GUI Task Execution on AITZ
66.64Success RateAtlas-Pro-7B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Atlas-Pro-7BMethod Category=Specialized Models, Tuning Strategy=Parameter-tuned, Memory-augmented=false2026.01 | 66.64 | 62.18 | |
| UI-Venus-Navi-7BMethod Category=Specialized Models, Tuning Strategy=Parameter-tuned, Memory-augmented=false2026.01 | 60.27 | 70.23 | |
| NaviMastertraining_data=GUI + Embodied2025.08 | 54 | 81.14 | |
| MAGNETMethod Category=Agentic Frameworks, Tuning Strategy=Training-free / Inference-only, Backbone=Gemini-2.5-Pro, Memory-augmented=true2026.01 | 52.77 | 57.35 | |
| NaviMastertraining_data=GUI only2025.08 | 52.56 | 77.57 | |
| InfiGUI-R1-3BMethod Category=Specialized Models, Tuning Strategy=Parameter-tuned, Memory-augmented=false2026.01 | 49.49 | 55.34 | |
| GUI-R1-7B2025.08 | 49.06 | 64.98 | |
| UI-shift2025.08 | 46.78 | 73.84 | |
| GUI-R1-7BMethod Category=Specialized Models, Tuning Strategy=Parameter-tuned, Memory-augmented=false2026.01 | 44.22 | 57.21 | |
| MAGNETMethod Category=Agentic Frameworks, Tuning Strategy=Training-free / Inference-only, Backbone=Qwen2.5-VL-32B, Memory-augmented=true2026.01 | 43.5 | 43.78 | |
| Agent-SMethod Category=Agentic Frameworks, Tuning Strategy=Training-free / Inference-only, Backbone=Qwen2.5-VL-32B, Memory-augmented=true2026.01 | 42.98 | 42.87 | |
| COATMethod Category=Agentic Frameworks, Tuning Strategy=Training-free / Inference-only, Backbone=Qwen2.5-VL-32B, Memory-augmented=false2026.01 | 41.09 | 39.28 | |
| infiGUI-3B2025.08 | 40.81 | 75.42 | |
| UI-AGILE2025.08 | 38.74 | 75.89 | |
| NaviMastertraining_data=Embodied only2025.08 | 37.37 | 76.81 | |
| Aguvis2025.08 | 36.15 | 62.61 | |
| Qwen2.5VL-7B2025.08 | 33.88 | 60.79 | |
| Qwen2.5VL-7Bvariant=*2025.08 | 31.18 | 58.36 | |
| OS-Atlas-7B2025.08 | 27.58 | 58.3 | |
| GPT-4o2025.08 | 20.99 | 27.31 |