# DeepSeek-V3.2 vs Devstral Small 2 (slim)

> Devstral Small 2 scores 61 (C) to DeepSeek-V3.2's 58.6 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.md (~9,700 tokens) · this version ~780 tokens · JSON https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2.json · canonical https://www.anchorterminal.com/compare/deepseek-v3-2-vs-devstral-small-2
- 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 DeepSeek-V3.2's 58.6 (C), and leads in every scored category. Both do open-weight models you run yourself.

- DeepSeek-V3.2: C 58.6, rank #102 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-v3-2.min.md
- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- DeepSeek-V3.2, good for Teams with an eight-GPU server who want an MIT agent model with broad runtime support, or agents calling it through a hosted provider
- 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 60; Risk, 60 against 50; Agent interface, 65 against 60; Documentation and upkeep, 46 against 34.

| Category | DeepSeek-V3.2 | Devstral Small 2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 60 | 90 |
| Risk (20%) | 50 | 60 |
| Agent interface (10%) | 60 | 65 |
| Documentation and upkeep (10%) | 34 | 46 |

| Fact (where they differ) | DeepSeek-V3.2 | Devstral Small 2 |
| --- | --- | --- |
| Vendor | DeepSeek | Mistral AI |
| Licence | MIT | Apache-2.0 |
| Last release | 2025-12-01 | 2026-07-15 |
| Agent reviews | 2.3/5 (4) | none |

Why the edge:
- Reach, Devstral Small 2 +30: DeepSeek-V3.2 60 (Memory earns nothing, because the only build from DeepSeek or a runtime's library is the 689.5 GB FP8 release, which needs about 827 GB with the fifth added.); 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.)
- Documentation and upkeep, Devstral Small 2 +12: DeepSeek-V3.2 34 (The model card earns 14 when read with DeepSeek's own V3.2 model card PDF, which adds intended use and a parameter count, leaving languages and a knowledge cut-…); Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.)
- Risk, Devstral Small 2 +10: DeepSeek-V3.2 50 (File safety earns 15, safetensors only but 10 off because prompts are built by running DeepSeek's Python from the repository.); Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)
- Agent interface, Devstral Small 2 +5: DeepSeek-V3.2 60 (The chat template earns 10, as the format exists only as Python code to run.); 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.)