开源1200亿与200亿参数推理模型，支持深度研究与编程工具调用。
gpt-oss-120b & gpt-oss-20b Model Card
- 采用高效专家混合架构，通过大规模蒸馏与强化学习训练。
- 在数学、编程和安全基准上表现优异，兼具强指令遵循能力。
- 适合开发者研究智能代理，提供完整开源工具链支持。
我们提出 gpt-oss-120b 与 gpt-oss-20b 两款开源权重推理模型，推动准确率与推理成本的边界。模型采用高效的专家混合变换器架构，通过大规模知识蒸馏与强化学习进行训练。优化后具备强大的智能体能力（深度研究浏览、Python 工具调用、支持开发者自定义函数），同时采用渲染化的聊天格式，实现清晰的指令遵循与角色区分。两款模型在数学、编码与安全性等多个基准测试中均取得优异表现。我们以 Apache 2.0 许可证发布模型权重、推理实现、工具环境及分词器，支持广泛使用与后续研究。
原文摘要 · Abstract (English)
We present gpt-oss-120b and gpt-oss-20b, two open-weight reasoning models that push the frontier of accuracy and inference cost. The models use an efficient mixture-of-expert transformer architecture and are trained using large-scale distillation and reinforcement learning. We optimize the models to have strong agentic capabilities (deep research browsing, python tool use, and support for developer-provided functions), all while using a rendered chat format that enables clear instruction following and role delineation. Both models achieve strong results on benchmarks ranging from mathematics, coding, and safety. We release the model weights, inference implementations, tool environments, and tokenizers under an Apache 2.0 license to enable broad use and further research.
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。