Devstral 2

Mistral AI llm

Mistral's flagship open-weight agentic coding model, released alongside the Mistral Vibe CLI.

overall ⌄

48.1

58 of 125 ranked

price · $/M tokens

0.4 / 2

in / out, as of 2026-07-25

to run it yourself ⌄

74 GB

minimum · 295 GB recommended

Benchmarks

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

benchmarkpublishedmeasured
SWE-bench72.2 —

Cheaper, and at least as good

On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.

DeepSeek V4-Flash DeepSeek$0.00042overall 57.9
Claude Haiku 5.5 Anthropic$0.00060overall 65.3
Qwen3.8-Flash-Next Alibaba$0.00062overall 61.2
DeepSeek V4-Pro DeepSeek$0.00130overall 65.6
DeepSeek-V4.1-Flash DeepSeek$0.00150overall 59.2

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

orgMistral AI
released2025-12-09
params123B
licensemodified-mit
hf idmistralai/Devstral-2-123B-Instruct-2512