{
 "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": "TasksHighPriorityTasksDueOnDate",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 81.2,
  "mobilerun_published_time_s": 133.7,
  "speed_ratio": 0.607,
  "lusor_cost_usd": 0.0232,
  "mobilerun_published_actions": 5,
  "mobilerun_est_cost_usd": 0.383,
  "lusor_tool_calls": 15,
  "disclosure": null,
  "skills_read": [
   "tasks"
  ],
  "skill_assisted": [
   "tasks"
  ],
  "goal": "Which tasks with high priority are due October 27 2023 in the Tasks app? Answer with the title only. If there are multiples titles, format your answer in a comma separated list.",
  "final_answer": "Code Review",
  "final_summary": "Only one task in the Tasks app has high priority and is due October 27, 2023: \"Code Review\". Its due date shows as Friday, October 27 10:00, and its priority is the top (red) setting.",
  "video_duration_s": 127.6,
  "steps": [
   {
    "step": 1,
    "tool": "read",
    "start_s": 34.7,
    "end_s": 34.7,
    "ok": true,
    "note": "Read the Tasks skill guidance"
   },
   {
    "step": 2,
    "tool": "get_ui_state",
    "start_s": 35.71,
    "end_s": 35.73,
    "ok": true,
    "note": "Observe current screen"
   },
   {
    "step": 3,
    "tool": "launch",
    "start_s": 36.61,
    "end_s": 40.18,
    "ok": true,
    "note": "Launch Tasks app"
   },
   {
    "step": 4,
    "tool": "map_app",
    "start_s": 41.68,
    "end_s": 56.58,
    "ok": true,
    "note": "Count all tasks in My Tasks list"
   },
   {
    "step": 5,
    "tool": "scroll_to",
    "start_s": 59.07,
    "end_s": 75.51,
    "ok": true,
    "note": "Open Code Review task to read priority and due date"
   },
   {
    "step": 6,
    "tool": "tap_element",
    "start_s": 76.65,
    "end_s": 77.88,
    "ok": true,
    "note": "Open More options menu to look for filter by priority"
   },
   {
    "step": 7,
    "tool": "key",
    "start_s": 79.38,
    "end_s": 81.49,
    "ok": true,
    "note": "Close menu and open Search to find Code Review"
   },
   {
    "step": 8,
    "tool": "swipe",
    "start_s": 82.56,
    "end_s": 87.18,
    "ok": true,
    "note": "Scroll list down to reach Code Review row"
   },
   {
    "step": 9,
    "tool": "tap_element",
    "start_s": 88.2,
    "end_s": 89.69,
    "ok": true,
    "note": "Read Code Review details: priority and due date"
   },
   {
    "step": 10,
    "tool": "screenshot",
    "start_s": 92.03,
    "end_s": 93.4,
    "ok": true,
    "note": "Inspect priority row icons to identify which radio is High"
   },
   {
    "step": 11,
    "tool": "key",
    "start_s": 98.68,
    "end_s": 99.2,
    "ok": true,
    "note": "Return to list and check remaining candidates' dates"
   },
   {
    "step": 12,
    "tool": "swipe",
    "start_s": 102.39,
    "end_s": 104.03,
    "ok": true,
    "note": "Scroll to lower rows and open Renew Driver's License to check its full date"
   },
   {
    "step": 13,
    "tool": "tap_element",
    "start_s": 105.81,
    "end_s": 106.61,
    "ok": true,
    "note": "Read Renew Driver's License full due date and priority"
   },
   {
    "step": 14,
    "tool": "key",
    "start_s": 110.18,
    "end_s": 110.59,
    "ok": true,
    "note": "Confirm list state and finish with answer Code Review"
   },
   {
    "step": 15,
    "tool": "done",
    "start_s": 113.11,
    "end_s": 113.12,
    "ok": true,
    "note": "Task complete; answer reported"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/TasksHighPriorityTasksDueOnDate/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/TasksHighPriorityTasksDueOnDate/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/TasksHighPriorityTasksDueOnDate/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/TasksHighPriorityTasksDueOnDate/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/TasksHighPriorityTasksDueOnDate/task.json"
  }
 }
}