{
 "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": "TasksDueNextWeek",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 180.2,
  "mobilerun_published_time_s": 154.4,
  "speed_ratio": 1.167,
  "lusor_cost_usd": 0.0712,
  "mobilerun_published_actions": 4,
  "mobilerun_est_cost_usd": 0.306,
  "lusor_tool_calls": 41,
  "disclosure": null,
  "skills_read": [
   "tasks"
  ],
  "skill_assisted": [
   "tasks"
  ],
  "goal": "How many tasks do I have due next week in Tasks app? Assume the week starts from Monday. Express your answer as a single integer.",
  "final_answer": "6",
  "final_summary": "You have 6 tasks due next week. The week runs Monday Oct 16 through Sunday Oct 22, 2023, and I counted only incomplete tasks: Complete project proposal (Mon Oct 16, shown as \"Tmrw\"), Review code changes (Tue Oct 17), Organize files and folders (Wed Oct 18), Organize movie night (Fri Oct 20), Prepare agenda for weekly meeting (Sat Oct 21) and Plan family reunion (Sun Oct 22). The other weekday-labelled tasks (Meal Prep for the Week, Renew Driver's License, Submit Expense Report, Grocery Shopping, Learn to Play Guitar) turned out to fall in the past week, Oct 9 to Oct 11, which I confirmed in each task's date picker.",
  "video_duration_s": 221.4,
  "steps": [
   {
    "step": 1,
    "tool": "read",
    "start_s": 29.8,
    "end_s": 29.81,
    "ok": true,
    "note": "Read the Tasks skill guidance"
   },
   {
    "step": 2,
    "tool": "get_ui_state",
    "start_s": 29.8,
    "end_s": 29.81,
    "ok": true,
    "note": "Observe current screen"
   },
   {
    "step": 3,
    "tool": "launch",
    "start_s": 30.81,
    "end_s": 34.53,
    "ok": true,
    "note": "Launch Tasks app and inspect task list"
   },
   {
    "step": 4,
    "tool": "map_app",
    "start_s": 36.49,
    "end_s": 52.66,
    "ok": true,
    "note": "Map full task list to count all tasks"
   },
   {
    "step": 5,
    "tool": "scroll_to",
    "start_s": 56.2,
    "end_s": 87.98,
    "ok": true,
    "note": "Scroll list to top and open 'Meal Prep for the Week' to check its due date"
   },
   {
    "step": 6,
    "tool": "swipe",
    "start_s": 89.46,
    "end_s": 97.01,
    "ok": true,
    "note": "Scroll task list to top"
   },
   {
    "step": 7,
    "tool": "swipe",
    "start_s": 98.32,
    "end_s": 103.31,
    "ok": true,
    "note": "Reach top of task list"
   },
   {
    "step": 8,
    "tool": "tap_element",
    "start_s": 104.78,
    "end_s": 106.31,
    "ok": true,
    "note": "Open 'Review code changes' and inspect its due date picker"
   },
   {
    "step": 9,
    "tool": "tap",
    "start_s": 107.55,
    "end_s": 108.38,
    "ok": true,
    "note": "Tap the due date row to open date picker for 'Review code changes'"
   },
   {
    "step": 10,
    "tool": "get_ui_state",
    "start_s": 109.9,
    "end_s": 110.12,
    "ok": true,
    "note": "Observe whether a date picker dialog opened"
   },
   {
    "step": 11,
    "tool": "chain",
    "start_s": 119.22,
    "end_s": 120.39,
    "ok": true,
    "note": "Cancel picker, go back to list, open next weekday-labelled task"
   },
   {
    "step": 12,
    "tool": "chain",
    "start_s": 122.36,
    "end_s": 123.33,
    "ok": true,
    "note": "Open 'Organize files and folders' and observe its detail screen"
   },
   {
    "step": 13,
    "tool": "chain",
    "start_s": 124.73,
    "end_s": 124.74,
    "ok": true,
    "note": "Tap due date row for 'Organize files and folders' and read picker"
   },
   {
    "step": 14,
    "tool": "tap",
    "start_s": 125.82,
    "end_s": 127.48,
    "ok": true,
    "note": "Tap due date row (540,1076) and read picker selection"
   },
   {
    "step": 15,
    "tool": "chain",
    "start_s": 130.21,
    "end_s": 133.8,
    "ok": true,
    "note": "Cancel picker, back, open 'Organize movie night' and read its screen"
   },
   {
    "step": 16,
    "tool": "chain",
    "start_s": 137.17,
    "end_s": 138.04,
    "ok": true,
    "note": "Open 'Organize movie night' rowBody [25] and read detail"
   },
   {
    "step": 17,
    "tool": "tap",
    "start_s": 139.37,
    "end_s": 141.3,
    "ok": true,
    "note": "Tap due date row for 'Organize movie night' and read picker"
   },
   {
    "step": 18,
    "tool": "chain",
    "start_s": 143.41,
    "end_s": 144.4,
    "ok": true,
    "note": "Cancel, back, open 'Prepare agenda for weekly meeting' [28]"
   },
   {
    "step": 19,
    "tool": "tap_element",
    "start_s": 146.33,
    "end_s": 147.39,
    "ok": true,
    "note": "Open 'Prepare agenda for weekly meeting' detail"
   },
   {
    "step": 20,
    "tool": "swipe",
    "start_s": 148.79,
    "end_s": 148.8,
    "ok": false,
    "note": "Scroll list slightly then open 'Prepare agenda for weekly meeting'"
   },
   {
    "step": 21,
    "tool": "swipe",
    "start_s": 149.84,
    "end_s": 151.59,
    "ok": true,
    "note": "Scroll list slightly then open 'Prepare agenda for weekly meeting'"
   },
   {
    "step": 22,
    "tool": "tap_element",
    "start_s": 152.35,
    "end_s": 153.11,
    "ok": true,
    "note": "Open 'Prepare agenda for weekly meeting' detail"
   },
   {
    "step": 23,
    "tool": "tap",
    "start_s": 154.05,
    "end_s": 155.8,
    "ok": true,
    "note": "Tap due date row for 'Prepare agenda for weekly meeting' and read selected date"
   },
   {
    "step": 24,
    "tool": "chain",
    "start_s": 158.07,
    "end_s": 158.99,
    "ok": true,
    "note": "Cancel, back, scroll list to top for the first group of tasks"
   },
   {
    "step": 25,
    "tool": "chain",
    "start_s": 160.65,
    "end_s": 161.48,
    "ok": true,
    "note": "Open 'Grocery Shopping' (Wed 12:02) detail via [4]"
   },
   {
    "step": 26,
    "tool": "tap",
    "start_s": 162.6,
    "end_s": 164.21,
    "ok": true,
    "note": "Tap due date row for 'Grocery Shopping' and read selected day"
   },
   {
    "step": 27,
    "tool": "chain",
    "start_s": 165.87,
    "end_s": 166.72,
    "ok": true,
    "note": "Cancel, back to list, then open 'Learn to Play Guitar'"
   },
   {
    "step": 28,
    "tool": "chain",
    "start_s": 168.34,
    "end_s": 169.07,
    "ok": true,
    "note": "Open 'Learn to Play Guitar' [7] detail"
   },
   {
    "step": 29,
    "tool": "tap",
    "start_s": 170.05,
    "end_s": 171.59,
    "ok": true,
    "note": "Tap due date row for 'Learn to Play Guitar' and read selected day"
   },
   {
    "step": 30,
    "tool": "chain",
    "start_s": 173.51,
    "end_s": 174.31,
    "ok": true,
    "note": "Cancel, back, then scroll up toward top of list"
   },
   {
    "step": 31,
    "tool": "swipe",
    "start_s": 175.4,
    "end_s": 177.22,
    "ok": true,
    "note": "Scroll list up toward top"
   },
   {
    "step": 32,
    "tool": "chain",
    "start_s": 178.6,
    "end_s": 179.31,
    "ok": true,
    "note": "Open 'Meal Prep for the Week' [7] detail"
   },
   {
    "step": 33,
    "tool": "tap",
    "start_s": 180.39,
    "end_s": 182.11,
    "ok": true,
    "note": "Tap due date row for 'Meal Prep for the Week' and read selected day"
   },
   {
    "step": 34,
    "tool": "chain",
    "start_s": 183.74,
    "end_s": 184.62,
    "ok": true,
    "note": "Cancel, back, then open 'Renew Driver's License'"
   },
   {
    "step": 35,
    "tool": "chain",
    "start_s": 186.03,
    "end_s": 186.82,
    "ok": true,
    "note": "Open 'Renew Driver's License' [10] detail"
   },
   {
    "step": 36,
    "tool": "tap",
    "start_s": 187.84,
    "end_s": 189.41,
    "ok": true,
    "note": "Tap due date row for 'Renew Driver's License' and read selected day"
   },
   {
    "step": 37,
    "tool": "chain",
    "start_s": 190.85,
    "end_s": 191.72,
    "ok": true,
    "note": "Cancel, back, open 'Submit Expense Report' (Tue 07:58)"
   },
   {
    "step": 38,
    "tool": "chain",
    "start_s": 194.31,
    "end_s": 195.01,
    "ok": true,
    "note": "Open 'Submit Expense Report' (Tue 07:58) via [16] detail"
   },
   {
    "step": 39,
    "tool": "tap",
    "start_s": 196.25,
    "end_s": 198.01,
    "ok": true,
    "note": "Tap due date row for 'Submit Expense Report' and read selected day"
   },
   {
    "step": 40,
    "tool": "chain",
    "start_s": 201.81,
    "end_s": 202.79,
    "ok": true,
    "note": "Close date picker and detail screen, then report count of tasks due Oct 16-22"
   },
   {
    "step": 41,
    "tool": "done",
    "start_s": 206.17,
    "end_s": 206.18,
    "ok": true,
    "note": "Report answer 6"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/TasksDueNextWeek/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/TasksDueNextWeek/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/TasksDueNextWeek/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/TasksDueNextWeek/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/TasksDueNextWeek/task.json"
  }
 }
}