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. | 40k | 200k |
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Jun 10 2025 | May 16 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
Magistral MediumvsClaude Fable 5.2codex-mini-latestvsClaude Fable 5.2Magistral MediumvsGemini 4 Carboncodex-mini-latestvsGemini 4 CarbonMagistral MediumvsMuse Embercodex-mini-latestvsMuse EmberMagistral MediumvsGrok 4.7codex-mini-latestvsGrok 4.7Magistral MediumvsDeepSeek-V4.1-Flash-1017codex-mini-latestvsDeepSeek-V4.1-Flash-1017Magistral MediumvsKimi K3.1 Procodex-mini-latestvsKimi K3.1 ProFrequently asked questions
Magistral Medium and codex-mini-latest don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. codex-mini-latest shipped 25 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.
Context windows are 40k (Magistral Medium) vs 200k (codex-mini-latest).
Direct benchmark comparisons are unavailable — Magistral Medium and codex-mini-latest don't publish scores on any of the same benchmarks.