Mistral
Saba
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. Read more at the blog post [here](https://mistral.ai/en/news/mistral-saba)
- Input / 1M tokens
- $0.200
- Output / 1M tokens
- $0.600
- Context window
- 33K tokens
- Provider
- Mistral
- Cached input / 1M
- $0.020
- Knowledge cutoff
- 2024-09-30
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 0 t/s
- Time to first token
- 0.00s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 12
- Coding Index
- —
- Math Index
- —
- MMLU-Pro
- 61.1%
- GPQA
- 42.4%
- HLE
- 4.1%
- LiveCodeBench
- —
- SciCode
- 24.1%
- MATH-500
- 67.7%
- AIME
- 13.0%
Benchmarks via Artificial Analysis