Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | — | 0.5B/1.5B/7B/57B/72B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 40k | 128k |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jun 10 2025 | Jun 6 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Magistral MediumvsClaude Haiku 5.5Qwen2vsClaude Haiku 5.5Magistral MediumvsGPT-6.1 SolQwen2vsGPT-6.1 SolMagistral MediumvsGemini 4 ArgonQwen2vsGemini 4 ArgonMagistral MediumvsMuse Spark OpenQwen2vsMuse Spark OpenMagistral MediumvsGrok 4.7Qwen2vsGrok 4.7Magistral MediumvsDeepSeek-V4.1-Flash-1017Qwen2vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Magistral Medium and Qwen2 don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Qwen2 shipped 369 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 40k (Magistral Medium) vs 128k (Qwen2). Magistral Medium is closed, while Qwen2 is open weight.
Direct benchmark comparisons are unavailable — Magistral Medium and Qwen2 don't publish scores on any of the same benchmarks.