mcpserver.lol
registry/the-aggregate
Connection check verified live · 20h ago

the-aggregate

Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.

Tools 8
GitHub stars
Installs / wk
Licence
Transport streamable-http
Last checked 20h ago

Tools & capabilities

8 tools

Read from the running server on 20h ago.

about_the_aggregate
What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.
compare_models models*
Head-to-head between 2-4 models: aggregate ranks, Elo gap with a significance note based on the standard errors, and notable benchmarks they share.
get_benchmark topbenchmark*
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_leaderboard limitoffsetinclude_variants
Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over ~5,000 public benchmark leaderboards. One row per model by default, fused…
get_model model*
One model in depth: aggregate rank, Elo with standard error, provider, what it is, cost per task where known, and its most notable benchmark results (with percentiles).
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 scor…
search_benchmarks limitquery*
Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.
search_models limitquery*include_variants
Find ranked models by (partial) name or provider. Returns rank, Elo and the model page URL. One row per model by default, fused across reasoning-effort settings.