`battle/35b.json`

146 lines
{
  "model": "mlx-community/Qwen3.6-35B-A3B-8bit",
  "when": "2026-08-18T16:22:52.604Z",
  "score": "11/12",
  "passed": 11,
  "total": 12,
  "tok_per_s": 55.2,
  "tok_s_ms": 7244,
  "longctx": {
    "placed": true,
    "pass": true,
    "got": "\n\nMAUVE-7719",
    "ms": 18380,
    "approx_ctx_tokens": 33990
  },
  "byCat": {
    "json": {
      "pass": 2,
      "tot": 3
    },
    "classify": {
      "pass": 3,
      "tot": 3
    },
    "constraint": {
      "pass": 2,
      "tot": 2
    },
    "reason": {
      "pass": 2,
      "tot": 2
    },
    "code": {
      "pass": 2,
      "tot": 2
    }
  },
  "results": [
    {
      "id": "json_person",
      "cat": "json",
      "pass": true,
      "got": {
        "name": "Maria Gonzalez",
        "age": 34,
        "city": "Chicago"
      },
      "ms": 14796,
      "out": "\n\n{\"name\": \"Maria Gonzalez\", \"age\": 34, \"city\": \"Chicago\"}"
    },
    {
      "id": "json_order",
      "cat": "json",
      "pass": false,
      "got": null,
      "ms": 16206,
      "out": "."
    },
    {
      "id": "json_list",
      "cat": "json",
      "pass": true,
      "got": {
        "items": [
          "silk wallpaper",
          "cork tiles",
          "grasscloth panels"
        ]
      },
      "ms": 10022,
      "out": "\n\n{\"items\": [\"silk wallpaper\", \"cork tiles\", \"grasscloth panels\"]}"
    },
    {
      "id": "cls_sentiment",
      "cat": "classify",
      "pass": true,
      "got": "\n\nnegative",
      "ms": 6510,
      "out": "\n\nnegative"
    },
    {
      "id": "cls_ticket",
      "cat": "classify",
      "pass": true,
      "got": "\n\nbilling",
      "ms": 6280,
      "out": "\n\nbilling"
    },
    {
      "id": "cls_spam",
      "cat": "classify",
      "pass": true,
      "got": "\n\nyes",
      "ms": 6431,
      "out": "\n\nyes"
    },
    {
      "id": "cons_oneword",
      "cat": "constraint",
      "pass": true,
      "got": "\n\nParis",
      "ms": 3565,
      "out": "\n\nParis"
    },
    {
      "id": "cons_numonly",
      "cat": "constraint",
      "pass": true,
      "got": "\n\n391",
      "ms": 3914,
      "out": "\n\n391"
    },
    {
      "id": "reason_word",
      "cat": "reason",
      "pass": true,
      "got": "\n\n27",
      "ms": 9808,
      "out": "\n\n27"
    },
    {
      "id": "reason_logic",
      "cat": "reason",
      "pass": true,
      "got": "\n\nMia",
      "ms": 9259,
      "out": "\n\nMia"
    },
    {
      "id": "code_sum",
      "cat": "code",
      "pass": true,
      "got": "function sumTo(n){let s=0;for(let i=1;i<=n;i++)s+=i;return s;}",
      "ms": 14847,
      "out": "\n\n```js\nfunction sumTo(n){let s=0;for(let i=1;i<=n;i++)s+=i;return s;}\n```"
    },
    {
      "id": "code_null",
      "cat": "code",
      "pass": true,
      "got": "function total(o){return (o.price ?? 0) * (o.qty ?? 0);}",
      "ms": 22830,
      "out": "\n\n```js\nfunction total(o){return (o.price ?? 0) * (o.qty ?? 0);}\n```"
    }
  ]
}