{
 "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": "ExpenseDeleteSingle",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 45.2,
  "mobilerun_published_time_s": 155.6,
  "speed_ratio": 0.29,
  "lusor_cost_usd": 0.0153,
  "mobilerun_published_actions": 4,
  "mobilerun_est_cost_usd": 0.306,
  "lusor_tool_calls": 18,
  "disclosure": null,
  "skills_read": [],
  "skill_assisted": [],
  "goal": "Delete the following expenses from pro expense: Sponsorships.",
  "final_answer": null,
  "final_summary": "I deleted the Sponsorships expense (2023 Oct 11, 489.42 USD) from Pro Expense. The Expense Logs list now shows \"NO EXPENSE LOGS\", so no other expense rows remain.",
  "video_duration_s": 87.9,
  "steps": [
   {
    "step": 1,
    "tool": "get_ui_state",
    "start_s": 30.48,
    "end_s": 30.51,
    "ok": true,
    "note": "Observe current screen to find Pro Expense app"
   },
   {
    "step": 2,
    "tool": "key",
    "start_s": 32.25,
    "end_s": 33.4,
    "ok": true,
    "note": "Open app drawer to find Pro Expense"
   },
   {
    "step": 3,
    "tool": "swipe",
    "start_s": 34.34,
    "end_s": 35.77,
    "ok": true,
    "note": "Swipe up to open app drawer and find Pro Expense"
   },
   {
    "step": 4,
    "tool": "key",
    "start_s": 36.49,
    "end_s": 36.97,
    "ok": true,
    "note": "Return to home, then swipe up for app drawer"
   },
   {
    "step": 5,
    "tool": "launch",
    "start_s": 38.59,
    "end_s": 39.81,
    "ok": true,
    "note": "Launch Pro Expense package"
   },
   {
    "step": 6,
    "tool": "swipe",
    "start_s": 41.58,
    "end_s": 44.62,
    "ok": true,
    "note": "Swipe up on home to open app drawer"
   },
   {
    "step": 7,
    "tool": "type",
    "start_s": 45.71,
    "end_s": 48.83,
    "ok": true,
    "note": "Search app drawer for Pro Expense"
   },
   {
    "step": 8,
    "tool": "tap_element",
    "start_s": 49.63,
    "end_s": 50.57,
    "ok": true,
    "note": "Open Pro Expense from search results"
   },
   {
    "step": 9,
    "tool": "get_ui_state",
    "start_s": 51.48,
    "end_s": 52.96,
    "ok": true,
    "note": "Observe Pro Expense main screen"
   },
   {
    "step": 10,
    "tool": "tap_element",
    "start_s": 54.38,
    "end_s": 54.78,
    "ok": true,
    "note": "Open expense list via MORE to find Sponsorships expense"
   },
   {
    "step": 11,
    "tool": "get_ui_state",
    "start_s": 55.67,
    "end_s": 55.69,
    "ok": true,
    "note": "Read expense logs list"
   },
   {
    "step": 12,
    "tool": "map_app",
    "start_s": 57.14,
    "end_s": 58.16,
    "ok": true,
    "note": "Map expense list to inventory all expenses"
   },
   {
    "step": 13,
    "tool": "tap_element",
    "start_s": 59.87,
    "end_s": 59.87,
    "ok": true,
    "note": "Tap Delete on the Sponsorships expense row"
   },
   {
    "step": 14,
    "tool": "swipe",
    "start_s": 61.42,
    "end_s": 63.27,
    "ok": true,
    "note": "Swipe the Sponsorships row left to reveal Delete"
   },
   {
    "step": 15,
    "tool": "tap_element",
    "start_s": 64.37,
    "end_s": 65.28,
    "ok": true,
    "note": "Tap the revealed Delete icon for Sponsorships"
   },
   {
    "step": 16,
    "tool": "tap_element",
    "start_s": 66.23,
    "end_s": 66.77,
    "ok": true,
    "note": "Confirm deletion in the bottom sheet"
   },
   {
    "step": 17,
    "tool": "map_app",
    "start_s": 67.88,
    "end_s": 68.5,
    "ok": true,
    "note": "Verify list is empty via map_app, then done"
   },
   {
    "step": 18,
    "tool": "done",
    "start_s": 71.4,
    "end_s": 71.4,
    "ok": true,
    "note": "Task complete"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/ExpenseDeleteSingle/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/ExpenseDeleteSingle/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/ExpenseDeleteSingle/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/ExpenseDeleteSingle/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/ExpenseDeleteSingle/task.json"
  }
 }
}