Model comparison
Mistral Small 3.1 vs Mistral Small 3
- Input
- $0.351 / 1M tokens
- Output
- $0.555 / 1M tokens
- Context
- 128K
- Released
- 2025-03-17
- Input
- $0.10 / 1M tokens
- Output
- $0.30 / 1M tokens
- Context
- 32k tokens
- Released
- 2025-01-30
Mistral Small 3.1 and Mistral Small 3 split the 4 benchmarks both report evenly; Mistral Small 3 is cheaper on input tokens ($0.1 vs $0.4 per 1M, 3.5×); Mistral Small 3.1 has the larger context window (128K vs 32K).
Specs and pricing side by side
| Spec | Mistral Small 3.1 | Mistral Small 3 |
|---|---|---|
| Maker | Mistral AI | Mistral AIsame |
| Released | 2025-03-17 | 2025-01-30 |
| Context window | 128K | 32k tokens |
| Max output | not published | Not separately published by Mistral; bounded… |
| Input price | $0.351 / 1M tokens | $0.10 / 1M tokens |
| Output price | $0.555 / 1M tokens | $0.30 / 1M tokens |
| Parameters | 24B | 24Bsame |
| License | Apache 2.0 | Apache-2.0 |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision | Text |
| Knowledge cutoff | October 2023 | October 2023same |
Benchmarks both models report
| Benchmark | Mistral Small 3.1 | Mistral Small 3 |
|---|---|---|
| MMLU | 80.62% | 81% |
| MMLU Pro | 66.76% | 66.3% |
| MATH | 69.3% | 70.6% |
| HumanEval | 88.41% | 84.8% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Mistral Small 3.1 if…
- You care about MMLU Pro, HumanEval (it scores higher on 2 shared benchmarks).
- You need the longer context (128K vs 32K).
- You need Vision input, which Mistral Small 3 lacks.
- Your use case is: self-hosted multimodal assistants that need to read images, documents, and charts.
Pick Mistral Small 3 if…
- You care about MMLU, MATH (it scores higher on 2 shared benchmarks).
- Cost matters: input tokens cost 3.5× less ($0.1 vs $0.4 per 1M).
- Your use case is: fast-response conversational assistants and chatbots.
FAQ
Which is better, Mistral Small 3.1 or Mistral Small 3?
Mistral Small 3.1 and Mistral Small 3 split the 4 benchmarks both report evenly; Mistral Small 3 is cheaper on input tokens ($0.1 vs $0.4 per 1M, 3.5×); Mistral Small 3.1 has the larger context window (128K vs 32K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Mistral Small 3?
Mistral Small 3.1: $0.351 / 1M tokens input, $0.555 / 1M tokens output. Mistral Small 3: $0.10 / 1M tokens input, $0.30 / 1M tokens output (list API prices as published by each maker).
What are the context windows of Mistral Small 3.1 and Mistral Small 3?
Mistral Small 3.1 offers 128K; Mistral Small 3 offers 32k tokens with up to Not separately published by Mistral; bounded by the 32k context window output.
Is Mistral Small 3.1 newer than Mistral Small 3?
Mistral Small 3.1 was released 2025-03-17; Mistral Small 3 was released 2025-01-30.
Go deeper
- Mistral Small 3.1: full specs, pricing and benchmarks
- Mistral Small 3: full specs, pricing and benchmarks
- mistral small 3 2 vs mistral small 3 1
- mistral small 3 1 vs llama 3 3
- mistral small 3 vs mistral small 2 409
- mistral small 3 vs llama 3 3
- mistral small 3 vs llama 3 1
- mistral small 3 1 vs qwen2 5 vl
- All model comparisons