{
 "version": "2026-11-09",
 "setup": {
  "benchmark": "AndroidWorld",
  "date": "2026-11-09",
  "agent": "Lusor",
  "model": "DeepSeek V4.1 Flash (low)",
  "seed": 42,
  "graders": {
   "mobilerun": "droidrun/android-world c5467e6",
   "google": "google-research/android_world 30583e2"
  },
  "mobilerun_cost_note": "ESTIMATE: published action count x $0.0766 (mean per-call cost we measured running gpt-6-astra low in our harness); not their bill",
  "mobilerun_source": "Mobilerun published per-task times and action counts",
  "skills_note": "skills_read = published app skills the agent opened in that task. skill_assisted = the subset with a rule written for an action or reading this task needs (our reading of each skill text); opening a skill whose rules do not apply to the task is not counted as assisted."
 },
 "task": {
  "task": "RecipeDeleteSingleWithRecipeWithNoise",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 48.2,
  "mobilerun_published_time_s": 301.6,
  "speed_ratio": 0.16,
  "lusor_cost_usd": 0.0122,
  "mobilerun_published_actions": 7,
  "mobilerun_est_cost_usd": 0.536,
  "lusor_tool_calls": 11,
  "disclosure": null,
  "skills_read": [
   "broccoli"
  ],
  "skill_assisted": [],
  "goal": "Delete the following recipes from Broccoli app: Classic Margherita Pizza.",
  "final_answer": null,
  "final_summary": "Deleted the Classic Margherita Pizza recipe from Broccoli. The deletion was confirmed by the app, and a full recount of the recipe list (29 recipes) shows it is no longer present.",
  "video_duration_s": 89.2,
  "steps": [
   {
    "step": 1,
    "tool": "read",
    "start_s": 30.2,
    "end_s": 30.21,
    "ok": true,
    "note": "Read Broccoli skill and observe screen"
   },
   {
    "step": 2,
    "tool": "get_ui_state",
    "start_s": 30.2,
    "end_s": 30.21,
    "ok": true,
    "note": "Read Broccoli skill and observe screen"
   },
   {
    "step": 3,
    "tool": "launch",
    "start_s": 31.03,
    "end_s": 34.95,
    "ok": true,
    "note": "Launch Broccoli and find the recipe list"
   },
   {
    "step": 4,
    "tool": "scroll_to",
    "start_s": 36.09,
    "end_s": 37.29,
    "ok": true,
    "note": "Scroll to Classic Margherita Pizza card"
   },
   {
    "step": 5,
    "tool": "tap_element",
    "start_s": 38.23,
    "end_s": 39.93,
    "ok": true,
    "note": "Open Classic Margherita Pizza recipe detail"
   },
   {
    "step": 6,
    "tool": "tap_element",
    "start_s": 41.06,
    "end_s": 42.14,
    "ok": true,
    "note": "Open the More options menu on the recipe detail page"
   },
   {
    "step": 7,
    "tool": "tap_element",
    "start_s": 42.88,
    "end_s": 43.82,
    "ok": true,
    "note": "Tap Delete in the menu and confirm if a dialog appears"
   },
   {
    "step": 8,
    "tool": "tap_element",
    "start_s": 44.92,
    "end_s": 46.14,
    "ok": true,
    "note": "Confirm DELETE in the dialog, then verify the recipe is gone from the list"
   },
   {
    "step": 9,
    "tool": "map_app",
    "start_s": 47.49,
    "end_s": 72.8,
    "ok": true,
    "note": "Map the full recipe list to verify Classic Margherita Pizza is gone"
   },
   {
    "step": 10,
    "tool": "get_ui_state",
    "start_s": 73.86,
    "end_s": 73.88,
    "ok": true,
    "note": "Report the deletion result"
   },
   {
    "step": 11,
    "tool": "done",
    "start_s": 75.99,
    "end_s": 75.99,
    "ok": true,
    "note": "Task complete"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/RecipeDeleteSingleWithRecipeWithNoise/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/RecipeDeleteSingleWithRecipeWithNoise/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/RecipeDeleteSingleWithRecipeWithNoise/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/RecipeDeleteSingleWithRecipeWithNoise/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/RecipeDeleteSingleWithRecipeWithNoise/task.json"
  }
 }
}