Model comparison
DeepSeek-V3.2-Speciale vs Magistral Small
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 29.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
Mistral AISummary
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 6.9.
- Magistral Small is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.
Side by side
| DeepSeek-V3.2-Speciale | Magistral Small | |
|---|---|---|
| Provider | DeepSeek | Mistral AI |
| Noometry Index | 39.1 | 29.9 |
| Released | 2025-12-01 | 2025-06-10 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 128K | 40K |
| Input $ / M tokens | $0.58 | $0.50 |
| Output $ / M tokens | $1.68 | $1.50 |
| Results tracked | 3 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 39.9 (#136), Magistral Small: 37.8 (#172)
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Magistral Small: 6.9 (#345)
| Benchmark | DeepSeek-V3.2-Speciale | Magistral Small |
|---|---|---|
| ARC-AGI-2 | — | 0% |
| SimpleBench | 52.6% | — |
| Kagi LLM Benchmark | — | 6.3% |
| ARC-AGI-1 | — | 5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 3% |
| DTBench | — | 61.3% |
| Epoch Capabilities Index | — | 133.19 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Magistral Small: 24.9 (#253)
| Benchmark | DeepSeek-V3.2-Speciale | Magistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 30% |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Magistral Small: 30.9 (#215)
| Benchmark | DeepSeek-V3.2-Speciale | Magistral Small |
|---|---|---|
| GPQA Diamond | — | 56.1% |
Writing & Preference Not comparable
DeepSeek-V3.2-Speciale: 46.1 (#217), Magistral Small: —
| Benchmark | DeepSeek-V3.2-Speciale | Magistral Small |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | — |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Magistral Small?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 29.9 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Speciale or Magistral Small?
Magistral Small is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.
Is DeepSeek-V3.2-Speciale or Magistral Small better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 37.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do DeepSeek-V3.2-Speciale and Magistral Small share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Magistral Small has 10.