com.modeltested/llm-benchmarks

up checked 2026-11-11T03:37:49.839Z

Unclaimed · Unverified

Publisher-provided title

Model Tested

Publisher-provided description

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

Summary by lookupd

Look up benchmark scores, rankings, memory needs and comparisons for open-weight LLMs, and find articles on newly tested models.

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http llm-benchmarks https://modeltested.com/mcp

Codex, remote (streamable-http)

codex mcp add llm-benchmarks --url https://modeltested.com/mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "llm-benchmarks": {
      "url": "https://modeltested.com/mcp"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Publisher-provided text

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 grap
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 n
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
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 ticket
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,

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/com.modeltested/llm-benchmarks.svg)](https://lookupd.com/servers/com.modeltested/llm-benchmarks)