Mistral Small 3.2
Intelligence
15.1
#336/523
Coding
13.3
#294/429
Math
27
#192/265
Speed
197 tok/s
TTFT: 294.00s
Pricing
$0.10 / $0.30
per 1M tokens (in/out)
Mistral Small 3.2 is Mistral’s offering for efficient processing of natural language tasks. It operates at a speed of 197.344 tokens per second and is priced at $0.1 per million input tokens, targeting professional users.
When to Use Mistral Small 3.2
✓ Best For
- Natural language processing tasks
- Coding assistance
- Mathematical problem solving
✗ Not Ideal For
- High-speed real-time applications
- Tasks requiring extensive contextual understanding
How Mistral Small 3.2 Compares
Intelligence Index · Higher is better
AlibabaMistralZ AINVIDIA
Benchmark Profile
Coding Index
LG AI ResearchUpstageMistralAlibaba
Output Speed · tok/s
GoogleCohereMistralInclusionAIOpenAI
Math Index
AlibabaOpenAIMistralNVIDIAZ AI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (15)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 15.1 | |
| Coding Index | 13.3 | |
| Math Index | 27 | |
| MMLU-Pro | 681% | |
| GPQA | 505% | |
| LiveCodeBench | 275% | |
| HLE | 43% | |
| SciCode | 26.4% | |
| IFBench | 33.5% | |
| LCR | 17.3% | |
| TerminalBench Hard | 6.8% | |
| Tau2 | 29.5% | |
| AIME | 32.3% | |
| AIME 2025 | 27% | |
| MATH 500 | 88.3% |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was Mistral Small 3.2 released?
Mistral Small 3.2 was released on June 20, 2025.
Who created Mistral Small 3.2?
Mistral Small 3.2 was created by Mistral.
How intelligent is Mistral Small 3.2?
Mistral Small 3.2 scores 15 on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 12).
How fast is Mistral Small 3.2?
Mistral Small 3.2 generates output at 155.2 tokens per second (based on Mistral's API), which is well above average compared to other open weight non-reasoning models of similar size (median: 97.8 t/s).
What is the latency of Mistral Small 3.2?
Mistral Small 3.2 has a time to first token (TTFT) of 0.57s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.58s).
How much does Mistral Small 3.2 cost?
Mistral Small 3.2 costs $0.10 per 1M input tokens (better than average, median: $0.15) and $0.30 per 1M output tokens (better than average, median: $0.30), based on Mistral's API.
What is Mistral Small 3.2 API pricing?
Mistral Small 3.2 costs $0.10 per 1M input tokens and $0.30 per 1M output tokens (based on Mistral's API). For a blended rate (3:1 input to output ratio), this is $0.15 per 1M tokens. Pricing may vary by provider.
How verbose is Mistral Small 3.2?
When evaluated on the Intelligence Index, Mistral Small 3.2 generated 4.5M output tokens, which is better than average compared to other open weight non-reasoning models of similar size (median: 5.3M).
Is Mistral Small 3.2 a reasoning model?
No, Mistral Small 3.2 is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Mistral Small 3.2 support?
Mistral Small 3.2 supports text and image input.
What output modalities does Mistral Small 3.2 support?
Mistral Small 3.2 supports text output.
Can Mistral Small 3.2 process images?
Yes, Mistral Small 3.2 supports image input and can analyze, describe, and answer questions about images.
Is Mistral Small 3.2 multimodal?
Yes, Mistral Small 3.2 is multimodal. It can process text and image input and generate text output.
What is the context window of Mistral Small 3.2?
Mistral Small 3.2 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Mistral Small 3.2 open source?
Yes, Mistral Small 3.2 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
