{
  "latest": [],
  "method": "Questions with one right answer about Anchor Terminal, answered through its MCP server, pages and API, three passes each, the model calling the tools itself or writing programs that call them, as it chooses (mode either). The Lab score is the share right with a level 2 question counting twice and a level 3 question three times, from either-mode runs only; a code-mode run (programs only) is listed and scores nothing.",
  "page": "https://www.anchorterminal.com/lab/evaluation/",
  "questions": "https://github.com/Anchor-Terminal/anchorlab/blob/main/eval/tasks.go",
  "runs": [
    {
      "byLevel": [
        20,
        24,
        10
      ],
      "correct": 54,
      "ended": "2026-11-18T15:10:45Z",
      "forbidden": 0,
      "harness": "2026.11.18-0557",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/qwen3-8-27b.json",
      "mode": "code",
      "model": "qwen3.8-27b",
      "modelMinutes": 175.5,
      "name": "Qwen3.8-27B",
      "ofLevel": [
        20,
        27,
        12
      ],
      "outputTps": 7.1,
      "passes": 3,
      "pct": 91.5,
      "points": 89,
      "scored": 59,
      "secPerTask": 187.523,
      "slug": "qwen3-8-27b",
      "steady": 45,
      "tokens": 1924154
    }
  ],
  "set": "anchor-lab-eval/1",
  "tasks": 59
}
