We’re excited to partner with @OpenAI to launch their new open source models natively on Databricks! gpt-oss sets a new standard of quality for open language models, supporting advanced reasoning with the transparency, flexibility and control enterprises need. Running on
LLMS
-
GPT-OSS Models Implement Advanced Safety Training Approaches
By
–
The gpt-oss models leverage our state-of-the-art approaches to safety training. We used deliberative alignment and an instruction hierarchy during post-training to help the models refuse unsafe prompts and defend against prompt injections, as well as pre-training interventions.
-
GPT-OSS-120B Fails High Capability Under Safety Framework
By
–
We adversarially fine-tuned gpt-oss-120b and evaluated the model. We found that even with robust fine-tuning, the model was unable to achieve High capability under our Preparedness Framework. Our methodology was reviewed by external experts, marking a step toward new safety
-
Free GPT-OSS Models Released with MXFP4 Quantization Support
By
–
Both gpt-oss models are free to download on Hugging Face, with native MXFP4 quantization built in for efficient deployment. Full list of day-one support is available on our blog.
-
Agentic AI Models: Advanced Function Calling and Reasoning Capabilities
By
–
These models are trained for agentic workflows—supporting function calling, web search, Python execution, configurable reasoning effort, and full raw chain-of-thought access.
-
Open Source Models Trained for Reasoning and Real-World Deployment
By
–
We trained the gpt-oss models for reasoning, efficiency, and real-world usability across a wide range of deployment environments. Both models were post-trained using our harmony response format to align them with the OpenAI Model Spec and teach them to apply chain‑of‑thought
-
Two Open-Weight Reasoning Models Released Under Apache 2.0
By
–
We released two open-weight reasoning models—gpt-oss-120b and gpt-oss-20b—under an Apache 2.0 license. Developed with open-source community feedback, these models deliver meaningful advancements in both reasoning capabilities & safety.
-
Open-Source LLM Matches OpenAI o4-mini on Benchmarks
By
–
gpt-oss-120b matches OpenAI o4-mini on core benchmarks and exceeds it in narrow domains like competitive math or health-related questions, all while fitting on a single 80GB GPU (or high-end laptop). gpt-oss-20b fits on devices as small as 16GB, while matching or exceeding
-
Competitive STEM Models: Performance Analysis Across Domains
By
–
Modelos bastante competentes en STEM, uso de herramientas, salud, etc. A la par de o3-mini y o4-mini.
-
Sam Altman Announces GPT-OSS Open Weights Reasoning Model Matching o4-mini
By
–
Sam Altman : "gpt-oss est une avancée majeure : il s'agit d'un modèle de raisonnement open weights à la pointe de la technologie, avec des performances solides dans le monde réel, comparables à o4-mini, et que vous pouvez faire tourner localement sur votre propre ordinateur (ou