Private AI
Magistral Small is a compact, high-performance language model optimized for efficient inference while maintaining strong capabilities across various tasks.
Added Sep 25, 2025
Context Window
32.8K
Max Output
32.8K
Input Price (Auto)
$0.40/1M
Output Price (Auto)
$1.40/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
10.7
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
64.1%
Better than 46% of models compared
HLE
Humanity's Last Exam
7.2%
Better than 55% of models compared
IFBench
Instruction-following benchmark
24.8%
Better than 7% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
26.6%
Better than 32% of models compared
AA-LCR
Long context reasoning evaluation
0.0%
Better than 7% of models compared
SciCode
Python programming for scientific computing
24.1%
Better than 30% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
4.5%
AIME 2025
American Invitational Mathematics Examination 2025
41.3%
Better than 43% of models compared
AIME
American Invitational Mathematics Examination
71.3%
Better than 81% of models compared
MMLU-Pro
Professional and academic subject knowledge
74.6%
Better than 47% of models compared
Last updated Jun 25, 2026
Artificial AnalysisBetter than 30% of models compared
LiveCodeBench
Contamination-free coding benchmark
51.4%
Better than 58% of models compared
Math-500
Diverse mathematical problem solving benchmark
96.3%
Better than 84% of models compared
