Browse all Mistral text models
Provider logo

Devstral 2 123B

mistralai/devstral-2-123b-instruct-2512
Provider logo

Devstral 2 123B

mistralai/devstral-2-123b-instruct-2512

Devstral 2 123B is a 123 billion parameter model from Mistral AI optimized for coding and development tasks. Features advanced reasoning capabilities for software engineering workflows.

Added Dec 9, 2025

Model weights

Context Window

262.1K

Max Output

65.5K

Avg output tokens (7d)

495 tokens

44%

Input Price (Auto)

$0.40/1M

Output Price (Auto)

$1.40/1M

Cache Read (Auto)

$0.20/1M

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

9.4

Better than 40% of models compared

Coding Index

31.3

Better than 39% of models compared

Agentic Index

4.9

Better than 33% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

3.1%

Better than 28% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

483 Elo

Better than 26% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

689 Elo

Better than 32% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

2.4%

Better than 20% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

32.3%

Better than 34% of models compared

Reasoning

HLE

Humanity's Last Exam

3.6%

Better than 7% of models compared

IFBench

Instruction-following benchmark

38.1%

Better than 34% of models compared

CritPt

Research-level physics reasoning

0.0%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

0.0%

Better than 17% of models compared

SciCode

Python programming for scientific computing

32.8%

Better than 13% of models compared

LiveCodeBench

Contamination-free coding benchmark

44.8%

Better than 51% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

36.7%

Better than 37% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

76.2%

Better than 53% of models compared

AA-Omniscience Accuracy

Proportion of correctly answered questions

20.8%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

85.3%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

59.4%

Better than 34% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

18.9%

Better than 59% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

24.9%

Better than 28% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

32.3%

Better than 34% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

9.4%

Last updated Sep 13, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Devstral 2 123B with similar models from the same provider or model family.