Devstral 2
Released
Benchmarks
Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.
Global rank#307 of 511 LLMs
TierEfficient
Intelligence Index (previous version)8.6
Agentic1.6
Coding
Terminal-Bench 4.0
0%
SciCode
33%
LiveCodeBench
45%
Agentic & knowledge work
AutomationBench
3%
GDPval
3%
GDP.pdf
2%
Briefcase (Elo)483
Terminal-Bench Hard
19%
τ²-Bench Telecom
25%
Science & reasoning
Humanity's Last Exam
4%
GPQA Diamond
59%
Long-context reasoning
32%
Knowledge
MMLU-Pro
76%
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 →