Side-by-side comparison of Codestral (Mistral AI) and Qwen 2.5 Coder 32B (Alibaba) — benchmarks, pricing, and capabilities.
| Codestral Mistral AI | Qwen 2.5 Coder 32B Alibaba | |
|---|---|---|
| Category | Code Models | Code Models |
| Specifications | ||
| Context Window | 32K | 128K |
| Pricing (per 1M tokens) | ||
| Input Cost | $0.20 | — |
| Output Cost | $0.60 | — |
| Performance | ||
| Overall Score | 86.2 | 88.0 |
| GSM8K | 84.0 | — |
| HumanEval | 92.5 | 92.7 |
| LiveCodeBench | — | 42.8 |
| MATH | 60.5 | — |
| MBPP | 88.0 | 90.2 |
| MMLU | 79.0 | — |
| SWE-bench Verified | — | 33.5 |
| Community | ||
| User Rating | ★ 4.6 | ★ 4.5 |
| Reviews | 289 | 175 |