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 | — |
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 | OpenAI |
| Release date | May 29 2024 | Feb 12 2026 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5GPT-5.3-Codex-SparkvsClaude Haiku 5.5Codestral 22BvsGemini 4 ArgonGPT-5.3-Codex-SparkvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenGPT-5.3-Codex-SparkvsMuse Spark OpenCodestral 22BvsGrok 4.7GPT-5.3-Codex-SparkvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017GPT-5.3-Codex-SparkvsDeepSeek-V4.1-Flash-1017Codestral 22BvsKimi K3GPT-5.3-Codex-SparkvsKimi K3Frequently asked questions
Codestral 22B and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 624 days before GPT-5.3-Codex-Spark, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Codestral 22B) vs 128k (GPT-5.3-Codex-Spark).
Direct benchmark comparisons are unavailable — Codestral 22B and GPT-5.3-Codex-Spark don't publish scores on any of the same benchmarks.