List your company

GUI Automation on OSWorld Verified (test)

61.92Overall Success RateSeed-1.8
2.099217.629633.1648.6904Oct 20, 2025Nov 7, 2025Nov 26, 2025Dec 15, 2025Jan 3, 2026Jan 22, 2026Feb 10, 2026

Evaluation results

MethodLinks
Seed-1.8Steps=1002026.0261.926353.872.36882.54970.86058.273.9
Claude-Sonnet-4.5Steps=502026.0258.156.457.76657.565.24770.866.752.969.6
UltraCUA-32B-RLModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1043.7——————————
UltraCUA-32B-SFTModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1041.5——————————
UltraCUA-32B-RLModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1041——————————
UltraCUA-32B-SFTModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1039——————————
TreeCUA-DPO-7BSteps=502026.0236.639.176.925.529.847.815.154.253.347.160.9
Claude 3.7 SonnetModel Category=General Model, Open-Source=false, Max Steps=502025.1035.8——————————
OpenCUA-32B†Model Category=Agentic Model, Open-Source=true, Max Steps=502025.1035.1——————————
TreeCUA-7BSteps=502026.0234.628.376.927.740.443.51458.333.341.247.8
Agent S2Model Category=Multi-Agent Framework, Open-Source=true, Max Steps=502025.1034.5——————————
OpenCUA-32BModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1034.1——————————
OpenCUA-32B†Model Category=Agentic Model, Open-Source=true, Max Steps=152025.1033.3——————————
OpenAI CUAModel Category=Agentic Model, Open-Source=false, Max Steps=502025.1031.3——————————
UltraCUA-7B-RLModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1030.2——————————
OpenCUA-32BModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1029.7——————————
UltraCUA-7BSteps=152026.0228.941.25013.927.155.410.63733.643.346.7
UltraCUA-7B-RLModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1028.9——————————
UltraCUA-7B-SFTModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1028.5——————————
OpenCUA-7BModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1028.2——————————
UI-TARS-1.5-7BModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1027.3——————————
Claude 3.7 SonnetModel Category=General Model, Open-Source=false, Max Steps=152025.1027.1——————————
Jedi-7B w/ GPT-4oModel Category=Multi-Agent Framework, Open-Source=true, Max Steps=502025.1027——————————
Agent S2Model Category=Multi-Agent Framework, Open-Source=true, Max Steps=152025.1027——————————
UltraCUA-7B-SFTModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1027——————————
Jedi-7B w/ GPT-4oModel Category=Multi-Agent Framework, Open-Source=true, Max Steps=152025.1026.8——————————
UI-TARS-1.5-7B†Model Category=Agentic Model, Open-Source=true, Max Steps=502025.1026.1——————————
OpenAI CUAModel Category=Agentic Model, Open-Source=false, Max Steps=152025.1026——————————
UI-TARS-72B-DPOModel Category=Agentic Model, Open-Source=true, Max Steps=502025.1025.8——————————
UI-TARS-1.5-7BSteps=502026.0225.128.8504.336.139.19.82546.718.847.8
UI-TARS-1.5-7BModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1024.5——————————
OpenCUA-7BSteps=152026.0224.336.95010.636.126.16.529.253.329.443.5
OpenCUA-7BModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1024.3——————————
UI-TARS-72B-DPOModel Category=Agentic Model, Open-Source=true, Max Steps=152025.1024——————————
UI-TARS-1.5-7B†Model Category=Agentic Model, Open-Source=true, Max Steps=152025.1023.4——————————
o3Model Category=General Model, Open-Source=false, Max Steps=502025.1017.2——————————
ScaleCUA-7BSteps=502026.0215——————————
o3Model Category=General Model, Open-Source=false, Max Steps=152025.109.1——————————
Qwen2.5-VL-7BSteps=502026.025.58.711.5004.31.18.36.717.621.7
Qwen2.5-VL-72BModel Category=General Model, Open-Source=true, Max Steps=152025.104.4——————————