model-market-comparison.app.mintapis.com WebMCP Tools, Schemas & Agent Capabilities

model-market-comparison.app.mintapis.com

live Unverified (seed import) AI & Agents 6 tools imperative implementation

Choose benchmarks by workload: JevBench, DecisionBench, RewardBench 2, ForecastBench, tau-bench and metamorphic testing. Methods and sources.

First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com

Answer 5 · Act 1 · Transact 0 · Score: Not yet scored

Tool inspector

get_model_benchmark_summary

answer imperative

Published benchmark results for one exact catalog model (variant included), with unit, basis, benchmark version and source date. Requested benchmarks without a published result return value null. Read-only; never estimates.

Page: /

Input schema

Property	Type	Required	Description
`model_id`	string	yes	Exact catalog model id including the variant, e.g. "kimi-k3::max".
`benchmark_ids`	array	no	Optional exact benchmark ids; each one without a published result comes back with value null.
`limit`	integer	no	—

Raw JSON schema

{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "model_id"
  ],
  "properties": {
    "model_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:@%+-]{0,159}$",
      "description": "Exact catalog model id including the variant, e.g. \"kimi-k3::max\"."
    },
    "benchmark_ids": {
      "type": "array",
      "maxItems": 25,
      "uniqueItems": true,
      "items": {
        "type": "string",
        "pattern": "^[A-Za-z0-9][A-Za-z0-9._:@%+-]{0,159}$"
      },
      "description": "Optional exact benchmark ids; each one without a published result comes back with value null."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 25
    }
  }
}