Qwen2.5 72B Instruct vs Magistral Medium (latest)
Magistral Medium (latest) is cheaper on output tokens, while Magistral Medium (latest) offers a larger context window. Choose Qwen2.5 72B Instruct or Magistral Medium (latest) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen2.5 72B Instruct | Magistral Medium (latest) |
|---|---|---|
| Provider | Alibaba | Mistral |
| Input / 1M tokens | $1.40 | $2.00 |
| Output / 1M tokens | $5.60 | $5.00 |
| Context window | 131K | 262K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Sep 2024 | Mar 2025 |
| GPQA Diamond score | 49.1 | — |
| LMArena (Chatbot Arena) Elo score | 1269 | 1255 |
FAQ
Is Qwen2.5 72B Instruct or Magistral Medium (latest) cheaper?
Magistral Medium (latest) is cheaper on output tokens ($5.00 vs $5.60 per 1M).
Which has the larger context window, Qwen2.5 72B Instruct or Magistral Medium (latest)?
Magistral Medium (latest) 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.