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. | 200k | 400k |
| Overview | ||
| Company | OpenAI | OpenAI |
| Release date | May 16 2025 | Nov 13 2025 |
| Access | Closed | Closed |
| Model details | View model | View model |
Other comparisons
codex-mini-latestvsClaude Fable 5.2GPT-5.1-Codex-MinivsClaude Fable 5.2codex-mini-latestvsGemini 4 CarbonGPT-5.1-Codex-MinivsGemini 4 Carboncodex-mini-latestvsMuse EmberGPT-5.1-Codex-MinivsMuse Embercodex-mini-latestvsGrok 4.7GPT-5.1-Codex-MinivsGrok 4.7codex-mini-latestvsDeepSeek-V4.1-Flash-1017GPT-5.1-Codex-MinivsDeepSeek-V4.1-Flash-1017codex-mini-latestvsMistral Large 4GPT-5.1-Codex-MinivsMistral Large 4Frequently asked questions
codex-mini-latest and GPT-5.1-Codex-Mini don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. codex-mini-latest shipped 181 days before GPT-5.1-Codex-Mini, so benchmark comparisons should account for the intervening progress.
Context windows are 200k (codex-mini-latest) vs 400k (GPT-5.1-Codex-Mini).
Direct benchmark comparisons are unavailable — codex-mini-latest and GPT-5.1-Codex-Mini don't publish scores on any of the same benchmarks.