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. | 22B | 32B |
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. | 32k | 128k |
| These models have no shared benchmark scores. | ||
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | — | 63.4% |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | May 29 2024 | Mar 6 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5QwQ-32BvsClaude Haiku 5.5Codestral 22BvsGPT-6.1 SolQwQ-32BvsGPT-6.1 SolCodestral 22BvsGemini 4 ArgonQwQ-32BvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenQwQ-32BvsMuse Spark OpenCodestral 22BvsGrok 4.7QwQ-32BvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017QwQ-32BvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and QwQ-32B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 281 days before QwQ-32B, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while QwQ-32B has 32B. Context windows are 32k (Codestral 22B) vs 128k (QwQ-32B). Codestral 22B is closed, while QwQ-32B is open weight.
Direct benchmark comparisons are unavailable — Codestral 22B and QwQ-32B don't publish scores on any of the same benchmarks.