arXiv:2601.03267cs.CLcs.AI2026-01被引 802

GPT-5通过智能路由系统动态选择模型,提升真实场景下的回答质量与安全性。

OpenAI GPT-5 System Card

  • 采用动态路由机制,根据问题类型和复杂度自动分配主模型或深度推理模型。
  • 在写作、编程、健康等常见任务上性能超越前代,幻觉率显著降低。
  • 内置安全补全功能,并对生物化学领域启用高能力防护策略。

GPT-5 是一个统一系统,包含快速响应的主模型与深层推理模型,并配备实时路由机制,根据对话类型、问题复杂度、工具需求及用户显式意图(如提示‘仔细思考’)自动选择最优模型。路由模块基于真实使用信号持续训练,包括用户切换行为、响应偏好率与正确性指标,实现自我优化。达到使用上限后,系统将调用各模型的微型版本处理剩余请求。本文重点介绍 gpt-5-thinking 与 gpt-5-main 模型,其他模型评估见附录。GPT-5 不仅在基准测试中表现更优、响应更快,更重要的是在真实查询中更具实用性。系统在减少幻觉、提升指令遵循与抑制盲从方面取得显著进展,并在写作、编码、健康三大常见场景中全面升级。所有 GPT-5 模型均集成安全补全技术,防止违规内容生成。类似 ChatGPT Agent,gpt-5-thinking 在生物与化学领域被列为高能力,触发相应安全机制。尽管尚无确凿证据表明其能助新手制造严重生物危害(高能力定义阈值),仍采取预防性措施。

原文摘要 · Abstract (English)

This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reasoning model for harder problems, and a real-time router that quickly decides which model to use based on conversation type, complexity, tool needs, and explicit intent (for example, if you say 'think hard about this' in the prompt). The router is continuously trained on real signals, including when users switch models, preference rates for responses, and measured correctness, improving over time. Once usage limits are reached, a mini version of each model handles remaining queries. This system card focuses primarily on gpt-5-thinking and gpt-5-main, while evaluations for other models are available in the appendix. The GPT-5 system not only outperforms previous models on benchmarks and answers questions more quickly, but -- more importantly -- is more useful for real-world queries. We've made significant advances in reducing hallucinations, improving instruction following, and minimizing sycophancy, and have leveled up GPT-5's performance in three of ChatGPT's most common uses: writing, coding, and health. All of the GPT-5 models additionally feature safe-completions, our latest approach to safety training to prevent disallowed content. Similarly to ChatGPT agent, we have decided to treat gpt-5-thinking as High capability in the Biological and Chemical domain under our Preparedness Framework, activating the associated safeguards. While we do not have definitive evidence that this model could meaningfully help a novice to create severe biological harm -- our defined threshold for High capability -- we have chosen to take a precautionary approach.

大模型智能路由安全机制

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。