The Aggregate — LLM benchmark aggregate

Official8 tools

by theaggregate

LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.

MCP Server: ai.theaggregate/the-aggregate

The MCP server ai.theaggregate/the-aggregate provides access to fused LLM rankings generated as a single IRT/Elo scale spanning approximately 5,000 public benchmark leaderboards, with updates on a daily schedule. It is described as a consolidation of multiple rankings into one coherent metric.

🛠️ Key Features

Fused LLM rankings
One IRT/Elo scale
Covers ~5,000 public benchmark leaderboards
Updated daily
8 tools available

🚀 Use Cases

Retrieve consolidated LLM ranking data across many benchmarks
Compare models using a single unified IRT/Elo metric
Track ranking changes across daily updates

⚡ Developer Benefits

Single-scale comparisons for public benchmark leaderboard results
Daily refresh supports use in automated ranking dashboards and pipelines

⚠️ Limitations

Scope is limited to public benchmark leaderboards included in the fused dataset
Update frequency is daily only

Captured live from the server via tools/list.

get_leaderboard

Top of the cross-benchmark aggregate ranking: every model placed on one rating scale by an IRT model fit over public benchmark leaderboards (call about_the_aggregate for the current coverage counts). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.

Parameters3

limit	number	optional	Rows to return (1-100, default 25).
offset	number	optional	Rows to skip from the top (default 0).
include_variants	boolean	optional	Rank each reasoning-effort variant separately (e.g. "Claude Opus 4.6 (High)") instead of one fused row per model. Default false.

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Rows to return (1-100, default 25)."
    },
    "offset": {
      "type": "number",
      "description": "Rows to skip from the top (default 0)."
    },
    "include_variants": {
      "type": "boolean",
      "description": "Rank each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false."
    }
  }
}

search_models

Find ranked models by (partial) name or provider. Returns rank, Aggregate Rating and the model page URL. One row per model by default, fused across reasoning-effort settings.

Parameters3

query	string	required	Model or provider name fragment, e.g. "opus" or "deepseek".
limit	number	optional	Max results (1-25, default 10).
include_variants	boolean	optional	Return each reasoning-effort variant separately (e.g. "Claude Opus 4.6 (High)") instead of one fused row per model. Default false.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Model or provider name fragment, e.g. \"opus\" or \"deepseek\"."
    },
    "limit": {
      "type": "number",
      "description": "Max results (1-25, default 10)."
    },
    "include_variants": {
      "type": "boolean",
      "description": "Return each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false."
    }
  },
  "required": [
    "query"
  ]
}

get_model

One model in depth: aggregate rank, Aggregate Rating with standard error, provider, what it is, cost per task where known, and its most notable benchmark results (with percentiles).

Parameters1

model

string

required

Model name or slug, e.g. "Claude Opus 4.5" or "gpt-5-5".

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name or slug, e.g. \"Claude Opus 4.5\" or \"gpt-5-5\"."
    }
  },
  "required": [
    "model"
  ]
}

compare_models

Head-to-head between 2-4 models: aggregate ranks, rating gap with a significance note based on the standard errors, and notable benchmarks they share.

Parameters1

models

array

required

Two to four model names or slugs.

Raw schema

{
  "type": "object",
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 2,
      "maxItems": 4,
      "description": "Two to four model names or slugs."
    }
  },
  "required": [
    "models"
  ]
}

search_benchmarks

Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.

Parameters2

query	string	required	Benchmark name fragment, e.g. "swe-bench" or "arena".
limit	number	optional	Max results (1-25, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Benchmark name fragment, e.g. \"swe-bench\" or \"arena\"."
    },
    "limit": {
      "type": "number",
      "description": "Max results (1-25, default 10)."
    }
  },
  "required": [
    "query"
  ]
}

get_benchmark

One benchmark in depth: what it measures, the original source leaderboard URL, IRT stats (difficulty, noise, model coverage), skill weights, and the current top models on it.

Parameters2

benchmark	string	required	Benchmark name or slug, e.g. "Aider polyglot".
top	number	optional	How many top models to list (1-50, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "benchmark": {
      "type": "string",
      "description": "Benchmark name or slug, e.g. \"Aider polyglot\"."
    },
    "top": {
      "type": "number",
      "description": "How many top models to list (1-50, default 10)."
    }
  },
  "required": [
    "benchmark"
  ]
}

get_prediction_duel

Guesswork — the public prediction duel: every day frontier LLMs and The Aggregate's own IRT model predict newly scraped benchmark scores before seeing them, and the errors are scored. Returns the current monthly standings, wins and losses included.

Parameters

No parameters.

Raw schema

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

about_the_aggregate

What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.

Parameters

No parameters.

Raw schema

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

Install

Tools (8)

get_leaderboardsearch_modelsget_modelcompare_modelssearch_benchmarksget_benchmarkget_prediction_duelabout_the_aggregate

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://theaggregate.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "the-aggregate": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://theaggregate.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: ai.theaggregate/the-aggregate

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

get_leaderboard

search_models

get_model

compare_models

search_benchmarks

get_benchmark

get_prediction_duel

about_the_aggregate

Install

Remote endpoint

Related servers