Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://theaggregate.ai/mcp8 tools · 147msget_leaderboardTop 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.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.
| Parameter | Type | Description |
|---|---|---|
| limit | number | Rows to return (1-100, default 25). |
| offset | number | Rows to skip from the top (default 0). |
| include_variants | boolean | Rank each reasoning-effort variant separately (e.g. "Claude Opus 4.6 (High)") instead of one fused row per model. Default false. |
search_modelsFind 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.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.
| Parameter | Type | Description |
|---|---|---|
| query* | string | Model or provider name fragment, e.g. "opus" or "deepseek". |
| limit | number | Max results (1-25, default 10). |
| include_variants | boolean | Return each reasoning-effort variant separately (e.g. "Claude Opus 4.6 (High)") instead of one fused row per model. Default false. |
get_modelOne 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).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).
| Parameter | Type | Description |
|---|---|---|
| model* | string | Model name or slug, e.g. "Claude Opus 4.5" or "gpt-5-5". |
compare_modelsHead-to-head between 2-4 models: aggregate ranks, Elo gap with a significance note based on the standard errors, and notable benchmarks they share.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.
| Parameter | Type | Description |
|---|---|---|
| models* | array | Two to four model names or slugs. |
search_benchmarksFind benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.
| Parameter | Type | Description |
|---|---|---|
| query* | string | Benchmark name fragment, e.g. "swe-bench" or "arena". |
| limit | number | Max results (1-25, default 10). |
get_benchmarkOne 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.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.
| Parameter | Type | Description |
|---|---|---|
| benchmark* | string | Benchmark name or slug, e.g. "Aider polyglot". |
| top | number | How many top models to list (1-50, default 10). |
get_prediction_duelGuesswork — 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.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.
No input schema was published for this tool.
about_the_aggregateWhat this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.
No input schema was published for this tool.
8 of 8 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.