All servers · AI models & agents

The Aggregate — LLM benchmark aggregate

ai.theaggregate/the-aggregate · v1.0.2

Measured by MCP Station

Description written by the publisher, not verified

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

Connect

claude mcp add --transport http the-aggregate https://theaggregate.ai/mcp

{
  "mcpServers": {
    "the-aggregate": {
      "url": "https://theaggregate.ai/mcp"
    }
  }
}

Tools as reported by the server

• 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/offs
• 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.
• 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).
• 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.
• search_benchmarks
  Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
• 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.
• 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.
• about_the_aggregate
  What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.

Website · JSON · Text for agents · Registry updated 2026-10-09