Codestral 25.08 (EU) vs Qwen2.5 Coder 32B Instruct
Codestral 25.08 (EU) is cheaper on output tokens, while Codestral 25.08 (EU) offers a larger context window. Choose Codestral 25.08 (EU) or Qwen2.5 Coder 32B Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Codestral 25.08 (EU) | Qwen2.5 Coder 32B Instruct |
|---|---|---|
| Provider | Eden AI | — |
| Input / 1M tokens | $0.33 | $0.66 |
| Output / 1M tokens | $0.99 | $1.00 |
| Context window | 256K | 33K |
| Parameters | — | — |
| Open weights | No | — |
| Released | Jul 2025 | — |
| Aider Polyglot score | — | 16.4 |
| SWE-bench Verified score | — | 47.0 |
| LMArena (Chatbot Arena) Elo score | — | 1230 |
FAQ
Is Codestral 25.08 (EU) or Qwen2.5 Coder 32B Instruct cheaper?
Codestral 25.08 (EU) is cheaper on output tokens ($0.99 vs $1.00 per 1M).
Which has the larger context window, Codestral 25.08 (EU) or Qwen2.5 Coder 32B Instruct?
Codestral 25.08 (EU) has the larger context window (256K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.