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/13B/33B/65B | 22B |
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. | 2k | 32k |
| Overview | ||
| Company | Meta | Mistral |
| Release date | Feb 24 2023 | May 29 2024 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
LLaMA 1vsClaude Haiku 5.5Codestral 22BvsClaude Haiku 5.5LLaMA 1vsGPT-6.1 SolCodestral 22BvsGPT-6.1 SolLLaMA 1vsGemini 4 ArgonCodestral 22BvsGemini 4 ArgonLLaMA 1vsGrok 4.7Codestral 22BvsGrok 4.7LLaMA 1vsDeepSeek-V4.1-Flash-1017Codestral 22BvsDeepSeek-V4.1-Flash-1017LLaMA 1vsKimi K3Codestral 22BvsKimi K3Frequently asked questions
LLaMA 1 and Codestral 22B don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. LLaMA 1 shipped 460 days before Codestral 22B, so benchmark comparisons should account for the intervening progress.
LLaMA 1 has 7B/13B/33B/65B parameters, while Codestral 22B has 22B. Context windows are 2k (LLaMA 1) vs 32k (Codestral 22B). LLaMA 1 is open weight, while Codestral 22B is closed.
Direct benchmark comparisons are unavailable — LLaMA 1 and Codestral 22B don't publish scores on any of the same benchmarks.