{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_c86r5qd9umjk","handle":"model-tested","url":"https://wellknown.network/agents/model-tested","links":{"self":"https://wellknown.network/agents/model-tested/record.json","html":"https://wellknown.network/agents/model-tested","markdown":"https://wellknown.network/agents/model-tested/record.md","api":"https://wellknown.network/api/v1/agents/model-tested","status":"https://wellknown.network/api/v1/agents/model-tested/status","claim":"https://wellknown.network/agents/model-tested/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/model-tested/claim.json","badge":"https://wellknown.network/agents/model-tested/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/model-tested/history","tools":"https://wellknown.network/api/v1/agents/model-tested/tools"},"ard":{"identifier":"urn:air:modeltested.com:server:model-tested","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"Model Tested","summary":"Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.","description":"Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.","publisher":{"name":"com.modeltested","url":null},"homepage":"https://modeltested.com/mcp/","repository":"https://github.com/jelly-ham/modeltested","version":"1.0.0","license":null,"protocols":["mcp"],"tags":[],"pricing":null,"endpoints":[{"url":"https://modeltested.com/mcp","type":"mcp_streamable_http","auth":null,"probeable":true}],"skills":null,"tools":null,"extra":{"updatedAt":"2026-10-18T03:58:38.345378Z","publishedAt":"2026-10-18T03:58:38.345378Z","registryName":"com.modeltested/llm-benchmarks"},"attribution":{"kind":"mcp_registry","name":"mcp_registry","repoUrl":"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":0.54,"provenance":"derived"}],"categories":["ai"],"language":"en"},"observed":{"status":"live","statusReason":"Responded 6h ago.","lastOkAt":"2026-10-25T14:26:32.120Z","lastProbedAt":"2026-10-25T14:26:32.120Z","statusComputedAt":"2026-10-25T14:30:05.782Z","reliability30d":{"probes":27,"successRate":1,"p50Ms":74,"basis":"service","measures":{"availability":"availability","latency":"response time","tools":"tool surface observed","summary":"Checks reached the service itself."},"checks":{"total":27,"ok":27,"authBoundaryOk":0,"serviceOk":27,"note":"Counted from the observation rows for the window, checks of the server only (HTTP, A2A card, MCP initialize). ok = authBoundaryOk + serviceOk. `probes` is the sum of daily rollups and includes registry checks, so it can differ from `total`."}},"latestObservations":[{"at":"2026-10-25T14:26:32.120Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":62,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-25T06:26:49.823Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":79,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T23:29:29.954Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":58,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T16:22:25.286Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":102,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T09:26:38.923Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":52,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-24T02:23:40.068Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":168,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-23T20:25:22.918Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":55,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-23T13:28:12.558Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":127,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-23T07:26:46.189Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":78,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}},{"at":"2026-10-23T00:29:55.542Z","kind":"mcp_initialize","ok":true,"httpStatus":200,"latencyMs":48,"error":null,"detail":{"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"toolCount":5,"toolsHash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","serverName":"modeltested","capabilities":["tools"],"serverVersion":"1.0.0","protocolVersion":"2025-06-18"}}],"tools":[{"name":"find_models","description":"Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their grap"},{"name":"get_model","description":"Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it n"},{"name":"compare_models","description":"Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 "},{"name":"decision_models","description":"Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing ticket"},{"name":"search_articles","description":"Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title,"}],"package":null,"toolSurface":{"id":"ts_v5qvfwb76u3d","endpointId":"ep_uvmj8rvvgx86","hash":"d1cf2d2df6fabd541f7c5b7c318f8f2fdd9ca68431cd0c81181f5863021a2c1a","toolCount":5,"serverName":"modeltested","serverVersion":"1.0.0","protocolVersion":"2025-06-18","firstSeenAt":"2026-10-18T07:24:50.973Z","lastSeenAt":"2026-10-25T14:26:32.133Z","observations":27,"toolNames":["find_models","get_model","compare_models","decision_models","search_articles"],"distinctSurfaces":1},"endpointFacts":[{"id":"ep_uvmj8rvvgx86","url":"https://modeltested.com/mcp","type":"mcp_streamable_http","factsCheckedAt":"2026-10-25T14:26:32.148Z","auth":{"observedAt":"2026-10-25T14:26:32.192Z","authRequired":false,"scheme":null,"resourceMetadata":null,"authorizationServer":null,"conformance":{"dpop":false,"rfc8414":false,"rfc9728":false,"pkceS256":false,"clientIdMetadataDocument":false,"dynamicClientRegistration":false}},"tls":{"observedAt":"2026-10-25T14:26:32.248Z","protocol":"TLSv1.3","chainValid":true,"chainError":null,"hostMatches":true,"subject":"modeltested.com","issuer":{"commonName":"WE1","organization":"Google Trust Services"},"validFrom":"2026-10-10T12:50:21.000Z","validTo":"2027-01-08T13:50:19.000Z","daysToExpiry":74,"sanCount":2,"fingerprint256":"B9:54:20:C8:FA:F3:29:0C:F6:80:63:48:A8:F8:15:6B:A4:8C:3C:19:04:35:0F:DC:09:35:C2:27:74:F2:7F:EA"}}]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"mcp_registry","key":"com.modeltested/llm-benchmarks","url":"https://registry.modelcontextprotocol.io/v0/servers/com.modeltested%2Fllm-benchmarks","firstSeenAt":"2026-10-18T07:18:37.564Z","fetchedAt":"2026-10-25T07:17:40.240Z","normalizedAt":"2026-10-25T07:17:40.240Z"}]},"firstSeenAt":"2026-10-18T07:18:37.564Z","updatedAt":"2026-10-25T14:31:31.059Z"}