Devstral Small 2
Released · 7 days after Ministral 3 14B
Benchmarks
Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.
Global rank#351 of 511 LLMs
TierEfficient
Intelligence Index (previous version)7.5
Agentic1.6
Coding
Terminal-Bench 4.0
0%
SciCode
32%
LiveCodeBench
35%
Agentic & knowledge work
AutomationBench
3%
GDPval
2%
GDP.pdf
1%
Briefcase (Elo)496
Terminal-Bench Hard
17%
τ²-Bench Telecom
23%
Science & reasoning
Humanity's Last Exam
4%
GPQA Diamond
53%
Long-context reasoning
28%
Knowledge
MMMU-Pro
45%
MMLU-Pro
68%
Math & instruction following
AIME 2025
34%
IFBench
31%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Devstral Small 2 isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →