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. | — | 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. | 256k | 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. | 86.6% | 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. | 37.9% | — |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jan 13 2025 | Apr 16 2024 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 25.01vsClaude Fable 5.2CodeQwen1.5vsClaude Fable 5.2Codestral 25.01vsGPT-6.2 AstraCodeQwen1.5vsGPT-6.2 AstraCodestral 25.01vsGemini 4 NeonCodeQwen1.5vsGemini 4 NeonCodestral 25.01vsMuse EmberCodeQwen1.5vsMuse EmberCodestral 25.01vsGrok 4.7CodeQwen1.5vsGrok 4.7Codestral 25.01vsDeepSeek-V4.1-Flash-1017CodeQwen1.5vsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 25.01 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 272 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Codestral 25.01) vs 64k (CodeQwen1.5). Codestral 25.01 is closed, while CodeQwen1.5 is open weight.
On HumanEval, Codestral 25.01 leads at 86.6% vs CodeQwen1.5 at 83.5%.