{
 "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": "RecipeDeleteMultipleRecipes",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 39.2,
  "mobilerun_published_time_s": 234.1,
  "speed_ratio": 0.167,
  "lusor_cost_usd": 0.0138,
  "mobilerun_published_actions": 13,
  "mobilerun_est_cost_usd": 0.996,
  "lusor_tool_calls": 17,
  "disclosure": null,
  "skills_read": [
   "broccoli"
  ],
  "skill_assisted": [],
  "goal": "Delete the following recipes from Broccoli app: Moroccan Chickpea Stew, Eggplant Parmesan, Quinoa Salad with Vegetables.",
  "final_answer": null,
  "final_summary": "I deleted all three recipes from Broccoli: Moroccan Chickpea Stew, Eggplant Parmesan, and Quinoa Salad with Vegetables. The recipe list now shows \"No recipes found.\", so the list holds no rows at all.",
  "video_duration_s": 80.2,
  "steps": [
   {
    "step": 1,
    "tool": "read",
    "start_s": 30.09,
    "end_s": 30.1,
    "ok": true,
    "note": "Read Broccoli skill, then observe screen"
   },
   {
    "step": 2,
    "tool": "get_ui_state",
    "start_s": 30.09,
    "end_s": 30.1,
    "ok": true,
    "note": "Read Broccoli skill, then observe screen"
   },
   {
    "step": 3,
    "tool": "launch",
    "start_s": 31.11,
    "end_s": 35.14,
    "ok": true,
    "note": "Launch Broccoli and inspect recipe list"
   },
   {
    "step": 4,
    "tool": "tap_element",
    "start_s": 36.28,
    "end_s": 37.82,
    "ok": true,
    "note": "Open Eggplant Parmesan recipe to delete it"
   },
   {
    "step": 5,
    "tool": "tap_element",
    "start_s": 40.22,
    "end_s": 41.25,
    "ok": true,
    "note": "Open more options menu on Eggplant Parmesan"
   },
   {
    "step": 6,
    "tool": "tap_element",
    "start_s": 42.43,
    "end_s": 43.33,
    "ok": true,
    "note": "Tap Delete on Eggplant Parmesan and confirm any dialog"
   },
   {
    "step": 7,
    "tool": "tap_element",
    "start_s": 44.29,
    "end_s": 45.53,
    "ok": true,
    "note": "Confirm deletion, then delete Moroccan Chickpea Stew"
   },
   {
    "step": 8,
    "tool": "tap_element",
    "start_s": 46.64,
    "end_s": 48.15,
    "ok": true,
    "note": "Open Moroccan Chickpea Stew"
   },
   {
    "step": 9,
    "tool": "tap_element",
    "start_s": 49.24,
    "end_s": 50.14,
    "ok": true,
    "note": "Open more options on Moroccan Chickpea Stew"
   },
   {
    "step": 10,
    "tool": "tap_element",
    "start_s": 51.22,
    "end_s": 52.03,
    "ok": true,
    "note": "Tap Delete on Moroccan Chickpea Stew and confirm"
   },
   {
    "step": 11,
    "tool": "tap_element",
    "start_s": 53.07,
    "end_s": 54.14,
    "ok": true,
    "note": "Confirm deletion, then delete Quinoa Salad with Vegetables"
   },
   {
    "step": 12,
    "tool": "tap_element",
    "start_s": 55.14,
    "end_s": 56.33,
    "ok": true,
    "note": "Open Quinoa Salad with Vegetables"
   },
   {
    "step": 13,
    "tool": "tap_element",
    "start_s": 57.52,
    "end_s": 58.31,
    "ok": true,
    "note": "Open more options on Quinoa Salad with Vegetables"
   },
   {
    "step": 14,
    "tool": "tap_element",
    "start_s": 59.41,
    "end_s": 60.22,
    "ok": true,
    "note": "Tap Delete on Quinoa Salad and confirm"
   },
   {
    "step": 15,
    "tool": "tap_element",
    "start_s": 61.28,
    "end_s": 62.12,
    "ok": true,
    "note": "Confirm deletion and verify list via map_app"
   },
   {
    "step": 16,
    "tool": "map_app",
    "start_s": 63.29,
    "end_s": 63.41,
    "ok": true,
    "note": "Map the recipe list to confirm no recipes remain"
   },
   {
    "step": 17,
    "tool": "done",
    "start_s": 65.64,
    "end_s": 65.65,
    "ok": true,
    "note": "Task complete"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipes/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipes/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipes/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipes/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipes/task.json"
  }
 }
}