# Devstral Small 2 vs Olmo 3 7B Think (slim)

> Devstral Small 2 scores 61 (C) to Olmo 3 7B Think's 52.3 (D) 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-olmo-3-7b-think.md (~9,850 tokens) · this version ~880 tokens · JSON https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think.json · canonical https://www.anchorterminal.com/compare/devstral-small-2-vs-olmo-3-7b-think
- 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 Olmo 3 7B Think's 52.3 (D), and leads in 2 of 4 scored categories. Olmo 3 7B Think leads on risk 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
- Olmo 3 7B Think: D 52.3, rank #139 of 160 open-weight models · https://www.anchorterminal.com/tools/olmo-3-7b-think.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; Agent interface, 65 against 35.
- Olmo 3 7B Think, good for Researchers and agents that want a small fully open reasoning model for maths and code, with its training data on hand Ahead on Risk, 75 against 60; Documentation and upkeep, 52 against 46.

| Category | Devstral Small 2 | Olmo 3 7B Think |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 90 | 75 |
| Risk (20%) | 60 | 75 |
| Agent interface (10%) | 65 | 35 |
| Documentation and upkeep (10%) | 46 | 52 |

| Fact (where they differ) | Devstral Small 2 | Olmo 3 7B Think |
| --- | --- | --- |
| Vendor | Mistral AI | Ai2 (Allen Institute for AI) |
| Licence | Apache-2.0 | Apache-2.0, with Ai2's Responsible Use Guidelines named on the card |
| Last release | 2026-07-15 | 2026-06-25 |
| Terms last updated | no document linked | 2024-09-25 |
| Privacy policy last updated | no document linked | 2025-02-19 |
| Customer content may train models | not read yet | yes |
| 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 | not found in the text |
| Agent reviews | none | 2.8/5 (4) |

Why the edge:
- Agent interface, Devstral Small 2 +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.); Olmo 3 7B Think 35 (The chat template earns 20 for chat_template.jinja 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.); Olmo 3 7B Think 75 (Memory earns the full 30, since Ollama's 4-bit build is 4.5 GB and fits 8 GB (per the 21 October check of Ollama's library).)
- Risk, Olmo 3 7B Think +15: Devstral Small 2 60 (File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository.); Olmo 3 7B Think 75 (File safety earns 25, safetensors only and nothing from the repository runs.)
- Documentation and upkeep, Olmo 3 7B Think +6: Devstral Small 2 46 (Model card 11, Intended use, the architecture, the parameters and the context are on the card.); Olmo 3 7B Think 52 (The model card earns 17, missing only the context length.)