{"name":"com.modeltested/llm-benchmarks","slug":"modeltested-llm-benchmarks","title":"Model Tested","description":"Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.","url":"https://mcp.market/server/modeltested-llm-benchmarks","rating":null,"grade":"A","score":91,"certified":false,"status":"active","category":"ai","tags":["ai"],"presence":{"score":23,"stars":0,"forks":0,"downloads_week":null,"last_push_at":"2026-10-27T12:23:07.000Z","license":null},"uptime":{"percent":100,"checks":28,"ok":28,"last_checked_at":"2026-11-04T07:00:46.793Z","last_ok_at":"2026-11-04T07:00:46.793Z","latency_ms":107},"claimed":false,"transport":"remote","callable_via_gateway":true,"default_price_micros":0,"repository":"https://github.com/jelly-ham/modeltested","website":"https://modeltested.com/mcp/","version":"1.0.0","remotes":[{"type":"streamable-http","url":"https://modeltested.com/mcp"}],"packages":[],"tools":[{"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 models side by side.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"models":{"type":"array","items":{"type":"string"},"minItems":2,"maxItems":6,"description":"Model names or slugs."}},"required":["models"]}},{"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 tickets, applying rules, spotting phishing, flagging risky code changes), how well each model's confidence matches its accuracy (calibration), and API cost per 1,000 calls. Covers dedicated decision models and regular LLMs given the same tasks.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["decision","llm","all"],"description":"decision = dedicated decision models only (default), llm = regular LLMs only."},"limit":{"type":"integer","minimum":1,"maximum":50,"description":"Default 15."}}}},{"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 graphics card (VRAM) or Mac. Returns tested models ranked by our own test scores, best first; with a GPU or Mac memory size it only returns models that fit, plus the quantization to download and the memory it needs. Examples: 'best model for a 16 GB GPU', 'best coding model on a 32 GB Mac', 'best small model under 10B'.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"sort_by":{"type":"string","enum":["overall","coding","documents","decisions","hard"],"description":"Score to rank by. Default overall."},"hardware":{"type":"string","enum":["gpu","mac"],"description":"Graphics card (VRAM) or Mac (unified memory)."},"memory_gb":{"type":"number","description":"VRAM or Mac memory in GB. Needs hardware."},"max_params_b":{"type":"number","description":"Only models with at most this many billion parameters."},"limit":{"type":"integer","minimum":1,"maximum":30,"description":"Default 10."}}}},{"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 needs, or which quantization to download. Returns our test scores, rank, memory at each quantization, the smallest GPU and Mac it fits, decision accuracy and our Q4 run on a Mac when there is one. Accepts a name or slug, e.g. 'qwen3.5 9b' or 'gpt-oss-20b'.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"model":{"type":"string","description":"Model name or slug."}},"required":["model"]}},{"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, summary, date and link.","write_action":false,"price_micros":0,"input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Words to look for, e.g. 'quantization' or 'ornith'. Empty lists the latest."},"limit":{"type":"integer","minimum":1,"maximum":20,"description":"Default 8."}}}}],"scan":{"score":91,"grade":"A","scanned_at":"2026-10-28T05:57:32.934Z","report":{"scannerVersion":"0.1.10","scannedAt":"2026-10-28T05:57:32.884Z","components":{"code":{"score":-1,"max":25,"notes":["remote-only server, no package to scan"]},"reliability":{"score":20,"max":20,"notes":["remote reachable in 305ms"]},"poisoning":{"score":15,"max":15,"notes":["5 tool descriptions checked"]},"auth":{"score":10,"max":15,"notes":["open endpoint, read-only tools"]},"maintenance":{"score":15,"max":15,"notes":["last push 1 days ago"]},"identity":{"score":8,"max":10,"notes":["endpoint served from the registry-verified namespace domain"]}},"findings":[],"inputs":{"probes":[{"url":"https://modeltested.com/mcp","reachable":true,"authRequired":false,"latencyMs":305,"serverInfo":{"name":"modeltested","version":"1.0.0"}}],"packages":[],"repo":{"found":true,"owner":"jelly-ham","repo":"modeltested","archived":false,"pushedAt":"2026-10-27T12:23:07Z","stars":0,"forks":0,"openIssues":1,"ownerType":"User","ownerAvatarUrl":"https://avatars.githubusercontent.com/u/263522418?v=4","ownerCreatedAt":"2026-02-24T02:54:04Z"},"icon":{"url":"https://modeltested.com/favicon-v2.svg","source":"site"},"presence":{"stars":0,"forks":0,"downloadsWeek":null,"license":null,"lastPushAt":"2026-10-27T12:23:07.000Z","score":23}}}},"grade_history":[],"reviews":[]}