BenchLeader

The BenchLeader Index leaderboard of large language models: a daily composite of independent public benchmarks, one row per model (its best reasoning-effort configuration) as on the homepage. Optionally rank by one category score (coding, agentic, reasoning, math, knowledge…), list every model × effort configuration, or filter to open-weights models or one developer. Paged.

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Rank by this category score instead of the overall Index, e.g. coding, agentic, reasoning, math, knowledge, instruction, multimodal, long_context."
    },
    "configurations": {
      "type": "boolean",
      "default": false,
      "description": "List every ranked model × reasoning-effort configuration rather than one row per model."
    },
    "open_weights_only": {
      "type": "boolean",
      "default": false,
      "description": "Only models with downloadable weights."
    },
    "developer": {
      "type": "string",
      "description": "Only models from this developer, e.g. OpenAI, Anthropic, Google, DeepSeek."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 20,
      "description": "How many rows to return (at most 100)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0,
      "description": "Rows to skip, for paging (use next_offset from the previous page)."
    }
  },
  "additionalProperties": false
}

Find models by name, alias, id or developer ("opus", "gemini 4", "deepseek"). Returns each match's id, rank, Index and reasoning-effort configurations, for use with get_model and compare_models.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Model name, alias, id or developer."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10,
      "description": "How many matches to return (at most 25)."
    }
  },
  "required": [
    "query"
  ],
  "additionalProperties": false
}

One model's BenchLeader profile: Index and rank, category scores, list price, speed, latency, context window, its other reasoning-effort configurations, and its strongest independent benchmark results (each with its board rank, publisher and source link).

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id (\"claude-opus-5-5\"), configuration id (\"gpt-6-astra@max\"), page URL or name."
    },
    "effort": {
      "type": "string",
      "description": "Reasoning-effort configuration to show (none, low, medium, high, xhigh, max…). Defaults to the best-ranked one."
    },
    "results_limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many benchmark results to return (at most 50)."
    }
  },
  "required": [
    "model"
  ],
  "additionalProperties": false
}

Head-to-head comparison of two models with BenchLeader's verdict: who leads on quality (a lead is claimed only outside the combined margin of error), price and speed ratios, category-by-category wins, when to choose each, and shared benchmark results. Links the comparison page.

{
  "type": "object",
  "properties": {
    "model_a": {
      "type": "string",
      "description": "First model: id, configuration id, page URL or name."
    },
    "model_b": {
      "type": "string",
      "description": "Second model: id, configuration id, page URL or name."
    },
    "effort_a": {
      "type": "string",
      "description": "Reasoning effort for model_a (defaults to its best-ranked configuration)."
    },
    "effort_b": {
      "type": "string",
      "description": "Reasoning effort for model_b (defaults to its best-ranked configuration)."
    }
  },
  "required": [
    "model_a",
    "model_b"
  ],
  "additionalProperties": false
}

The benchmarks BenchLeader reads: what each measures, publisher, category, whether it feeds the Index (and its weight), how many models it covers, status and caveats. Filter by category or a search query. Paged.

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Only this category, e.g. coding, agentic, reasoning, math, knowledge."
    },
    "query": {
      "type": "string",
      "description": "Search benchmark names, ids, aliases and publishers (\"swe-bench\", \"arc\", \"epoch\")."
    },
    "in_index_only": {
      "type": "boolean",
      "default": false,
      "description": "Only benchmarks that feed the BenchLeader Index."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "default": 50,
      "description": "How many benchmarks to return (at most 100)."
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "default": 0,
      "description": "Rows to skip, for paging (use next_offset from the previous page)."
    }
  },
  "additionalProperties": false
}

One benchmark: what it measures, unit, publisher and source, whether and how much it counts in the BenchLeader Index, status and caveats, and its top models (one row per model, best result first).

{
  "type": "object",
  "properties": {
    "benchmark": {
      "type": "string",
      "description": "Benchmark id (\"gpqa_diamond\"), name (\"SWE-bench Verified\"), alias or page URL."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 25,
      "default": 10,
      "description": "How many top models to return (at most 25)."
    }
  },
  "required": [
    "benchmark"
  ],
  "additionalProperties": false
}

What BenchLeader is, how the BenchLeader Index is computed, the current method version, data date and update cadence, coverage counts, licence and how to cite it.

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}