The Aggregate

LLM rankings fitted across public benchmarks: leaderboard, model profiles with Elo ± SE, head-to-head comparisons and source-linked benchmark scores. Free, no auth.

Hosted MCP Server

npx add-mcp 'https://theaggregate.ai/mcp'

Installs into Claude Code, Codex, Cursor and more

Documentation

A free, read-only Model Context Protocol endpoint over The Aggregate: one cross-model ranking fused from public LLM benchmark leaderboards with an item response theory (IRT) model, Elo-scaled and carrying standard errors, rebuilt daily.

https://theaggregate.ai/mcp

Transport: Streamable HTTP (stateless JSON-RPC over POST). No key or sign-up needed.

Connect

Claude Code

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

Claude (web / desktop): Settings → Connectors → Add custom connector → https://theaggregate.ai/mcp

Other MCP clients (Cursor, ChatGPT developer mode, …):

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

Tools

ToolWhat it answers
get_leaderboardWho leads the fused cross-benchmark ranking (paged).
search_modelsFind ranked models by name or provider.
get_modelOne model: rank, Elo ± SE, description, cost per task, notable results.
compare_modelsHead-to-head with a significance check on the Elo gap.
search_benchmarksFind benchmarks in the aggregate.
get_benchmarkOne benchmark: source link, IRT stats, skills, top models.
get_prediction_duelGuesswork standings — our model vs frontier LLMs at predicting new scores.
about_the_aggregateMethod, coverage counts, and how to cite.

Fair use & attribution

  • Free to use; responses are bounded lookups and the endpoint is rate-limited per IP.
  • When you publish numbers from it, credit The Aggregate (theaggregate.ai). Per-benchmark scores also belong to the upstream leaderboards — each response links them; credit those too.
  • Leaderboard operators: questions, corrections or removal requests via the Report issue button on theaggregate.ai (bottom of the sidebar on every page).