# Devstral Small 2 vs Laguna S 2.1 (slim)

> Devstral Small 2 and Laguna S 2.1 score within a point of each other for open-weight models you run yourself, 61 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.md (~9,650 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-laguna-s-2-1
- 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 and Laguna S 2.1 score within a point of each other on agent readiness, 61 (C) and 61 (C). Laguna S 2.1 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
- Laguna S 2.1: C 61, rank #45 of 160 open-weight models · https://www.anchorterminal.com/tools/laguna-s-2-1.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 75; Risk, 60 against 55; Documentation and upkeep, 46 against 41.
- Laguna S 2.1, good for Agents doing long coding sessions on a 128 GB machine or a multi-GPU server that want a permissive licence and a 1M context. Ahead on Agent interface, 85 against 65.

| Category | Devstral Small 2 | Laguna S 2.1 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 75 |
| Risk (20%) | 60 | 55 |
| Agent interface (10%) | 65 | 85 |
| Documentation and upkeep (10%) | 46 | 41 |

| Fact (where they differ) | Devstral Small 2 | Laguna S 2.1 |
| --- | --- | --- |
| Vendor | Mistral AI | Poolside |
| Licence | Apache-2.0 | OpenMDW-1.1 |
| Last release | 2026-07-15 | 2026-08-19 |
| Terms last updated | no document linked | 2026-07-21 |
| Privacy policy last updated | no document linked | 2026-07-21 |
| Customer content may train models | not read yet | yes, with an opt-out |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | yes |
| Arbitration or class-action waiver | not read yet | yes |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- Agent interface, Laguna S 2.1 +20: 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.); Laguna S 2.1 85 (Chat template 20, a Jinja file in the repository.)
- Reach, Devstral Small 2 +15: 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.); Laguna S 2.1 75 (Memory 10 of 30, the smallest 4-bit build is Ollama's 66 GB MLX nvfp4, which needs 96 GB with a fifth added and fits our 128 GB reference machine.)
- Risk, Devstral Small 2 +5: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Laguna S 2.1 55 (File safety 15 of 25, safetensors and GGUF only, but the repository ships model code behind auto_map and the card's SGLang and TensorRT-LLM commands use trust_r…)
- Documentation and upkeep, Devstral Small 2 +5: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Laguna S 2.1 41 (Model card 11 of 20, intended use, architecture, parameters and context are on the card, limitations, languages and a cut-off aren't.)