# Devstral Small 2 vs Mistral Large 4 (slim)

> Devstral Small 2 scores 61 (C) to Mistral Large 4's 54.6 (C) 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-mistral-large-4.md (~9,850 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-mistral-large-4
- 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 Mistral Large 4's 54.6 (C), and leads in 1 of 4 scored categories. Mistral Large 4 leads on risk, agent interface and documentation and upkeep. 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
- Mistral Large 4: C 54.6, rank #128 of 160 open-weight models · https://www.anchorterminal.com/tools/mistral-large-4.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 50.
- Mistral Large 4, good for Operators with an 8-GPU Blackwell or H200 node who want a frontier-sized open model for coding agents and defensive security, with a hosted twin on Mistral's API. Ahead on Risk, 75 against 60; Agent interface, 95 against 65; Documentation and upkeep, 64 against 46.

| Category | Devstral Small 2 | Mistral Large 4 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 50 |
| Risk (20%) | 60 | 75 |
| Agent interface (10%) | 65 | 95 |
| Documentation and upkeep (10%) | 46 | 64 |

| Fact (where they differ) | Devstral Small 2 | Mistral Large 4 |
| --- | --- | --- |
| Licence | Apache-2.0 | Mistral Ecosystem Open-Weight License (modified MIT) |
| Last release | 2026-07-15 | 2026-10-29 |

Why the edge:
- Reach, Devstral Small 2 +40: 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.); Mistral Large 4 50 (Memory scores 0, since the smallest 4-bit build, Mistral's NVFP4, is 610 GB, about 732 GB with a fifth added, far above 256 GB.)
- Agent interface, Mistral Large 4 +30: 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.); Mistral Large 4 95 (The chat template is in the repository (20).)
- Documentation and upkeep, Mistral Large 4 +18: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Mistral Large 4 64 (The card covers intended use, architecture, parameters, context and languages, and misses limitations and a cut-off (14).)
- Risk, Mistral Large 4 +15: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Mistral Large 4 75 (File safety scores 25, safetensors only and loaded by Transformers' own code with a Jinja template.)