The Aggregate — LLM benchmark aggregate
LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.
Connect it
Settings → Connectors → Add custom connector
URL: https://theaggregate.ai/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://theaggregate.ai/mcp{
"mcpServers": {
"the-aggregate": {
"url": "https://theaggregate.ai/mcp"
}
}
}claude mcp add --transport http the-aggregate https://theaggregate.ai/mcp{
"servers": {
"the-aggregate": {
"type": "http",
"url": "https://theaggregate.ai/mcp"
}
}
}8 tools, verified live
get_leaderboardread-onlyTop 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.
search_modelsread-onlyFind 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_modelread-onlyOne 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_modelsread-onlyHead-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_benchmarksread-onlyFind benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
get_benchmarkread-onlyOne 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_duelread-onlyGuesswork — 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_aggregateread-onlyWhat this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.
Alternatives in AI & Agents
Compare →RERealestateA
Czech distressed real estate — anonymized district aggregates (k≥5). Free tier.
SASanctionsA
Sanctions screening for KYC/AML — EU FSF + OFAC SDN checks for Czech companies & individuals.
ARAresA
Czech & Slovak business registry — company lookup by IČO, name, legal form, VAT. Official ARES.
SISignal8A
SEC filings, dilution, insider & institutional ownership, and political-trade data for AI agents.
UCUN Charter 1945A
UN Charter (1945, as amended) as an executable model with worked cases; not UN-affiliated
CMCall MeA
Your AI rings your iPhone, speaks its question, and gets your spoken answer back as text.