# Lab score: open-weight models on our own evaluation

> Open-weight models answering 59 questions about Anchor Terminal through its MCP server, pages and API, scored 0 to 100, with every run dated.

- Canonical: https://www.anchorterminal.com/lab/evaluation/
- Markdown: https://www.anchorterminal.com/lab/evaluation/index.md (~450 tokens)
- Slim: https://www.anchorterminal.com/lab/evaluation/index.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/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: 2026-11-18

Each open-weight model the lab runs answers 59 questions about Anchor Terminal through our MCP server, pages and API, three times over, calling the tools itself or writing programs that call them, as it chooses. The right answers come from the site when each question is asked. The Lab score, 0 to 100, is the questions it got right with harder ones counting more.

No model has a Lab score yet.

## Every evaluation

A run in code mode, where the model may only write programs, is kept beside the Lab score's runs and scores nothing.

| Date | Model | Mode | Score | Right |
| --- | --- | --- | --- | --- |
| 18 November 2026 | qwen3.8-27b | code only | 89 | 54 of 59 |

The questions: https://github.com/Anchor-Terminal/anchorlab/blob/main/eval/tasks.go

An answer is checked against the site before and after the model answered, a question whose subject left the site or that has two right answers is skipped, and an answer with no lookup behind it counts as wrong. A question counts as right when it's right in more than half of three passes; a level 2 question counts twice and a level 3 question three times.

JSON: https://www.anchorterminal.com/api/v1/lab-evals.json

---

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