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 | 16B |
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 |
| Overview | ||
| Company | Mistral | Moonshot AI |
| Release date | May 29 2024 | Apr 10 2025 |
| Access | Closed | Open Weight |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5Kimi-VLvsClaude Haiku 5.5Codestral 22BvsGPT-6.1 SolKimi-VLvsGPT-6.1 SolCodestral 22BvsGemini 4 ArgonKimi-VLvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenKimi-VLvsMuse Spark OpenCodestral 22BvsGrok 4.7Kimi-VLvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017Kimi-VLvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Codestral 22B and Kimi-VL don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 316 days before Kimi-VL, so benchmark comparisons should account for the intervening progress.
Codestral 22B has 22B parameters, while Kimi-VL has 16B. Context windows are 32k (Codestral 22B) vs 128k (Kimi-VL). Codestral 22B is closed, while Kimi-VL is open weight.
Direct benchmark comparisons are unavailable — Codestral 22B and Kimi-VL don't publish scores on any of the same benchmarks.