GUI Agent Interaction on Memory-World (test)
82.6T-AccStamp-GUI
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Stamp-GUITraining from=GUI-Owl-1.5-8B-Think, pass@k=pass@32026.05 | 82.6 | 84.2 | |
| Stamp-GUITraining from=GUI-Owl-1.5-8B-Think, pass@k=pass@12026.05 | 75.3 | 77.9 | |
| Claude-Sonnet-4.6Model Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@32026.05 | 67.7 | 98.5 | |
| Claude-Sonnet-4.6Model Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@12026.05 | 59.1 | 95.2 | |
| GPT-5.4Model Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@32026.05 | 56.7 | 89.8 | |
| Gemini-3.1-ProModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@32026.05 | 55.2 | 87.4 | |
| GPT-5.4Model Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@12026.05 | 52 | 85.4 | |
| GUI-Owl-1.5-8B-ThinkModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@32026.05 | 52 | 59.8 | |
| Gemini-3.1-ProModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@12026.05 | 49.6 | 79.6 | |
| MAI-UI-8BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@32026.05 | 45.7 | 56.7 | |
| GUI-Owl-1.5-8B-ThinkModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@12026.05 | 44.9 | 55.9 | |
| Qwen3-VL-8B-ThinkModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@32026.05 | 41.7 | 64.6 | |
| MAI-UI-8BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@12026.05 | 40.2 | 51.2 | |
| Qwen3-VL-8B-ThinkModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@12026.05 | 36.2 | 60.6 | |
| UI-Tars-1.5-7BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@32026.05 | 26.8 | 37.4 | |
| CogAgent-9BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@32026.05 | 22.1 | 26.8 | |
| UI-Venus-1.5-8BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@32026.05 | 22 | 24.4 | |
| UI-Tars-1.5-7BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@12026.05 | 20.5 | 33.9 | |
| Qwen3-VL-8B-InstructModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@32026.05 | 19.7 | 50.4 | |
| CogAgent-9BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@12026.05 | 19.7 | 24.4 | |
| UI-Venus-1.5-8BModel Category=GUI-specialized Model + History-Retention Protocol (HRP), pass@k=pass@12026.05 | 18.9 | 21.2 | |
| Qwen3-VL-8B-InstructModel Category=General-purpose Multimodal Model + Active Memory Instruction (AMI), pass@k=pass@12026.05 | 16.5 | 46.6 |