OpenMark

Ingested from the official MCP Registry

FastDrop pulled this entry from the official MCP Registry as ai.openmark/openmark and probed the endpoint. The maker did not submit it, so the outbound link is not endorsed and the description is not theirs.

If this is your server, claim the listing to edit it and take ownership. The registry index lists everything else still awaiting a probe.

Tools this endpoint exposes

Read directly from the endpoint on 18 Oct 2026. Not supplied by the maker.

• get_task_format

  How to write an OpenMark task: the YAML structure, every scoring mode, and tips. Call this before writing a task.

• list_models

  Current OpenMark model ids with list prices ($ per 1M tokens). Use these ids in run_benchmark. Append @low, @medium or @high to a reasoning model id to set its reasoning effort.

• run_benchmark

  Save 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; poll get_results. Spends the user's credits.

• get_results

  Status of a benchmark job, and once completed the ranked results: score, stability, cost per run and latency for every model.

• watch_task

  Watch the task of a completed job: OpenMark re-tests it on new or cheaper models as they ship (no credits used) and emails the user only when one beats the best model of that job.

Is this tool yours?

Claim this listing and we’ll verify ownership before handing it over.