Mistral Small 3.1 vs Llama 3.2 3B Instruct
Mistral Small 3.1 is cheaper on output tokens, while Llama 3.2 3B Instruct offers a larger context window. Choose Mistral Small 3.1 or Llama 3.2 3B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Mistral Small 3.1 | Llama 3.2 3B Instruct |
|---|---|---|
| Provider | Azure | Meta |
| Input / 1M tokens | $0.10 | $0.05 |
| Output / 1M tokens | $0.30 | $0.33 |
| Context window | 128K | 131K |
| Parameters | — | — |
| Open weights | No | — |
| Released | Mar 2025 | — |
| GPQA Diamond score | 41.9 | — |
| Epoch Capabilities Index score | 127 | — |
| LMArena (Chatbot Arena) Elo score | — | 1109 |
FAQ
Is Mistral Small 3.1 or Llama 3.2 3B Instruct cheaper?
Mistral Small 3.1 is cheaper on output tokens ($0.30 vs $0.33 per 1M).
Which has the larger context window, Mistral Small 3.1 or Llama 3.2 3B Instruct?
Llama 3.2 3B Instruct has the larger context window (131K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.