Devstral Small (May '25)
Released · 14 days after Mistral Medium 3
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Global rank#361 of 597 LLMs
TierEfficient
Intelligence Index11.8
Reasoning & knowledge
MMLU-Pro
63%
GPQA Diamond
43%
Humanity's Last Exam
4%
Long-context reasoning
30%
Coding
LiveCodeBench
26%
SciCode
25%
Agentic & tool use
Terminal-Bench Hard
6%
τ²-Bench Telecom
38%
Math & instruction following
IFBench
32%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Devstral Small (May '25) isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →