Devstral Medium
Released · 20 days after Mistral Small 3.2 24B Instruct
Benchmarks
Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.
Global rank#292 of 511 LLMs
TierEfficient
Intelligence Index (previous version)9.0
Coding
LiveCodeBench
34%
Agentic & knowledge work
Terminal-Bench Hard
9%
τ²-Bench Telecom
20%
Science & reasoning
Humanity's Last Exam
4%
GPQA Diamond
49%
Long-context reasoning
32%
Knowledge
MMLU-Pro
71%
Math & instruction following
AIME 2025
5%
IFBench
30%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Devstral Medium isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →