# The Aggregate — LLM benchmark aggregate

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

- name: ai.theaggregate/the-aggregate
- version: 1.0.2
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.theaggregate%2Fthe-aggregate
- tools: https://api.protogrid.dev/v1/servers/ai.theaggregate%2Fthe-aggregate/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "the-aggregate": {
      "type": "http",
      "url": "https://theaggregate.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-98% +updated-11d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 8 of 8 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,049 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 13 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 8, about 1,049 tokens to load them all
- tool set hash: 3ab671a12696713dd8e5ca8c865e4b2c
- tools last changed: 2026-10-12T14:07:56.341Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.theaggregate/the-aggregate.svg)](https://protogrid.dev/servers/ai.theaggregate/the-aggregate)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-12 `search_benchmarks` changed (description)
  - before: Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.
  - after: Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
- 2026-10-12 `compare_models` changed (description)
  - before: 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.
  - after: 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.
- 2026-10-12 `get_model` changed (description)
  - before: 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).
  - after: 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).
- 2026-10-12 `search_models` changed (description)
  - before: 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.
  - after: 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.
- 2026-10-12 `get_leaderboard` changed (description)
  - before: Top of the cross-benchmark aggregate ranking: every model placed on one Elo 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.
  - after: 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.
- 2026-10-10 `about_the_aggregate` changed (annotations)
- 2026-10-10 `get_prediction_duel` changed (annotations)
- 2026-10-10 `get_benchmark` changed (annotations)
- 2026-10-10 `search_benchmarks` changed (annotations)
- 2026-10-10 `compare_models` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/ai.theaggregate%2Fthe-aggregate/changes

## Remotes

- https://theaggregate.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.9831933)

## Packages

_none_

## Tools (8)

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