# Arete-27B vs Kronos (slim)

> Kronos and Arete-27B score within a point of each other for open-weight models you run yourself, 55.2 and 55.1 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/arete-27b-vs-kronos.md (~7,850 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/arete-27b-vs-kronos.json · canonical https://www.anchorterminal.com/compare/arete-27b-vs-kronos
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Kronos and Arete-27B score within a point of each other on agent readiness, 55.2 (C) and 55.1 (C). Arete-27B leads on risk. Both do open-weight models you run yourself.

- Arete-27B: C 55.1, rank #123 of 160 open-weight models · https://www.anchorterminal.com/tools/arete-27b.min.md
- Kronos: C 55.2, rank #122 of 160 open-weight models · https://www.anchorterminal.com/tools/kronos.min.md
- Arete-27B, good for Agents that want Qwen3.8-27B's coding and tool use without its handling of politically sensitive topics, on a 24 GB card or a 128 GB machine Ahead on Risk, 55 against 50.
- Kronos, good for Agents that need a quick local forecast or synthetic sample of a candlestick series on modest hardware, for research or as one input among others. Ahead on Reach, 55 against 50.

| Category | Arete-27B | Kronos |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 50 | 55 |
| Risk (20%) | 55 | 50 |
| Agent interface (10%) | 60 | 60 |
| Documentation and upkeep (10%) | 63 | 61 |

| Fact (where they differ) | Arete-27B | Kronos |
| --- | --- | --- |
| Vendor | Nous Research | Yu Shi (shiyu-coder, NeoQuasar), Tsinghua University |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-11-06 | 2026-04-13 |
| Popularity | none | 43k stars |

Why the edge:
- Reach, Kronos +5: Arete-27B 50 (Memory 10, the only build from Nous Research is the 54.7 GB BF16 release, which needs about 66 GB and fits the reference machine.); Kronos 55 (Memory 30, the publisher's Kronos-mini with its tokeniser is 0.03 GB and even Kronos-base is 0.43 GB in FP32. Runtimes 0, it runs only through the publisher's o…)
- Risk, Arete-27B +5: Arete-27B 55 (File safety 25, safetensors only and no remote code.); Kronos 50 (File safety 15, safetensors only, but the only documented loading path is the publisher's Python package in place of a runtime.)