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 | 32k |
| Overview | ||
| Company | Mistral | Qwen |
| Release date | Jul 16 2024 | Jan 28 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Codestral Mamba 7BvsClaude Haiku 5.5Qwen2.5-MaxvsClaude Haiku 5.5Codestral Mamba 7BvsGPT-6.1 SolQwen2.5-MaxvsGPT-6.1 SolCodestral Mamba 7BvsGemini 4 ArgonQwen2.5-MaxvsGemini 4 ArgonCodestral Mamba 7BvsMuse Spark OpenQwen2.5-MaxvsMuse Spark OpenCodestral Mamba 7BvsGrok 4.7Qwen2.5-MaxvsGrok 4.7Codestral Mamba 7BvsDeepSeek-V4.1-Flash-1017Qwen2.5-MaxvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral Mamba 7B and Qwen2.5-Max don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral Mamba 7B shipped 196 days before Qwen2.5-Max, so benchmark comparisons should account for the intervening progress.
Context windows are 256k (Codestral Mamba 7B) vs 32k (Qwen2.5-Max). Codestral Mamba 7B is open weight, while Qwen2.5-Max is closed.
Direct benchmark comparisons are unavailable — Codestral Mamba 7B and Qwen2.5-Max don't publish scores on any of the same benchmarks.