Mistral: Saba Rank
Saba has an overall score of 51 out of 100, tied for rank 265 of 291. The published scores are price 76, context 27, parameters 35, and freshness 64. The overall score is their average. recency is not published and is left out of the average.
Data sourced from OpenRouter API and manual data collection | Last updated: Nov 3, 2026, 8:01 AM UTC
Component scores are ranked in
tied for rank 265 of 291
Component scores
| Score | Result | Published value | Source |
|---|---|---|---|
| Freshness | 64 | AI Knowledge Cutoff | |
| Recency | — | — | AI Release Date |
| Context | 27 | 32.8K tokens, output 26.2K | AI Context Window |
| Parameters | 35 | 24B total | AI Parameter Count |
| Price | 76 | $0.3 / 1M blended, $0.2 / 1M input, $0.6 / 1M output | AI Token Price |
264 listed models have a higher overall score. Among Mistral models, it ranks 15 of 20.
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...
Higher overall scores
Other Mistral models
🤖 Generate website with AI 👆
Join the beta waitlist and get 50% off your first 3 months.
Frequently asked questions
What is the Saba rank?
Saba has an overall score of 51 out of 100, tied for rank 265 of 291. The published scores are price 76, context 27, parameters 35, and freshness 64. The overall score is their average. recency is not published and is left out of the average.
Where does Saba rank?
Saba is tied for rank 265 of 291. 264 listed models have a higher overall score. Among Mistral models, it ranks 15 of 20.
What scores make up Saba?
Saba scores price 76 (AI Token Price), context 27 (AI Context Window), parameters 35 (AI Parameter Count), and freshness 64 (AI Knowledge Cutoff). The overall score of 51 is the average of those 4.