This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Mistral has launched a newer release, Mistral Small 3.2. We suggest considering it instead.
Mistral Saba Intelligence, Performance & Price Analysis
Model summary
Speed
Verbosity
Mistral Saba is below average in intelligence when comparing to other non-reasoning models. The model supports text input, outputs text, and has a 32k tokens context window.
Mistral Saba scores 6 on the Artificial Analysis Intelligence Index, placing it below average among comparable models (median: 7).
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 32k ~48 A4 pages of size 12 Arial font |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Speed
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Evaluations
Agentic knowledge work, (Elo-500)/2000
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, (Elo-500)/2000
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Intelligence Index Comparisons
Intelligence Index vs. Cost per Task
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Frequently Asked Questions
Common questions about Mistral Saba
Mistral Saba was released on February 17, 2025.
Mistral Saba was created by Mistral.
Mistral Saba scores 6 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other non-reasoning models (median: 7).
No, Mistral Saba is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Mistral Saba supports text input.
Mistral Saba supports text output.
No, Mistral Saba does not support image input. It can only process text.
No, Mistral Saba is not multimodal. It only supports text input.
Mistral Saba has a context window of 32k tokens. This determines how much text and conversation history the model can process in a single request.
No, Mistral Saba is proprietary. The model weights are not publicly available.
Mistral Saba has 24 billion parameters.
Mistral Saba achieves a score of 6 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Check the providers page for current API availability. View providers
Visit the providers page to see availability. Compare providers