{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_s4rughm8yzx8","handle":"the-aggregate-llm-benchmark-aggregate","url":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate","links":{"self":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate/record.json","html":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate","markdown":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate/record.md","api":"https://wellknown.network/api/v1/agents/the-aggregate-llm-benchmark-aggregate","status":"https://wellknown.network/api/v1/agents/the-aggregate-llm-benchmark-aggregate/status","claim":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate/claim","claimApi":"https://wellknown.network/api/v1/claims","badge":"https://wellknown.network/agents/the-aggregate-llm-benchmark-aggregate/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air:theaggregate.ai:server:the-aggregate-llm-benchmark-aggregate","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"The Aggregate — LLM benchmark aggregate","summary":"Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.","description":"Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.","publisher":{"name":"ai.theaggregate","url":null},"homepage":"https://theaggregate.ai/mcp","repository":null,"version":"1.0.1","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://theaggregate.ai/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-07-25T18:25:18.84469Z","publishedAt":"2026-07-25T18:25:18.84469Z","registryName":"ai.theaggregate/the-aggregate"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","summary":"mcp_registry","version":"mcp_registry","description":"mcp_registry","homepageUrl":"mcp_registry","publisherName":"mcp_registry"}},"derived":{"capabilities":[{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":1,"provenance":"derived"}],"categories":["ai"]},"observed":{"status":"unknown","statusReason":"Not checked yet.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[{"at":"2026-09-05T18:27:19.458Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":17,"error":null,"detail":{"tools":[{"name":"get_leaderboard","description":"Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over ~5,000 public benchmark leaderboards. One row per mod"},{"name":"search_models","description":"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"},{"name":"get_model","description":"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 perce"},{"name":"compare_models","description":"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."},{"name":"search_benchmarks","description":"Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL."},{"name":"get_benchmark","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"},{"name":"get_prediction_duel","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"},{"name":"about_the_aggregate","description":"What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it."}],"toolCount":8,"serverName":"the-aggregate","capabilities":["tools"],"serverVersion":"1.0.1","protocolVersion":"2025-06-18"}}],"tools":[{"name":"get_leaderboard","description":"Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over ~5,000 public benchmark leaderboards. One row per mod"},{"name":"search_models","description":"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"},{"name":"get_model","description":"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 perce"},{"name":"compare_models","description":"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."},{"name":"search_benchmarks","description":"Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL."},{"name":"get_benchmark","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"},{"name":"get_prediction_duel","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"},{"name":"about_the_aggregate","description":"What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it."}],"package":null},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"ai.theaggregate/the-aggregate","url":"https://registry.modelcontextprotocol.io/v0/servers/ai.theaggregate%2Fthe-aggregate","firstSeenAt":"2026-09-05T14:18:32.977Z","fetchedAt":"2026-09-05T14:18:32.977Z","normalizedAt":"2026-09-05T14:18:32.977Z"}]},"firstSeenAt":"2026-09-05T14:18:32.977Z","updatedAt":"2026-09-05T14:19:00.102Z"}