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 | 48B |
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 | 1M |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | May 29 2024 | Oct 30 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5Kimi LinearvsClaude Haiku 5.5Codestral 22BvsGPT-6.1 SolKimi LinearvsGPT-6.1 SolCodestral 22BvsGemini 4 ArgonKimi LinearvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenKimi LinearvsMuse Spark OpenCodestral 22BvsGrok 4.7Kimi LinearvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017Kimi LinearvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and Kimi Linear don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 519 days before Kimi Linear, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while Kimi Linear has 48B. Context windows are 32k (Codestral 22B) vs 1M (Kimi Linear). Codestral 22B is closed, while Kimi Linear is open weight.
Direct benchmark comparisons are unavailable — Codestral 22B and Kimi Linear don't publish scores on any of the same benchmarks.