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 | 7B |
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 | 64k |
| Benchmarks | ||
HumanEvalFunction synthesis — 164 small Python problems: the AI is given a function's description and has to write the working function. This was the coding benchmark of the GPT-3.5 and GPT-4 era, before the field moved to fixing real bugs in real repositories. Higher is better. | 81.1% | 83.5% |
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. | 31.5% | — |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | May 29 2024 | Apr 16 2024 |
| Access | Open Weight | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2Codestral 22BvsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraCodestral 22BvsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonCodestral 22BvsMuse EmberCodeQwen1.5vsMuse EmberCodestral 22BvsGrok 4.7CodeQwen1.5vsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017CodeQwen1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
CodeQwen1.5 leads Codestral 22B on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 43 days before Codestral 22B, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while CodeQwen1.5 has 7B. Context windows are 32k (Codestral 22B) vs 64k (CodeQwen1.5).
On HumanEval, CodeQwen1.5 leads at 83.5% vs Codestral 22B at 81.1%.