GPT-5.4 Thinking System Card
GPT‑5.4 Thinking 是 GPT‑5 系列中最新的推理模型，相关说明见我们在博客上的介绍 https://openai.com/index/introducing-gpt-5-4/ 。该模型的全面安全缓解策略与该系列以往模型大体相似，但 GPT‑5.4 Thinking 是首个在网络安全领域针对 High capability in Cybersecurity 实施缓解措施的通用模型。这些网络安全方面的做法是在此前为 GPT‑5.3 Codex、 ChatGPT 和 API 推出的最新方法基础上发展而来。本文还将 GPT‑5.4 Thinking 简称为 gpt-5.4-thinking；需要注意的是，并不存在名为 GPT‑5.3 Thinking 的模型，因此用于对比基线的主要参考模型是 GPT‑5.2 Thinking 。
----------------------
Introduction
GPT‑5.4 Thinking is the latest reasoning model in the GPT‑5 series, and explained in our blog. The comprehensive safety mitigation approach for this model is similar to previous models in this series, but 5.4 Thinking is the first general purpose model to have implemented mitigations for High capability in Cybersecurity. The approach to cyber safety builds on the latest approaches implemented for GPT‑5.3 Codex, in ChatGPT and the API.
In this card we also refer to GPT‑5.4 Thinking as gpt-5.4-thinking. Note that there is not a model named GPT‑5.3 Thinking, so the main model to baseline against is GPT‑5.2 Thinking.
via OpenAI News
GPT‑5.4 Thinking 是 GPT‑5 系列中最新的推理模型，相关说明见我们在博客上的介绍 https://openai.com/index/introducing-gpt-5-4/ 。该模型的全面安全缓解策略与该系列以往模型大体相似，但 GPT‑5.4 Thinking 是首个在网络安全领域针对 High capability in Cybersecurity 实施缓解措施的通用模型。这些网络安全方面的做法是在此前为 GPT‑5.3 Codex、 ChatGPT 和 API 推出的最新方法基础上发展而来。本文还将 GPT‑5.4 Thinking 简称为 gpt-5.4-thinking；需要注意的是，并不存在名为 GPT‑5.3 Thinking 的模型，因此用于对比基线的主要参考模型是 GPT‑5.2 Thinking 。
----------------------
Introduction
GPT‑5.4 Thinking is the latest reasoning model in the GPT‑5 series, and explained in our blog. The comprehensive safety mitigation approach for this model is similar to previous models in this series, but 5.4 Thinking is the first general purpose model to have implemented mitigations for High capability in Cybersecurity. The approach to cyber safety builds on the latest approaches implemented for GPT‑5.3 Codex, in ChatGPT and the API.
In this card we also refer to GPT‑5.4 Thinking as gpt-5.4-thinking. Note that there is not a model named GPT‑5.3 Thinking, so the main model to baseline against is GPT‑5.2 Thinking.
via OpenAI News
