BenchLeader

com.benchleaderPublished by benchleader.comOfficial publisherv1.0.0Updated Oct 31, 2026

Daily LLM leaderboard from independent benchmarks: ranks, scores, prices, speed and comparisons.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

BenchLeader gives an assistant a daily leaderboard of large language models built from independent public benchmarks, with ranks, scores, prices, speed and…

What you can do
  • Browse the daily BenchLeader Index leaderboard, optionally ranked by category score such as coding, agentic, reasoning, math or knowledge
  • Search models by name, alias, id or developer and get each match's rank, Index and reasoning-effort configurations
  • Read one model's profile: Index and rank, category scores, list price, speed, latency, context window and strongest benchmark results
  • Compare two models head-to-head with a verdict on quality, price and speed ratios, category wins and when to choose each
  • List and inspect the benchmarks behind the Index, including what each measures, publisher, weight, coverage and caveats
  • Explain how the Index is computed, its method version, data date…
When to use it
Useful when choosing between LLMs, justifying a model choice with independent benchmark evidence, or checking current prices, speed and context windows before building on a model.
Requirements
Remote streamable HTTP endpoint at benchleader.com; no packages, environment variables or headers declared. No authentication is declared.
Before you install
Figures are third-party composite rankings and should be attributed using the url fields the server returns; treat scores as one input to a decision rather than a definitive verdict.

Installation

In SourceWeft

  1. Open BenchLeader in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.benchleader%2Fbenchleader/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

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

Tools

7

get_leaderboard

BenchLeader leaderboard

The 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 category score (coding, agentic, reasoning, math, knowledge…), list every model × effort configuration, or filter to open-weights models or one developer. Paged.

Parameterslimitoffsetcategorydeveloperconfigurationsopen_weights_only

search_models

Search models

Find 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.

Parameterslimitqueryrequired

get_model

Model details

One 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 board rank, publisher and source link).

Parametersmodelrequiredeffortresults_limit

compare_models

Compare two models

Head-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, and shared benchmark results. Links the comparison page.

Parametersmodel_arequiredmodel_brequiredeffort_aeffort_b

list_benchmarks

List benchmarks

The 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.

Parameterslimitqueryoffsetcategoryin_index_only

get_benchmark

Benchmark details

One 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).

Parameterslimitbenchmarkrequired

about_benchleader

About BenchLeader

What 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.

Takes no parameters.

Version history

1
  1. v1.0.0LatestOct 31, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.