List your company

GUI Automation on WindowsAgentArena

44.2Success RateHiViG
30.47234.03637.641.164Jun 9, 2026

Evaluation results

MethodLinks
HiViGPolicy Backbone=Gemini-3-Flash2026.0644.2————————
HiViGPolicy Backbone=Qwen3-VL-32B-Thinking2026.0638————————
CGI (32B)Policy Backbone=Gemini-3-Flash2026.0637.9————————
CGI (8B)Policy Backbone=Gemini-3-Flash2026.0637.9————————
Base agentPolicy Backbone=Gemini-3-Flash2026.0635.8————————
OpenCUAPolicy Backbone=Gemini-3-Flash2026.0635.8————————
Base agentPolicy Backbone=Qwen3-VL-32B-Thinking2026.0635.7————————
OpenCUAPolicy Backbone=Qwen3-VL-32B-Thinking2026.0635.2————————
SE-WSMPolicy Backbone=Gemini-3-Flash2026.0635.1————————
GUI-Critic-R1Policy Backbone=Qwen3-VL-32B-Thinking2026.0634.4————————
CGI (32B)Policy Backbone=Qwen3-VL-32B-Thinking2026.0633.7————————
GUI-Critic-R1Policy Backbone=Gemini-3-Flash2026.0632.5————————
SE-WSMPolicy Backbone=Qwen3-VL-32B-Thinking2026.0631.6————————
CGI (8B)Policy Backbone=Qwen3-VL-32B-Thinking2026.0631————————
Agent SBase Model=GPT-4o2025.02—013.345.829.219.122.2——
Agent S2Base Model=Claude-3.7-Sonnet2025.02—716.454.262.528.633.3——
Agent S3Step=50, Backbone=GPT-52026.01————————54.1
Agent S3Step=100, Backbone=GPT-52026.01————————56.6
GPT-4o2025.02—013.729.2010.30——
GPT-4o-mini2025.02—014.98.3000——
NAVI2025.02—027.333.327.330.38.3——
OS-SYMPHONYStep=50, Backbone=Qwen3-VL-32B-Inst.2026.01—26.1946.337547.3727.941.6769.2345.32
OS-SYMPHONYStep=50, Backbone=GPT-5-Mini2026.01—42.867379.1768.4248.6666.6769.2362.15
OS-SYMPHONYStep=50, Backbone=GPT-52026.01—54.76737542.1170.097553.8563.45
Phi3-V2025.02—06.98.306.20——
Qwen3-VL-32B-InstructStep=502026.01—19.0549.6654.1721.0542.1925031.68
UI-TARS-1.5-7BStep=502026.01————————42.1
UI-TARS-2Step=502026.01————————50.6
WorldGUI-AgentBase Model=Claude-3.5-Sonnet2025.02—753.345.833.328.633.3——