Mistral AI
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
Running this yourself: can likely run on your own machine.
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding.
39.2
Quality Score
---
Arena ELO
123B
Parameters
262K
Context
Use this section to answer one simple question first: how much outside evidence do we have that this model performs well? Structured benchmark scores appear first, then official provider evidence, then live arena signal.
This model has normalized benchmark rows, so scores here are directly comparable across benchmark sources.
Sign in to join the discussion
0
Downloads
0
Likes
Dec 2025
Released
These are recent benchmark or leaderboard claims from official provider sources. They are useful for freshness and context, but they are not treated the same as normalized independent benchmark rows.
devstral-2512 - SWE-Bench Verified
SWE-Bench Verified resolved rate 53.8
View sourceDevstral 2 Benchmark Update
Quality: 22/100 | Price: $0/M tokens | Output: 74.091 tok/s | MMLU: 0.762% | HumanEval: 0.448%
View source