# DeepSeek-V4-Flash-0731 vs Devstral Small 2 (slim)

> DeepSeek-V4-Flash-0731 and Devstral Small 2 score within a point of each other for open-weight models you run yourself, 61.9 and 61 out of 100. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.md (~10,450 tokens) · this version ~830 tokens · JSON https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-devstral-small-2.json · canonical https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-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)

DeepSeek-V4-Flash-0731 and Devstral Small 2 score within a point of each other on agent readiness, 61.9 (C) and 61 (C). Devstral Small 2 leads on reach, risk and documentation and upkeep. Both do open-weight models you run yourself.

- DeepSeek-V4-Flash-0731: C 61.9, rank #33 of 160 open-weight models · https://www.anchorterminal.com/tools/deepseek-v4-flash-0731.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-V4-Flash-0731, good for Agents or teams with a multi-GPU server, or a provider account, who want DeepSeek's V4 agent model under MIT with a 1M context Ahead on Agent interface, 75 against 65.
- 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 70; Risk, 60 against 50; Documentation and upkeep, 46 against 38.

| Category | DeepSeek-V4-Flash-0731 | Devstral Small 2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 70 | 90 |
| Risk (20%) | 50 | 60 |
| Agent interface (10%) | 75 | 65 |
| Documentation and upkeep (10%) | 38 | 46 |

| Fact (where they differ) | DeepSeek-V4-Flash-0731 | Devstral Small 2 |
| --- | --- | --- |
| Vendor | DeepSeek | Mistral AI |
| Licence | MIT | Apache-2.0 |
| Last release | 2026-07-31 | 2026-07-15 |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Reach, Devstral Small 2 +20: DeepSeek-V4-Flash-0731 70 (Memory 5, because the smallest build of 4-bit or better from a runtime's own library is LM Studio's MXFP4 GGUF at 156.4 GB, which with a fifth added needs 187.7…); 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.)
- Risk, Devstral Small 2 +10: DeepSeek-V4-Flash-0731 50 (File safety 15, safetensors only, less 10 because prompts are built by running DeepSeek's encoding_dsv4.py from the repository and the card's serving commands p…); Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)
- Agent interface, DeepSeek-V4-Flash-0731 +10: DeepSeek-V4-Flash-0731 75 (Chat template 10, there is no Jinja template and the format is given as Python 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.)
- Documentation and upkeep, Devstral Small 2 +8: DeepSeek-V4-Flash-0731 38 (Model card 8, the card and the DSpark card it names give architecture, parameters and context, with intended use, limitations, languages and cut-off missing.); Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.)