{
 "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": "RecipeDeleteMultipleRecipesWithNoise",
  "mobilerun_grader_pass": true,
  "google_grader_pass": true,
  "lusor_time_s": 108.2,
  "mobilerun_published_time_s": 474.7,
  "speed_ratio": 0.228,
  "lusor_cost_usd": 0.0238,
  "mobilerun_published_actions": 17,
  "mobilerun_est_cost_usd": 1.302,
  "lusor_tool_calls": 21,
  "disclosure": null,
  "skills_read": [
   "broccoli"
  ],
  "skill_assisted": [],
  "goal": "Delete the following recipes from Broccoli app: Avocado Toast with Egg, Classic Margherita Pizza, Thai Peanut Noodle Salad.",
  "final_answer": null,
  "final_summary": "I deleted all three recipes from Broccoli: Avocado Toast with Egg, Classic Margherita Pizza, and Thai Peanut Noodle Salad. After each deletion the app confirmed it, and the recipe list now holds 29 recipes with none of the three remaining.",
  "video_duration_s": 149.3,
  "steps": [
   {
    "step": 1,
    "tool": "read",
    "start_s": 30.01,
    "end_s": 30.01,
    "ok": true,
    "note": "Read Broccoli skill guidance"
   },
   {
    "step": 2,
    "tool": "get_ui_state",
    "start_s": 31.19,
    "end_s": 31.21,
    "ok": true,
    "note": "Observe current screen, launch Broccoli if needed"
   },
   {
    "step": 3,
    "tool": "launch",
    "start_s": 32.3,
    "end_s": 36.24,
    "ok": true,
    "note": "Launch Broccoli app and view recipe list"
   },
   {
    "step": 4,
    "tool": "map_app",
    "start_s": 37.34,
    "end_s": 64.62,
    "ok": true,
    "note": "Map the recipe list to find the three target recipes"
   },
   {
    "step": 5,
    "tool": "tap_element",
    "start_s": 66.12,
    "end_s": 66.55,
    "ok": true,
    "note": "Search for Avocado Toast with Egg"
   },
   {
    "step": 6,
    "tool": "type",
    "start_s": 67.56,
    "end_s": 71.08,
    "ok": true,
    "note": "Type search query for Avocado Toast with Egg"
   },
   {
    "step": 7,
    "tool": "tap_element",
    "start_s": 72.36,
    "end_s": 73.62,
    "ok": true,
    "note": "Open Avocado Toast with Egg recipe"
   },
   {
    "step": 8,
    "tool": "tap_element",
    "start_s": 74.72,
    "end_s": 75.74,
    "ok": true,
    "note": "Open More options menu on Avocado Toast with Egg to find Delete"
   },
   {
    "step": 9,
    "tool": "tap_element",
    "start_s": 76.54,
    "end_s": 77.46,
    "ok": true,
    "note": "Tap Delete for Avocado Toast with Egg"
   },
   {
    "step": 10,
    "tool": "tap_element",
    "start_s": 78.29,
    "end_s": 79.41,
    "ok": true,
    "note": "Confirm delete, then search for Classic Margherita Pizza"
   },
   {
    "step": 11,
    "tool": "type",
    "start_s": 80.54,
    "end_s": 84.19,
    "ok": true,
    "note": "Search for Classic Margherita Pizza"
   },
   {
    "step": 12,
    "tool": "tap_element",
    "start_s": 85.12,
    "end_s": 86.81,
    "ok": true,
    "note": "Open Classic Margherita Pizza and delete it"
   },
   {
    "step": 13,
    "tool": "tap_element",
    "start_s": 88.47,
    "end_s": 89.22,
    "ok": true,
    "note": "Tap More options on Classic Margherita Pizza"
   },
   {
    "step": 14,
    "tool": "tap_element",
    "start_s": 90.26,
    "end_s": 91.21,
    "ok": true,
    "note": "Tap Delete menu item for Classic Margherita Pizza"
   },
   {
    "step": 15,
    "tool": "tap_element",
    "start_s": 92.32,
    "end_s": 93.52,
    "ok": true,
    "note": "Confirm delete, then search for Thai Peanut Noodle Salad"
   },
   {
    "step": 16,
    "tool": "chain",
    "start_s": 94.67,
    "end_s": 102.93,
    "ok": true,
    "note": "Search and delete Thai Peanut Noodle Salad"
   },
   {
    "step": 17,
    "tool": "tap_element",
    "start_s": 104.21,
    "end_s": 104.92,
    "ok": true,
    "note": "Close search and recount list with map_app levels 1"
   },
   {
    "step": 18,
    "tool": "map_app",
    "start_s": 106.04,
    "end_s": 106.06,
    "ok": true,
    "note": "Recount full list with map_app levels 1 to confirm 29 recipes and no targets"
   },
   {
    "step": 19,
    "tool": "key",
    "start_s": 107.14,
    "end_s": 107.45,
    "ok": true,
    "note": "Close keyboard, then map_app levels 1 to recount"
   },
   {
    "step": 20,
    "tool": "map_app",
    "start_s": 108.95,
    "end_s": 132.37,
    "ok": true,
    "note": "Recount full list to confirm 29 recipes with no targets"
   },
   {
    "step": 21,
    "tool": "done",
    "start_s": 134.61,
    "end_s": 134.62,
    "ok": true,
    "note": "Task complete"
   }
  ],
  "files": {
   "video_mp4": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipesWithNoise/video.mp4",
   "video_webm": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipesWithNoise/video.webm",
   "poster": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipesWithNoise/poster.webp",
   "steps": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipesWithNoise/steps.json",
   "task": "benchmarks/androidworld/2026-11-09/RecipeDeleteMultipleRecipesWithNoise/task.json"
  }
 }
}