Devstral 2
Released
Benchmarks
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Intelligence Index9.4
Coding Index31.3
Math Index36.7
Reasoning & knowledge
MMLU-Pro
76%
GPQA Diamond
59%
Humanity's Last Exam
4%
Long-context reasoning
32%
Coding
LiveCodeBench
45%
SciCode
33%
Agentic & tool use
Terminal-Bench Hard
19%
τ²-Bench Telecom
25%
Math & instruction following
AIME 2025
37%
IFBench
38%
See full leaderboard →Benchmarks via Artificial Analysis · View on AA
Available routes
No routes currently available — Devstral 2 isn't routed through the Opper gateway right now. It's tracked here for its release history.
Contact us about this model →