{
  "sku": "ai-answer-evaluation",
  "kind": "tool",
  "name": "AI Answer Evaluation and Comparison",
  "description": "Score two sets of answers against customer references with normalized exact match and token F1. Up to 200 examples. These metrics do not verify factual truth. Local processing. Limits and retention: /ai-services.",
  "price_cents": 3,
  "price_usd": "0.03",
  "unit": "per completed bounded job",
  "license": "Customer retains rights to supplied content. Generated/model-derived outputs require customer review; base-model licences apply.",
  "delivery": "instant",
  "input_schema": {
    "type": "object",
    "properties": {
      "examples": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "reference": {
              "type": "string",
              "maxLength": 1500,
              "minLength": 1
            },
            "answer_a": {
              "type": "string",
              "maxLength": 1500,
              "minLength": 1
            },
            "answer_b": {
              "type": "string",
              "maxLength": 1500,
              "minLength": 1
            }
          },
          "required": [
            "reference",
            "answer_a",
            "answer_b"
          ],
          "additionalProperties": false
        },
        "minItems": 1,
        "maxItems": 200,
        "default": [
          {
            "reference": "Paris",
            "answer_a": "Paris",
            "answer_b": "London"
          }
        ]
      }
    },
    "required": [
      "examples"
    ],
    "additionalProperties": false
  },
  "details_url": "https://market.datapackvibe.com/services/ai-answer-evaluation",
  "x402_url": "https://market.datapackvibe.com/x402/ai-answer-evaluation"
}