot=true2026.01 | 49.1 | |
| UI-Venus-7BParas.=7B2025.12 | 49.1 | |
| MAI-UI-2BParas.=2B2025.12 | 49.1 | |
| Qwen3-VL-8BParas.=8B2025.12 | 47.6 | |
| UI-TARS-72BPlanner=false, A11y Tree=false, Screenshot=true2026.01 | 46.6 | |
| UI-Tars-SFT-72BParas.=72B2025.12 | 46.6 | |
| Aria-UIPlanner=true, A11y Tree=false, Screenshot=true2026.01 | 44.8 | |
| ScaleTrackPlanner=false, A11y Tree=true, Screenshot=false2026.01 | 44 | |
| UGroundPlanner=true, A11y Tree=false, Screenshot=true2026.01 | 44 | |
| Qwen3-VL-2BParas.=2B2025.12 | 36.4 | |
| Qwen2.5-VL-72BPlanner=false, A11y Tree=false, Screenshot=true2026.01 | 35 | |
| UI-Tars-7BParas.=7B2025.12 | 33 | |
| GPT-4oPlanner=false, A11y Tree=true, Screenshot=false2026.01 | 30.6 | |
| UI-Tars-1.5-7BParas.=7B2025.12 | 30 | |
| Ferret-UI Lite-3BParas.=3B2025.12 | 28 | |
| GUI-Critic-R1-7BPlanner=false, A11y Tree=true, Screenshot=true2026.01 | 27.6 | |
| ScaleCUA-3BParas.=3B2025.12 | 23.7 |