Compare AI models
| Specifications | ||
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 | 200k |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Dec 11 2023 | May 16 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Mistral MediumvsClaude Fable 5.2codex-mini-latestvsClaude Fable 5.2Mistral MediumvsGemini 4 Carboncodex-mini-latestvsGemini 4 CarbonMistral MediumvsMuse Embercodex-mini-latestvsMuse EmberMistral MediumvsGrok 4.7codex-mini-latestvsGrok 4.7Mistral MediumvsDeepSeek-V4.1-Flash-1017codex-mini-latestvsDeepSeek-V4.1-Flash-1017Mistral MediumvsKimi K3.1 Procodex-mini-latestvsKimi K3.1 ProFrequently asked questions
Mistral Medium and codex-mini-latest don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Mistral Medium shipped 522 days before codex-mini-latest, so benchmark comparisons should account for the intervening progress.
Context windows are 32k (Mistral Medium) vs 200k (codex-mini-latest).
Direct benchmark comparisons are unavailable — Mistral Medium and codex-mini-latest don't publish scores on any of the same benchmarks.