Embed Score
55/100
An LLM eval harness graded by computed ground truth, not an LLM judge. Worked example: poker, served to models as MCP to…
Score Badge shields.io style
Minimal inline badge — best for README tables and lists.
Markdown
[](https://agentrank-ai.com/tool/yangstar89--ground-truth-evals/) HTML
<a href="https://agentrank-ai.com/tool/yangstar89--ground-truth-evals/"><img src="https://agentrank-ai.com/api/badge/tool/yangstar89--ground-truth-evals" alt="AgentRank"></a> Score Widget — SVG GitHub README
Rich widget with signal breakdown. Use in GitHub READMEs where iframes aren't allowed.
Markdown
[](https://agentrank-ai.com/tool/yangstar89--ground-truth-evals/) HTML
<a href="https://agentrank-ai.com/tool/yangstar89--ground-truth-evals/"><img src="https://agentrank-ai.com/api/embed/yangstar89--ground-truth-evals.svg" alt="AgentRank" height="148"></a> Score Widget — Live blogs & sites
Interactive widget with light/dark mode. Use in blogs, newsletters, or any site that supports iframes.
HTML iframe
<iframe src="https://agentrank-ai.com/api/embed/yangstar89--ground-truth-evals.html" width="340" height="170" frameborder="0" style="border-radius:6px;border:none;overflow:hidden;"></iframe> JS snippet
<script src="https://agentrank-ai.com/embed.js" data-tool="yangstar89/ground-truth-evals"></script>