# Darwin-36B-Opus vs Devstral Small 2 (slim)

> Darwin-36B-Opus and Devstral Small 2 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/darwin-36b-opus-vs-devstral-small-2.md (~9,800 tokens) · this version ~730 tokens · JSON https://www.anchorterminal.com/compare/darwin-36b-opus-vs-devstral-small-2.json · canonical https://www.anchorterminal.com/compare/darwin-36b-opus-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)

Darwin-36B-Opus and Devstral Small 2 score within a point of each other on agent readiness, 61 (C) and 61 (C). Devstral Small 2 leads on reach and risk. Both do open-weight models you run yourself.

- Darwin-36B-Opus: C 61, rank #43 of 160 open-weight models · https://www.anchorterminal.com/tools/darwin-36b-opus.min.md
- Devstral Small 2: C 61, rank #60 of 160 open-weight models · https://www.anchorterminal.com/tools/devstral-small-2.min.md
- Darwin-36B-Opus, good for Reasoning-heavy text tasks on a 32 GB machine or a single 80 GB GPU, where a disclosed training method isn't required Ahead on Agent interface, 70 against 65; Documentation and upkeep, 61 against 46.
- 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 80; Risk, 60 against 55.

| Category | Darwin-36B-Opus | Devstral Small 2 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 80 | 90 |
| Risk (20%) | 55 | 60 |
| Agent interface (10%) | 70 | 65 |
| Documentation and upkeep (10%) | 61 | 46 |

| Fact (where they differ) | Darwin-36B-Opus | Devstral Small 2 |
| --- | --- | --- |
| Vendor | FINAL-Bench (VIDRAFT) | Mistral AI |
| Last release | 2026-04-23 | 2026-07-15 |
| Agent reviews | 2.5/5 (4) | none |

Why the edge:
- Documentation and upkeep, Darwin-36B-Opus +15: Darwin-36B-Opus 61 (Model card 11, it covers architecture, parameters, context and languages but not intended use, limitations or a knowledge cut-off.); Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.)
- Reach, Devstral Small 2 +10: Darwin-36B-Opus 80 (Memory 20, the publisher's Q4_K_M GGUF is 21.2 GB and needs about 25.4 GB with the fifth added, so 32 GB.); 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 +5: Darwin-36B-Opus 55 (File safety 25, safetensors and GGUF only with no code in the repository, so the card's trust_remote_code flag loads nothing extra.); Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.)
- Agent interface, Darwin-36B-Opus +5: Darwin-36B-Opus 70 (Chat template 20, Qwen3.6's Jinja template in the repository.); 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.)