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 | 400k |
| These models have no shared benchmark scores. | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 39% |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | May 29 2024 | Sep 15 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Codestral 22BvsClaude Haiku 5.5GPT-5-CodexvsClaude Haiku 5.5Codestral 22BvsGemini 4 ArgonGPT-5-CodexvsGemini 4 ArgonCodestral 22BvsMuse Spark OpenGPT-5-CodexvsMuse Spark OpenCodestral 22BvsGrok 4.7GPT-5-CodexvsGrok 4.7Codestral 22BvsDeepSeek-V4.1-Flash-1017GPT-5-CodexvsDeepSeek-V4.1-Flash-1017Codestral 22BvsKimi K3GPT-5-CodexvsKimi K3Frequently asked questions
Codestral 22B and GPT-5-Codex don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Codestral 22B shipped 474 days before GPT-5-Codex, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Codestral 22B) vs 400k (GPT-5-Codex).
Direct benchmark comparisons are unavailable — Codestral 22B and GPT-5-Codex don't publish scores on any of the same benchmarks.