允许工具 / high / 框架未记录 · OSWorld-Verified official methodology; averaged over 5 runs, one attempt each, Docker/evaluator, 1080p, max 100 steps, pyautogui and UI-specific function declarations.
OSWorld-Verified · Partial score; 5 runs; 100-step maximum · Partial score · 允许工具 / high / 框架未记录 · OSWorld-Verified official methodology; averaged over 5 runs, one attempt each, Docker/evaluator, 1080p, max 100 steps, pyautogui and UI-specific function declarations.
Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Partial score %
Tools allowed / high / Framework not recorded · OSWorld-Verified official methodology; averaged over 5 runs, one attempt each, Docker/evaluator, 1080p, max 100 steps, pyautogui and UI-specific function declarations.
OSWorld-Verified · Partial score; 5 runs; 100-step maximum · Partial score · Tools allowed / high / Framework not recorded · OSWorld-Verified official methodology; averaged over 5 runs, one attempt each, Docker/evaluator, 1080p, max 100 steps, pyautogui and UI-specific function declarations.