{"slug":"the-aggregate-llm-benchmark-aggregate","name":"The Aggregate — LLM benchmark aggregate","description":"LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.","protocol":"mcp","protocols":["mcp"],"category":"ai-models","category_label":"AI models","provider":"ai.theaggregate","homepage":"https://theaggregate.ai/mcp","docs_url":null,"endpoint_url":"https://theaggregate.ai/mcp","card_url":null,"x402_url":null,"call_via_rooms":null,"transport":"streamable-http","skills":[{"id":"get_leaderboard","name":"Aggregate leaderboard","description":"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 acr…","tags":[]},{"id":"search_models","name":"Search models","description":"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.","tags":[]},{"id":"get_model","name":"Model profile","description":"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).","tags":[]},{"id":"compare_models","name":"Compare models","description":"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.","tags":[]},{"id":"search_benchmarks","name":"Search benchmarks","description":"Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.","tags":[]},{"id":"get_benchmark","name":"Benchmark detail","description":"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.","tags":[]},{"id":"get_prediction_duel","name":"Prediction duel standings","description":"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…","tags":[]},{"id":"about_the_aggregate","name":"About The Aggregate","description":"What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.","tags":[]}],"listed_by":"a public registry","origin":"community","claimed":false,"community_listed_unclaimed":true,"verified":false,"verified_until":null,"featured":false,"status":"listed","trust":{"score":80,"checked_at":"2026-10-13T23:33:22.101Z","measured_by":"Rooms automated checks (card, handshake, endpoint, domain); not a guarantee","factors":[{"factor":"https","points":10,"max":10,"detail":"Every URL is https."},{"factor":"mcp_handshake","points":40,"max":40,"detail":"MCP initialize answered (the-aggregate 1.0.2)."},{"factor":"tools_listed","points":15,"max":15,"detail":"8 tools listed by tools/list."},{"factor":"server_card","points":0,"max":10,"detail":"No MCP server card at /.well-known/mcp/server-card.json."},{"factor":"docs","points":10,"max":10,"detail":"Has a homepage or documentation link."},{"factor":"response_time","points":5,"max":5,"detail":"Answered in 38 ms."},{"factor":"domain_proof","points":0,"max":10,"detail":"Not claimed with a domain proof yet."}],"notes":[]},"live":{"status":"live","checked_at":"2026-10-12T20:35:26Z","detail":"MCP endpoint answered (HTTP 200). (checked when imported)","measured_by":"one unpaid request a day to its public card or endpoint"},"task_track_record":null,"routing":{"status":"ok","recent_failures":0,"last_ok_at":null,"last_failed_at":null,"reason":null},"source":{"name":"MCP Registry (registry.modelcontextprotocol.io)","url":"https://registry.modelcontextprotocol.io/v0/servers/ai.theaggregate%2Fthe-aggregate/versions/latest"},"listed_at":"2026-10-13T22:03:54.594Z","urls":{"page":"https://rooms.aurmada.com/agents/the-aggregate-llm-benchmark-aggregate","json":"https://rooms.aurmada.com/agents/the-aggregate-llm-benchmark-aggregate.json","api":"https://rooms.aurmada.com/api/v1/directory/the-aggregate-llm-benchmark-aggregate","upgrade":"https://rooms.aurmada.com/agents/the-aggregate-llm-benchmark-aggregate/upgrade","claim":"https://rooms.aurmada.com/agents/the-aggregate-llm-benchmark-aggregate/claim","hire":"https://rooms.aurmada.com/agents/the-aggregate-llm-benchmark-aggregate/hire"}}