# Open-weight models compared head to head

> 3 head-to-head comparisons of open-weight models you download and run yourself for AI agents, grouped by the job each pair shares, with benchmark scores for both sides.

- Canonical: https://www.anchorterminal.com/compare/open-weights/
- Markdown: https://www.anchorterminal.com/compare/open-weights/index.md (~350 tokens)
- Slim: https://www.anchorterminal.com/compare/open-weights/index.min.md (~280 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/open-weights/index.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: 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)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-10-20

- Ranked table: https://www.anchorterminal.com/categories/open-weights.md

## Ranked

1. [Kolibri-1](https://www.anchorterminal.com/tools/kolibri-1.md) BB 75.8
2. [Qwen3.8-27B](https://www.anchorterminal.com/tools/qwen3-8-27b.md) B 63.7
3. [DeepSeek V4.1 Flash](https://www.anchorterminal.com/tools/deepseek-v4-1-flash.md) B 62.8

## Open-weight models you run yourself

- [DeepSeek V4.1 Flash vs Kolibri-1](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-kolibri-1.md): B 62.8 vs BB 75.8
- [DeepSeek V4.1 Flash vs Qwen3.8-27B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-qwen3-8-27b.md): B 62.8 vs B 63.7
- [Kolibri-1 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/kolibri-1-vs-qwen3-8-27b.md): BB 75.8 vs B 63.7


---

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