List your company

GUI Automation on OSWorld overall

86.8Overall Success RateLLM-as-Code w/ Claude Sonnet 4.6
71.51275.48179.4583.419Jun 14, 2026

Evaluation results

MethodLinks
LLM-as-Code w/ Claude Sonnet 4.6Max Steps=152026.0686.8
Holo3-35B-A3BMax Steps=1002026.0680.4
OpenAPA w/ Gemini-3.1-proMax Steps=1002026.0678.3
Claude Sonnet 4.6Max Steps=1002026.0672.1