Compare / Magistral Small 1.2 vs Mistral Small 3.2
Magistral Small 1.2 vs Mistral Small 3.2
Updated November 2026
Verdict
Magistral Small 1.2 scores higher on the Small LM Index: 55.9 vs 38.6. On the 1 benchmark both labs report, Magistral Small 1.2 wins 1 and Mistral Small 3.2 wins 0. Both need about 16.9 GB of memory at 4-bit quantization. Only Mistral Small 3.2 has a hosted API on OpenRouter ($0.11 per million tokens); the other has to be self-hosted.
Pick Magistral Small 1.2 if…
- you want the strongest model overall
Pick Mistral Small 3.2 if…
- you want a hosted API rather than running it yourself
- you want the more widely used model (more quantized builds and community support)
Specifications
| Magistral Small 1.2 | Mistral Small 3.2 | |
|---|---|---|
| Small LM Index | 55.9 (likely 51–60) | 38.6 (likely 29–49) |
| Lab | Mistral AI · Europe | Mistral AI · Europe |
| Released | 2025-09-17 | 2025-06-20 |
| Parameters | 24B (dense) | 24B (dense) |
| Memory at 4-bit | ~16.9 GB | ~16.9 GB |
| Context window | 128K tokens | 128K tokens |
| Input | text, image | text, image |
| Reasoning | Always thinks | No thinking |
| License | Apache-2.0 | Apache-2.0 |
| API price / 1M tokens | Self-host only | $0.11 ($0.075 in, $0.20 out) |
| Hugging Face downloads (30 days) | 29.7K | 118.9K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | Magistral Small 1.2 | Mistral Small 3.2 |
|---|---|---|
| MMLU-Pro Knowledge | ≈ 76 | 69.1 |
| GPQA Diamond Knowledge | 70.1 | 46.1 |
| AIME Math | 77.3 | ≈ 50 |
| LiveCodeBench Coding | 70.9 | ≈ 43 |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, Magistral Small 1.2 or Mistral Small 3.2?
Magistral Small 1.2 scores higher on the Small LM Index: 55.9 vs 38.6. On the 1 benchmark both labs report, Magistral Small 1.2 wins 1 and Mistral Small 3.2 wins 0.
Which is cheaper to run?
Only Mistral Small 3.2 has a hosted API on OpenRouter ($0.11 per million tokens); the other has to be self-hosted. Both need about 16.9 GB of memory at 4-bit quantization.
Which has the longer context window?
Both have a 128K-token context window.
Can I use Magistral Small 1.2 and Mistral Small 3.2 commercially?
Both are released under the Apache-2.0 license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.
Related comparisons
- Gemma 4 26B-A4B vs Magistral Small 1.2
- gpt-oss-20b vs Magistral Small 1.2
- LFM2.5 24B-A2B vs Magistral Small 1.2
- EuroLLM 22B Instruct vs Magistral Small 1.2
- Magistral Small 1.2 vs Tri-21B Think
- Gemma 4 26B-A4B vs Mistral Small 3.2
- LFM2.5 24B-A2B vs Mistral Small 3.2
- EuroLLM 22B Instruct vs Mistral Small 3.2