{
  "generated": "2026-09-08",
  "benchmark": "androidworld",
  "results": [
    {
      "system": "M3A (GPT-4 Turbo, a11y tree)",
      "developer": "Google Research",
      "value": 30.6,
      "date": "2024-05-23",
      "source": {
        "url": "https://arxiv.org/abs/2405.14573",
        "kind": "paper",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "scaffold": "M3A",
        "notes": "Best agent in the paper abstract."
      }
    },
    {
      "system": "AutoGLM-Mobile (9B)",
      "developer": "Zhipu AI",
      "value": 80.2,
      "date": "2025-09-26",
      "source": {
        "url": "https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?gid=0#gid=0",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "pass_k": 1,
        "notes": "Self-reported entry on the official community leaderboard sheet (screenshot + a11y tree); updated 2025-09-26 from 75.8. No independent verification."
      }
    },
    {
      "system": "Gemini 2.5 Computer Use",
      "developer": "Google",
      "value": 69.7,
      "date": "2025-10-01",
      "source": {
        "url": "https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?gid=0#gid=0",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "pass_k": 1,
        "notes": "Self-reported entry on the community leaderboard sheet (screenshot only, single model); sheet gives only 10/2025, 1st used."
      }
    },
    {
      "system": "FluizAI agent (gpt-4o / gpt-5.6-sol)",
      "developer": "FluizAI",
      "value": 100.0,
      "date": "2026-08-01",
      "source": {
        "url": "https://docs.google.com/spreadsheets/d/1cchzP9dlTZ3WXQTfYNhh3avxoLipqHN75v1Tb86uhHo/edit?gid=0#gid=0",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "pass_k": 1,
        "scaffold": "FluizAI",
        "notes": "Rank 1 on the community sheet as of access date; screenshot + a11y tree; code not open-sourced. Sheet gives only 08/2026, 1st used. No independent verification."
      }
    },
    {
      "system": "Qwen3.8 Max",
      "developer": "Alibaba",
      "value": 85.3,
      "date": "2026-09-03",
      "source": {
        "url": "https://benchlm.ai/benchmarks/androidworld",
        "kind": "aggregator",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "notes": "Vendor-published number republished by aggregator; harness and observation space unspecified."
      }
    }
  ]
}