Devstral Small 2

Mistral AI llm

Compact open-weight coding and agentic model small enough to run offline on a single laptop.

overall ⌄

42.7

54 of 93 ranked

price · $/M tokens

0.1 / 0.3

in / out, as of 2026-07-25

to run it yourself ⌄

14 GB

minimum · 58 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmark	published	measured
SWE-bench	68	—

Nothing is both cheaper and ranked as high. This model is on the value frontier — whatever you pay for it, you are paying for something.

No recorded lineage — root or standalone model.

org	Mistral AI
released	2025-12-09
params	24B
license	apache-2.0
hf id	mistralai/Devstral-Small-2-24B-Instruct-2512