{
  "id": "appworld",
  "name": "AppWorld",
  "category": "information",
  "summary": "Benchmark and sandbox of 9 simulated day-to-day apps operable via 457 APIs and populated by ~100 simulated people, for evaluating function-calling and interactive coding agents.",
  "description": "Agents complete natural tasks by writing code that calls the apps' APIs on behalf of a supervisor; Evaluation uses database-state-based unit tests that also catch collateral damage. Includes a task explorer, API explorer, leaderboard and an AppWorld MCP server/client for evaluating terminal agents such as Codex and Gemini CLI. ACL 2024 Best Resource Paper (arXiv 2407.18901). Installs from PyPI as `appworld`.",
  "url": "https://appworld.dev/",
  "repo": "https://github.com/StonyBrookNLP/appworld",
  "docs": "https://github.com/StonyBrookNLP/appworld#readme",
  "tags": [
    "benchmark",
    "function-calling",
    "coding-agent",
    "agent-evaluation",
    "leaderboard"
  ],
  "license": "Apache-2.0",
  "pricing": "open-source",
  "status": "active",
  "related": [
    "tau-bench",
    "bfcl",
    "webarena",
    "osworld"
  ],
  "sources": [
    "https://github.com/StonyBrookNLP/appworld",
    "https://appworld.dev/",
    "https://arxiv.org/abs/2407.18901"
  ],
  "added": "2026-10-18",
  "updated": "2026-10-18",
  "last_verified": "2026-10-18",
  "submitted_by": "agentica-curator",
  "maintainer": "Stony Brook NLP",
  "longform": [
    {
      "type": "comparison",
      "id": "agent-benchmarks",
      "title": "Agent benchmarks compared",
      "url": "https://indexagentica.com/compare/agent-benchmarks/",
      "json": "https://indexagentica.com/api/longform/compare/agent-benchmarks.json"
    }
  ],
  "links": {
    "html": "https://indexagentica.com/entries/appworld/",
    "markdown": "https://indexagentica.com/entries/appworld.md",
    "json": "https://indexagentica.com/api/entries/appworld.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/appworld.json"
  }
}