Agents Index

OpenMark

Online

Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.

Visit publisherConnectJSON

What it can do: 10 tools

  • get_task_formatHow to write an OpenMark task: the YAML structure, all 18 scoring modes, and tips. Call this before writing a task. Pass a topic for the full detail on one subject (the app's Task Guide): fields, scoring, composite, chai
  • validate_taskCheck a task YAML the way OpenMark will before running it: structure, scoring settings, and the test limit of the user's plan. Free, saves nothing. Returns the problems to fix and warnings worth a look.
  • list_modelsCurrent OpenMark model ids with list prices ($ per 1M tokens), as text and as a structured list. Use these ids in run_benchmark. Append @low, @medium or @high to a reasoning model id to set its reasoning effort.
  • prepare_attachmentsGet an upload_uid and a one-hour upload link (no API key needed) for images, PDFs or text documents, with the exact curl command. Upload the files, reference them by file name in each test's attachments list, then pass t
  • estimate_costCredits a run_benchmark call would use, before spending anything: the expected total, the split per model, the balance needed to start, the worst case, and the user's balance. Same inputs and run settings as run_benchmar
  • run_benchmarkSave a task (YAML, see get_task_format) to the user's OpenMark account and run it on the given models with real API calls. Returns a job_id and the expected cost; poll get_results. Spends the user's credits; pass max_cre
  • get_resultsStatus of a benchmark job, and once completed the ranked results (score, stability, cost per run, latency), the tests each model missed with its answer, a recommendation for the chosen objective and quick picks for the o
  • export_openclaw_csvA completed job's results as the CSV the OpenMark Router plugin for OpenClaw reads (the same file as the app's Export > OpenClaw). Save it in the plugin's benchmarks folder, by default ~/.openclaw/workspace/plugins/openm
  • get_accountThe user's plan, credit balance and limits, and what a credit pack, Pro or Expert would unlock. Use it before large runs, or when a run is refused for credits or limits.
  • watch_taskWatch the task of a completed job: when new or cheaper models ship, OpenMark re-tests up to 4 of them next to the user's pick and emails the user only when one beats it. Each check uses the user's credits at the normal r

Connect it

Claude Code
claude mcp add --transport http openmark https://openmark.ai/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://openmark.ai/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "openmark": {
      "url": "https://openmark.ai/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "openmark": {
      "type": "http",
      "url": "https://openmark.ai/mcp"
    }
  }
}

Questions

What does OpenMark do?

Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes. It exposes 10 tools to AI assistants.

What tools does OpenMark provide?

10 tools, including get_task_format, validate_task, list_models, prepare_attachments, estimate_cost, run_benchmark, get_results, export_openclaw_csv, get_account, watch_task.

How do I connect OpenMark to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://openmark.ai/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does OpenMark require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is OpenMark online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes OpenMark?

openmark.ai. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Agents & Orchestration