# Devstral Small 2 vs LongCat-2.5 (slim)

> Devstral Small 2 scores 61 (C) to LongCat-2.5's 50.5 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.md (~8,800 tokens) · this version ~580 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-longcat-2-5
- 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)

Devstral Small 2 scores 61 (C) on agent readiness against LongCat-2.5's 50.5 (D), and leads in 1 of 4 scored categories. LongCat-2.5 leads on agent interface. Both do open-weight models you run yourself.

- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- LongCat-2.5: D 50.5, rank #145 of 160 open-weight models · https://www.anchorterminal.com/tools/longcat-2-5.min.md
- Devstral Small 2, good for Developers who want a dependable local coding agent on one consumer GPU or a 32 GB Mac Ahead on Reach, 90 against 35.
- LongCat-2.5, good for Operators with NPU clusters, and anyone tracking what the open flagships can do Ahead on Agent interface, 75 against 65.

| Category | Devstral Small 2 | LongCat-2.5 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 35 |
| Risk (20%) | 60 | 60 |
| Agent interface (10%) | 65 | 75 |
| Documentation and upkeep (10%) | 46 | 46 |

| Fact (where they differ) | Devstral Small 2 | LongCat-2.5 |
| --- | --- | --- |
| Vendor | Mistral AI | Meituan (LongCat) |
| Licence | Apache-2.0 | MIT |
| Last release | 2026-07-15 | 2026-11-10 |
| Terms last updated | no document linked | not read yet |

Why the edge:
- Reach, Devstral Small 2 +55: Devstral Small 2 90 (Memory 25, the smallest build at 4 bits from a runtime's own library is Ollama's devstral-small-2 at Q4_K_M, 15 GB, and 15 GB × 1.2 = 18 GB, within 24 GB.); LongCat-2.5 35 (Memory 0, the smallest build is Meituan's W4A4 repository, 1,336 GB, and 1,336 GB × 1.2 = 1,603 GB, far above 256 GB.)
- Agent interface, LongCat-2.5 +10: Devstral Small 2 65 (Chat template 20, chat_template.jinja in the repository (11,362 characters), with the tokenizer's tekken file for mistral-common.); LongCat-2.5 75 (Chat template 20, chat_template.jinja in the repository (11,823 characters), with a copy in tokenizer_config.json.)