{
  "data": {
    "evaluations": [
      {
        "json": "https://www.anchorterminal.com/api/v1/lab-evals.json",
        "modelsScored": 15,
        "name": "Open-weight models, on questions about this site",
        "page": "https://www.anchorterminal.com/benchmark/lab/evaluation/models/",
        "passes": 3,
        "set": "anchor-lab-eval/1",
        "tasks": 59
      }
    ],
    "lab": "https://www.anchorterminal.com/benchmark/lab/",
    "page": "https://www.anchorterminal.com/benchmark/lab/evaluation/"
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/benchmark/lab/evaluation/",
    "json": "https://www.anchorterminal.com/benchmark/lab/evaluation/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/benchmark/lab/evaluation/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/benchmark/lab/evaluation/index.min.md"
  },
  "markdown": "An evaluation is a fixed set of questions with known answers that the lab runs the same way every time, so two results can be put side by side. Open-weight models are the first, and more will be listed here as the lab runs them.\n\n- Open-weight models, on questions about this site (set anchor-lab-eval/1): 59 questions with one right answer, 3 passes each, scored 0 to 100. https://www.anchorterminal.com/benchmark/lab/evaluation/models/index.md\n\nThe evaluations run on the lab's box: https://www.anchorterminal.com/benchmark/lab/index.md\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-22",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "1.0",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Benchmark",
        "url": "https://www.anchorterminal.com/benchmark/"
      },
      {
        "name": "Lab",
        "url": "https://www.anchorterminal.com/benchmark/lab/"
      },
      {
        "name": "Evaluations",
        "url": ""
      }
    ],
    "description": "The evaluations Anchor Terminal's lab runs, each a fixed set of questions with known answers. The first is of open-weight models, scored 0 to 100, with every run dated.",
    "facts": [
      "15 models scored",
      "102 listings tried",
      "every run dated"
    ],
    "h1": "The lab's evaluations",
    "image": "https://www.anchorterminal.com/assets/og/benchmark-lab-evaluations.png",
    "path": "/benchmark/lab/evaluation/",
    "published": "",
    "section": "benchmark",
    "title": "The lab's evaluations: fixed questions, known answers",
    "toc": null,
    "updated": "2026-11-22",
    "url": "https://www.anchorterminal.com/benchmark/lab/evaluation/"
  },
  "tokens": {
    "markdown": 300,
    "slim": 230
  },
  "version": 1
}
