Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications.
Context Window
32.0K
Max Output
32.8K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$0.59/1M
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
12.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
42.4%
Better than 24% of models compared
HLE
Humanity's Last Exam
4.1%
Better than 18% of models compared
SciCode
Python programming for scientific computing
24.1%
Better than 35% of models compared
AIME
American Invitational Mathematics Examination
13.0%
Better than 39% of models compared
Math-500
Diverse mathematical problem solving benchmark
67.7%
Better than 25% of models compared
MMLU-Pro
Professional and academic subject knowledge
61.1%
Better than 23% of models compared
Last updated May 15, 2026
Artificial Analysis
