List your company
ResearchFormerly WizWand

General GUI navigation on OS-Genesis

62.3Web Task Success RateRISK-R1-7B
-1.1415.3331.848.27Sep 26, 2025
Updated 6mo ago

Evaluation results

MethodLinks
RISK-R1-7BModel Category=Ours, Base Model=Qwen2.5-VL-7B-Instruct, Training Type=RFT2025.0962.3
RISK-SFT-7BModel Category=Ours, Base Model=Qwen2.5-VL-7B-Instruct, Training Type=SFT2025.0961.5
GPT-4oModel Category=Commercial Models2025.0955.3
Qwen-VL-MaxModel Category=Commercial Models2025.0950.3
Qwen2.5-VL-72BModel Category=General Open-source Models2025.0950
Qwen2.5-VL-7BModel Category=General Open-source Models2025.0932.2
Aguvis-7BModel Category=GUI-specific Models (SFT)2025.0929.7
InternVL3-8BModel Category=General Open-source Models2025.0929.5
GUI-R1-7BModel Category=GUI-specific Models (RL)2025.0928
UI-TARS-1.5-7BModel Category=GUI-specific Models (RL)2025.0926.5
GUI-R1-3BModel Category=GUI-specific Models (RL)2025.0924.3
OS-Atlas-7BModel Category=GUI-specific Models (SFT)2025.0923
GUI-G1-3BModel Category=GUI-specific Models (RL)2025.0919.1
UI-Venus-Navi-7BModel Category=GUI-specific Models (RL)2025.0914.3
InfiGUI-R1-3BModel Category=GUI-specific Models (RL)2025.0910.6
UI-TARS-72BModel Category=GUI-specific Models (SFT)2025.095.8
UI-TARS-7BModel Category=GUI-specific Models (SFT)2025.094.2
ShowUI-2BModel Category=GUI-specific Models (SFT)2025.093.4
UI-TARS-2BModel Category=GUI-specific Models (SFT)2025.091.3