# The lab's evaluations

> The evaluations Anchor Terminal's lab runs, each a fixed set of questions with known answers. The first is of open-weight models, scored 0 to 100, with every run dated.

- Canonical: https://www.anchorterminal.com/benchmark/lab/evaluation/
- Markdown: https://www.anchorterminal.com/benchmark/lab/evaluation/index.md (~300 tokens)
- Slim: https://www.anchorterminal.com/benchmark/lab/evaluation/index.min.md (~230 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/benchmark/lab/evaluation/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-22

An evaluation is a fixed set of questions with known answers that the lab runs the same way every time, so two results can be put side by side. Open-weight models are the first, and more will be listed here as the lab runs them.

- Open-weight models, on questions about this site (set anchor-lab-eval/1): 59 questions with one right answer, 3 passes each, scored 0 to 100. https://www.anchorterminal.com/benchmark/lab/evaluation/models/index.md

The evaluations run on the lab's box: https://www.anchorterminal.com/benchmark/lab/index.md

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp
