Mistral AI, open weights
Mistral Small 3.2
Mistral Small 3.2 by Mistral AI ranks 280th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.2. Its strongest category is writing & preference, where it ranks 224th. API pricing starts at $0.0938 per million input tokens and $0.25 per million output tokens, with a 256K-token context window.
Last verified
Specifications
- Noometry rank
- #280 of 354
- Index score
- 31.2
- Evidence
- Confirmed 6 results
- Provider
Mistral AI- Released
- June 20, 2025
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- 256K
- Max output
- 16K
- Input price
- $0.0938 / M
- Output price
- $0.25 / M
- Blended price
- $0.13 / M
- Output speed
- 68 tokens/s Kagi
- Value
- #36 of 219
- Knowledge cutoff
- Unknown
- Input
- image, text
- Hugging Face
- mistralai/Mistral-Small-3.2-24B-Instruct-2506
Category scores
Each category score combines every public result we have in that category.
- Reasoning 18.1
- Math 26.3
- Knowledge 26.7
- Writing & Preference 45.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Reasoning | 18.1 | #287 | 2 |
| Math | 26.3 | #260 | 1 |
| Knowledge | 26.7 | #256 | 1 |
| Writing & Preference | 45.0 | #224 | 1 |
Strengths and weaknesses
Categories where Mistral Small 3.2 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Writing & Preference | 45.0 | −8.8 | #224 of 312, top 72% |
| Math | 26.3 | −10.3 | #260 of 327, top 80% |
Closest competitors
The models ranked just above and below Mistral Small 3.2. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Phi 3 Mini 4k Instruct June 2024 | #276 | 31.3 | — | — | Compare |
| Gemma 1.1 7b IT | #277 | 31.3 | — | — | Compare |
| Mistral Small 3 | #278 | 31.2 | $0.0575 | — | Compare |
| Phi-4 | #279 | 31.2 | $0.0875 | — | Compare |
| Amazon Nova Pro | #281 | 31.0 | $1.40 | — | Compare |
| Llama 4 Maverick | #282 | 30.9 | $0.30 | 456 | Compare |
| Phi-4 Mini | #283 | 30.9 | $0.13 | — | Compare |
| Gemma 3 27B | #284 | 30.8 | $0.10 | 62 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 40.4% | #79 of 99, top 80% | Kagi LLM Benchmark | ||
| Chess Puzzles | 1% | #106 of 129, top 83% | Epoch AI | 2026-08-30 | |
| Epoch Capabilities Index | 131.74 | #134 of 213, top 63% | Epoch AI | 2025-06-20 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 30.3% | #120 of 173, top 70% | Epoch AI | 2026-08-30 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 49.1% | #130 of 186, top 70% | Epoch AI | 2026-08-28 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| EQ-Bench Creative Writing | 1255 | #84 of 115, top 74% | EQ-Bench |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.0938 | $0.25 | — | 2026-10-10 |
Compare Mistral Small 3.2
- Mistral Small 3.2 vs Mistral Small 3.1
- Mistral Small 3.2 vs Phi-4
- Mistral Small 3.2 vs Amazon Nova Pro
- Mistral Small 3.2 vs Mistral Small 3
- Mistral Small 3.2 vs Llama 4 Maverick
- Mistral Small 3.2 vs Gemma 1.1 7b IT
- Mistral Small 3.2 vs Phi-4 Mini
- Mistral Small 3.2 vs GPT-6 Astra
- Mistral Small 3.2 vs Claude Fable 5.1
- Mistral Small 3.2 vs Gemini 3.8 Flash
- Mistral Small 3.2 vs Kimi K3
- Mistral Small 3.2 vs Grok 4.6
- Mistral Small 3.2 vs Qwen3.8 Max
- Mistral Small 3.2 vs GLM-5.3
Other Mistral AI models
- Mistral Large 443.1
- Mistral Medium 3.540.2
- Mistral Large 339.1
- Mistral Medium36.3
- Magistral Medium35.2
- Devstral Small 250534.3
- Mistral Small33.4
- Pixtral Large32.2
Frequently asked questions
How good is Mistral Small 3.2?
Mistral Small 3.2 by Mistral AI ranks 280th of 354 ranked models on the Noometry Index as of October 2026, with a score of 31.2. Its strongest category is writing & preference, where it ranks 224th. API pricing starts at $0.0938 per million input tokens and $0.25 per million output tokens, with a 256K-token context window.
How much does Mistral Small 3.2 cost?
Mistral Small 3.2 costs $0.0938 per million input tokens and $0.25 per million output tokens on openrouter.
What is Mistral Small 3.2's context window?
Mistral Small 3.2 accepts up to 256K tokens of input and can write up to 16K tokens in one response.
Is Mistral Small 3.2 open source?
Yes. Mistral Small 3.2's weights are downloadable from Hugging Face (mistralai/Mistral-Small-3.2-24B-Instruct-2506); check the license for commercial terms.
How fast is Mistral Small 3.2?
Mistral Small 3.2 generated about 68 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Mistral Small 3.2's strengths and weaknesses?
Relative to other ranked models, Mistral Small 3.2 places best in writing & preference, math and lowest in reasoning, knowledge.
What is Mistral Small 3.2 best at?
Its best category is writing & preference, where it ranks 224th on Noometry.