# Model Tested

> Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.

- name: com.modeltested/llm-benchmarks
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 81/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.modeltested%2Fllm-benchmarks
- tools: https://api.protogrid.dev/v1/servers/com.modeltested%2Fllm-benchmarks/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "llm-benchmarks": {
      "type": "http",
      "url": "https://modeltested.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-100% +updated-3d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 81/100 (new)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 5 of 5 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: find_models (destructiveHint, idempotentHint); compare_models (destructiveHint, idempotentHint); decision_models (destructiveHint, idempotentHint); …
- pass `tools.token_cost`: about 816 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: n/a (weight 15)

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 2 of the 7 days needed

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 816 tokens to load them all
- tool set hash: aa91d06ed71247fd77f61c8bd197c6de
- badge: [![protogrid quality](https://protogrid.dev/badge/com.modeltested/llm-benchmarks.svg)](https://protogrid.dev/servers/com.modeltested/llm-benchmarks)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://modeltested.com/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (5)

- `compare_models`: 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.
- `decision_models`: 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.
- `find_models`: 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'.
- `get_model`: 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'.
- `search_articles`: 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.