The Aggregate — LLM benchmark aggregate
Cross-benchmark LLM rankings with significance checks, free and read-only
- Pricing
- Free
- Platforms
- API
- Runs
- Remotely
- Version
- 1.0.2
- Listing updated
- 1 day ago
About The Aggregate — LLM benchmark aggregate
The Aggregate — LLM benchmark aggregate is a free MCP server for ai models and llm tooling. It runs as a hosted remote server, so there is nothing to install locally.
Rather than reporting one leaderboard, The Aggregate fuses many public LLM benchmark leaderboards into a single ranking using an item response theory model. Each model carries an Aggregate Rating with a standard error, rebuilt daily, so a head-to-head comparison can say whether a rating gap is statistically meaningful.
Eight tools cover the leaderboard, model and benchmark search, per-model and per-benchmark detail, comparison, a prediction-duel standing that pits the site's model against frontier LLMs at forecasting new scores, and a methodology note with citation guidance. Per-benchmark scores link back to the upstream leaderboards.
The endpoint is stateless Streamable HTTP, needs no key, and is rate-limited per IP. Published numbers should credit The Aggregate and the upstream leaderboards.
Install
Run in a terminal
claude mcp add --transport http the-aggregate https://theaggregate.ai/mcpAdd to Settings → Connectors → Add custom connector
https://theaggregate.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"the-aggregate": {
"url": "https://theaggregate.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"the-aggregate": {
"type": "http",
"url": "https://theaggregate.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"the-aggregate": {
"serverUrl": "https://theaggregate.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"the-aggregate": {
"type": "http",
"url": "https://theaggregate.ai/mcp"
}
}
}Tools this server provides (8)
Taken from the project documentation; the running server may differ.
- get_leaderboard
- Paged fused cross-benchmark ranking
- search_models
- Find ranked models by name or provider
- get_model
- One model: rank, rating, description, cost per task
- compare_models
- Head-to-head with significance check
- search_benchmarks
- Find benchmarks in the aggregate
- get_benchmark
- One benchmark with source link and stats
- get_prediction_duel
- Prediction standings versus frontier LLMs
- about_the_aggregate
- Method, coverage and how to cite
What it does
- Fused leaderboard
- One ranking built from public benchmarks via an IRT model.
- Rating with error
- Aggregate Ratings come with standard errors and daily rebuilds.
- Significance check
- compare_models tests whether the rating gap is meaningful.
- Benchmark detail
- get_benchmark returns source link, IRT stats, skills and top models.
- Prediction duel
- Shows how the model fares against frontier LLMs at predicting new scores.
- Source links
- Responses link the upstream leaderboards.
Good for
- Pick a model by cross-benchmark standing
- Compare two models head to head
- Look up what a benchmark measures
- Cite model rankings with sources
Pricing
Free
Free, read-only
Prices change. Check theaggregate.ai before you buy.
The Aggregate — LLM benchmark aggregate FAQ
Do I need a key?
No key or sign-up is needed.
How often does data update?
Ratings are rebuilt daily.
Is it rate-limited?
Yes, per IP.
Do I have to credit anyone?
Credit The Aggregate and the upstream leaderboards when publishing numbers.
Is The Aggregate — LLM benchmark aggregate free?
Yes. The Aggregate — LLM benchmark aggregate is free to use.
How do I add The Aggregate — LLM benchmark aggregate to Claude Code?
Run this command in your terminal: claude mcp add --transport http the-aggregate https://theaggregate.ai/mcp
What are the best alternatives to The Aggregate — LLM benchmark aggregate?
The closest alternatives to The Aggregate — LLM benchmark aggregate are Claude Code Ultimate Guide, signafAIde, Toolkien, Lugh and HypePaper.
Alternatives to The Aggregate — LLM benchmark aggregate

Claude Code Ultimate Guide
MCP serverMCP server for searching the Claude Code Ultimate Guide from any MCP client
Runs locally- Open source
- 6.5K GitHub stars
- AI models and LLM tooling

signafAIde
MCP serverLocal MCP server to set up, verify and check coverage of signed agent action records
Runs locally- 5 tools
- Freemium
- Security

Toolkien
MCP serverOne MCP gateway for all your MCP servers, with code mode, permissions and audit
Not checked yet- 3 tools
- Remote
- Open source
- AI models and LLM tooling
Lugh
MCP serverWrite, check and dry-run Lugh agent programs with policy, budgets and approvals
Runs locally- 5 tools
- Open source
- AI models and LLM tooling
HypePaper
MCP serverResearch papers, benchmarks, citations and topic experts for AI assistants
- 58 tools
- Remote
- Freemium
- AI models and LLM tooling

One compact entry point that finds, describes and runs hundreds of pay-per-call data tools
- 3 tools
- Remote
- Freemium
- Developer tools