{
  "lesson": "20-benchmarks-webarena-osworld",
  "title": "Benchmarks: WebArena and OSWorld",
  "questions": [
    {
      "stage": "pre",
      "question": "Why does WebArena self-host its four target apps?",
      "options": [
        "To avoid TLS",
        "To pin reproducible versions so evaluation is execution-based and not flaky",
        "To save money",
        "To run on GPUs"
      ],
      "correct": 1,
      "explanation": "Pinned self-hosted apps make execution-based evaluation reliable and comparable over time."
    },
    {
      "stage": "pre",
      "question": "Why does OSWorld use real OS screenshots rather than accessibility APIs?",
      "options": [
        "Screenshots cost less",
        "Accessibility APIs leak PII",
        "Accessibility APIs are too fast",
        "Screenshots force the agent to do real GUI grounding in 1920x1080, matching production constraints"
      ],
      "correct": 3,
      "explanation": "Screenshot-driven evaluation forces pixel-to-element grounding, the actual production constraint."
    },
    {
      "stage": "check",
      "question": "What two primary failure modes does OSWorld surface?",
      "options": [
        "Latency and bandwidth",
        "Hallucination and refusal",
        "Embedding drift and token leakage",
        "GUI grounding and operational knowledge"
      ],
      "correct": 3,
      "explanation": "Grounding (pixel-to-element) and operational knowledge (menus, shortcuts) are the headline blockers."
    },
    {
      "stage": "check",
      "question": "What does OSWorld-Human add on top of the base benchmark?",
      "options": [
        "Manually curated gold action trajectories that surface a 1.4-2.7x agent step-inefficiency gap",
        "A larger screen resolution",
        "More tasks",
        "A new OS"
      ],
      "correct": 0,
      "explanation": "Gold trajectories make trajectory efficiency measurable, not just success rate."
    },
    {
      "stage": "check",
      "question": "Which release-time number does the lesson cite for WebArena?",
      "options": [
        "Best agent at 50% with human at 50%",
        "Best agent at 0% across the board",
        "Best agent at 99% with human at 100%",
        "Best GPT-4 agent 14.41% success vs human 78.24%"
      ],
      "correct": 3,
      "explanation": "The 14.41% vs 78.24% gap is the WebArena release-time number."
    },
    {
      "stage": "post",
      "question": "What does the lesson warn happens with screenshot-only evaluation when the agent uses DOM or accessibility APIs?",
      "options": [
        "Nothing changes",
        "Tests pass trivially",
        "You exceed the rate limit",
        "You miss the grounding challenge OSWorld is designed to measure"
      ],
      "correct": 3,
      "explanation": "Evaluating an accessibility-API agent on screenshot-only benchmarks skips the grounding test."
    },
    {
      "stage": "post",
      "question": "Why is ignoring trajectory length a benchmarking failure?",
      "options": [
        "Length is the only metric that matters",
        "It hides cost and inefficiency that success rate alone misses (the 1.4-2.7x gap OSWorld-Human surfaces)",
        "Trajectories are not measurable",
        "Trajectory length always matches gold"
      ],
      "correct": 1,
      "explanation": "Two agents at 60% success can differ 2-3x in steps; cost and efficiency only show up if you measure trajectory length."
    }
  ]
}