Mistral Small 3.2 vs Gemma 4 31B StyleTune
Mistral Small 3.2 is cheaper on output tokens, while Gemma 4 31B StyleTune offers a larger context window. Choose Mistral Small 3.2 or Gemma 4 31B StyleTune based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Mistral Small 3.2 | Gemma 4 31B StyleTune |
|---|---|---|
| Provider | Mistral | NanoGPT |
| Input / 1M tokens | $0.10 | $0.31 |
| Output / 1M tokens | $0.30 | $0.31 |
| Context window | 128K | 262K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Jun 2025 | May 2026 |
| LMArena (Chatbot Arena) Elo score | 1338 | — |
| GPQA Diamond score | 49.0 | — |
| LMArena Vision Elo score | 1142 | — |
FAQ
Is Mistral Small 3.2 or Gemma 4 31B StyleTune cheaper?
Mistral Small 3.2 is cheaper on output tokens ($0.30 vs $0.31 per 1M).
Which has the larger context window, Mistral Small 3.2 or Gemma 4 31B StyleTune?
Gemma 4 31B StyleTune has the larger context window (262K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.