EVAL SYS

Open-source community initiated by LobeHub to track agentic capabilities. Maintains MCPMark. mcpmark.ai/about links x.com/evalsysorg, and the eval-sys GitHub org lists the same handle (seen 2026-09-24).

Their benchmarks in the atlas

MCPMark Verifiedby EVAL SYS, LobeHub and NUS TRAILTask level · Pass@1 (single run)
96.1%kimi-k3-max · 20 Jul 2026
Saturated

Work their benchmarks cover

Office and administrative support Software engineering Data and analytics

Embed this card

The image names the institutions behind the numbers and links back to this page.

HTML:

<a href="https://canagentswork.com/institutions/eval-sys/"><img src="https://canagentswork.com/og/institutions-eval-sys.png" width="600" height="315" alt="EVAL SYS's agent benchmarks, mapped onto the world of work:" loading="lazy"></a>

Markdown:

[![EVAL SYS's agent benchmarks, mapped onto the world of work:](https://canagentswork.com/og/institutions-eval-sys.png)](https://canagentswork.com/institutions/eval-sys/)

For EVAL SYS: link to this page

You can link to this page from your site. Copy this HTML:

<a href="https://canagentswork.com/institutions/eval-sys/">Featured in the Work Atlas — Can Agents Work?</a>

If a summary or number on this page is wrong, tell us. We correct errors within 48 hours of a report. To grant permission to show your logo, contact us; until then we show only your name.