BenchLeader

Connect it to your AI

Claude Code

claude mcp add --transport http benchleader https://www.benchleader.com/mcp

Claude, ChatGPT, Cursor and other apps

Add it as a custom connector with this URL (Streamable HTTP):

https://www.benchleader.com/mcp

Cursor, VS Code and other apps (mcp.json)

{
  "mcpServers": {
    "benchleader": {
      "url": "https://www.benchleader.com/mcp"
    }
  }
}

Tools it offers

7 tools, as the server itself reported during our check on Oct 31, 2026.

• get_leaderboardThe BenchLeader Index leaderboard of large language models: a daily composite of independent public benchmarks, one row per model (its best reasoning-effort configuration) as on the homepage. Optionally rank by one categ
• search_modelsFind models by name, alias, id or developer ("opus", "gemini 4", "deepseek"). Returns each match's id, rank, Index and reasoning-effort configurations, for use with get_model and compare_models.
• get_modelOne model's BenchLeader profile: Index and rank, category scores, list price, speed, latency, context window, its other reasoning-effort configurations, and its strongest independent benchmark results (each with its boar
• compare_modelsHead-to-head comparison of two models with BenchLeader's verdict: who leads on quality (a lead is claimed only outside the combined margin of error), price and speed ratios, category-by-category wins, when to choose each
• list_benchmarksThe benchmarks BenchLeader reads: what each measures, publisher, category, whether it feeds the Index (and its weight), how many models it covers, status and caveats. Filter by category or a search query. Paged.
• get_benchmarkOne benchmark: what it measures, unit, publisher and source, whether and how much it counts in the BenchLeader Index, status and caveats, and its top models (one row per model, best result first).
• about_benchleaderWhat BenchLeader is, how the BenchLeader Index is computed, the current method version, data date and update cadence, coverage counts, licence and how to cite it.

Questions