LLMBenchmark.ai

● Active

ai.llmbenchmark/llmbenchmark

Which LLM for which task: benchmark scores and API prices for 400+ models. Free, no key.

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "llmbenchmark": {
      "command": "uvx",
      "args": [
        "llmbenchmark-mcp"
      ]
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add llmbenchmark -- uvx llmbenchmark-mcp
OpenAI Codex CLI
codex mcp add llmbenchmark -- uvx llmbenchmark-mcp
VS Code
code --add-mcp '{"name":"llmbenchmark","type":"stdio","command":"uvx","args":["llmbenchmark-mcp"]}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & Agents
Version
1.0.1
Registry
active
Published
11/19/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: LLMBenchmark.ai is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit 3 days ago (Nov 19, 2026), 0 open issues.
Official registry
Active
Published as ai.llmbenchmark/llmbenchmark in the official MCP registry, version 1.0.1.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Local package or hosted
Ships as a local package (PyPI) that runs on your machine, and as a hosted endpoint at api.llmbenchmark.ai that receives what your client sends it.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 07:07 UTCStatus history & uptime →
● Working648 msprotocol 2025-06-18v1.0.0promptsresourcestools

The endpoint answered the MCP handshake as "LLMBenchmark.ai: which LLM for which task" and listed 6 tools. Answering since Nov 21, 2026.

Context cost ≈ 1k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 6 tools.

Tools (6)

  • recommend_model5 params

    Which model should I use for this task? Maps the task text to a category (coding, agentic, reasoning, math, knowledge, web design, or overall when nothing matches) by a fixed keyword map, filters by output price per million tokens, context length and open weights, and ranks by that category's benchmark board. Deterministic, no LLM call. Returns top_k models with scores, rank, prices, context, page URLs and a one-line reason. overall is the LLMBenchmark Index: a weighted mean of the Vibe Coding Index, the agentic, reasoning, math and knowledge indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.

    Show parameters
    • taskstringrequired
    • max_output_price_per_m
    • min_context_tokens
    • open_weights_onlyboolean
    • top_kinteger
  • The top models on one category's board. category is one of overall, coding, agentic, reasoning, math, knowledge, design (see list_categories). limit is 1 to 50. overall is the LLMBenchmark Index: a weighted mean of the Vibe Coding Index, the agentic, reasoning, math and knowledge indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.

    Show parameters
    • categorystring
    • limitinteger
  • Two models side by side: score on every category board where both were measured, prices, context. Names are matched loosely: 'claude opus', 'gpt-5' or a slug all work.

    Show parameters
    • model_astringrequired
    • model_bstringrequired
  • get_model1 param

    One model: maker, release date, prices, context, open weights, and its score and rank on every category board. Name or slug.

    Show parameters
    • modelstringrequired
  • get_prices3 params

    API prices (USD per million tokens), cheapest output price first: the maker's own price when it serves the model on OpenRouter, else the median of providers (price_basis says which), plus the cheapest provider. Filter by model name and/or maker; limit is 1 to 100.

    Show parameters
    • model
    • maker
    • limitinteger
  • The categories recommend_model and get_leaderboard know, the benchmark board behind each, and the task keywords that select it.

Checked by Serverdex with a plain initialize + tools/list call to api.llmbenchmark.ai/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 21, 2026
Stars
0
Forks
0
Last push
Nov 19, 2026
License
MIT

Pythonai-modelsbenchmarkllmllm-benchmarkllm-pricingmcpmcp-servermodel-context-protocol

From the README

LLMBenchmark.ai MCP server Ask "which model should I use for this task?" and get an answer from benchmark scores and API prices of 400+ LLMs, updated daily. • Free. No API key. 500 requests per IP per UTC day. • Remote server, Streamable HTTP: https://api.llmbenchmark.ai/mcp • Deterministic: no LLM call inside, the same task and the same data return the same answer. • Every answer carries the data date, the source ("LLMBenchmark.ai") and links to the pages behind the numbers. Docs: https://llmbenchmark.ai/api Install Claude Code Cursor (.cursor/mcp.json) Codex (~/.codex/config.toml) Claude Desktop (claudedesktopconfig.json, through the mcp-remote bridge) Install as a local server (stdio) The package proxies to the hosted server, so clients that only start local commands can use it too. Needs uv. Claude Desktop (claudedesktopconfig.json): Docker, built from this repository: Set LLMBENCHMARKMCPURL to point the proxy at another endpoint. Tools recommend_model maps the task to a category with a fixed keyword map (printed at https://llmbenchmark.ai/api#how-recommend-works), drops models that break your limits and ranks the rest on that category's board.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://api.llmbenchmark.ai/mcp

The most-starred AI & Agents servers in the index, with their live-check result.

ServerStarsLast pushLive check
Ruflo81,994Nov 2026Local / not checked
Claude Flow81,985Nov 2026Local / not checked
CodeBurn11,880Nov 2026Local / not checked
Kaneo9,825Nov 2026Local / not checked
Ha MCP7,958Nov 2026Local / not checked

LLMBenchmark.ai: questions people ask

Is LLMBenchmark.ai a remote or a local MCP server?
According to its entry in the official MCP registry, LLMBenchmark.ai ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (PyPI) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
Does LLMBenchmark.ai need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is LLMBenchmark.ai safe to use?
Looks healthy: LLMBenchmark.ai is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Local package or hosted; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is LLMBenchmark.ai still maintained?
Active: the repository's last commit 3 days ago. Last push Nov 19, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
What tools does LLMBenchmark.ai expose?
6 tools as listed by the server itself during the live check, including recommend_model, get_leaderboard, compare_models, get_model, get_prices. The full list with parameters is in the Live check section above.
How do I add LLMBenchmark.ai to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all AI & Agents →

Add the badge to your site

Show visitors that LLMBenchmark.ai is listed here — it’s also the link we check for a free listing.

LLMBenchmark.ai — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/ai-llmbenchmark-llmbenchmark?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="LLMBenchmark.ai — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![LLMBenchmark.ai — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/ai-llmbenchmark-llmbenchmark?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/ai-llmbenchmark-llmbenchmark) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/ai-llmbenchmark-llmbenchmark) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/ai-llmbenchmark-llmbenchmark)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/ai-llmbenchmark-llmbenchmark"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/ai-llmbenchmark-llmbenchmark"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/ai-llmbenchmark-llmbenchmark"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).