Mistral Small 3.2vsQwen2.5-Coder
Mistral Small 3.2 | Qwen2.5-Coder | |
|---|---|---|
| Specifications | ||
ParametersA rough measure of how big the model is. More parameters usually means more capable and more expensive to run, though it is a poor guide on its own — a smaller, newer model often beats a larger, older one. | 24B | 32B |
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| API pricingUSD per 1M tokens · lower wins | ||
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.075DeepInfra | $0.66Cloudflare |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | $0.20DeepInfra | $1.00Cloudflare |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jun 20 2025 | Nov 12 2024 |
| Access | Open Weight | Open Weight |
Other comparisons
Mistral Small 3.2vsClaude Fable 5.1Qwen2.5-CodervsClaude Fable 5.1Mistral Small 3.2vsGPT-6 AstraQwen2.5-CodervsGPT-6 AstraMistral Small 3.2vsGemini 3.8 FlashQwen2.5-CodervsGemini 3.8 FlashMistral Small 3.2vsMuse Spark 1.3Qwen2.5-CodervsMuse Spark 1.3Mistral Small 3.2vsGrok 4.6Qwen2.5-CodervsGrok 4.6Mistral Small 3.2vsDeepSeek-V4.1-FlashQwen2.5-CodervsDeepSeek-V4.1-Flash
Frequently asked questions
Mistral Small 3.2 and Qwen2.5-Coder don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2.5-Coder shipped 220 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.
Mistral Small 3.2 has 24B parameters, while Qwen2.5-Coder has 32B.
Direct benchmark comparisons are unavailable — Mistral Small 3.2 and Qwen2.5-Coder don't publish scores on any of the same benchmarks.