gpt-oss-120b & gpt-oss-20b Model Card

• URL: http://arxiv.org/abs/2508.10925v1
• Date: Fri, 08 Aug 2025 19:24:38 GMT
• Title: gpt-oss-120b & gpt-oss-20b Model Card
• Authors: OpenAI, :, Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, Mark Chen, Enoch Cheung, Aidan Clark, Dan Cook, Marat Dukhan, Casey Dvorak, Kevin Fives, Vlad Fomenko, Timur Garipov, Kristian Georgiev, Mia Glaese, Tarun Gogineni, Adam Goucher, Lukas Gross, Katia Gil Guzman, John Hallman, Jackie Hehir, Johannes Heidecke, Alec Helyar, Haitang Hu, Romain Huet, Jacob Huh, Saachi Jain, Zach Johnson, Chris Koch, Irina Kofman, Dominik Kundel, Jason Kwon, Volodymyr Kyrylov, Elaine Ya Le, Guillaume Leclerc, James Park Lennon, Scott Lessans, Mario Lezcano-Casado, Yuanzhi Li, Zhuohan Li, Ji Lin, Jordan Liss, Lily, Liu, Jiancheng Liu, Kevin Lu, Chris Lu, Zoran Martinovic, Lindsay McCallum, Josh McGrath, Scott McKinney, Aidan McLaughlin, Song Mei, Steve Mostovoy, Tong Mu, Gideon Myles, Alexander Neitz, Alex Nichol, Jakub Pachocki, Alex Paino, Dana Palmie, Ashley Pantuliano, Giambattista Parascandolo, Jongsoo Park, Leher Pathak, Carolina Paz, Ludovic Peran, Dmitry Pimenov, Michelle Pokrass, Elizabeth Proehl, Huida Qiu, Gaby Raila, Filippo Raso, Hongyu Ren, Kimmy Richardson, David Robinson, Bob Rotsted, Hadi Salman, Suvansh Sanjeev, Max Schwarzer, D. Sculley, Harshit Sikchi, Kendal Simon, Karan Singhal, Yang Song, Dane Stuckey, Zhiqing Sun, Philippe Tillet, Sam Toizer, Foivos Tsimpourlas, Nikhil Vyas, Eric Wallace, Xin Wang, Miles Wang, Olivia Watkins, Kevin Weil, Amy Wendling, Kevin Whinnery, Cedric Whitney, Hannah Wong, Lin Yang, Yu Yang, Michihiro Yasunaga, Kristen Ying, Wojciech Zaremba, Wenting Zhan, Cyril Zhang, Brian Zhang, Eddie Zhang, Shengjia Zhao,
• Abstract summary: We present two open-weight reasoning models that push the frontier of accuracy and inference cost.<n>The models use an efficient mixture-of-expert transformer architecture and are trained using large-scale distillation and reinforcement learning.
• Score: 128.07668730833967
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection [51.10348385624784]
  We present WebSeer, a more intelligent search agent trained via reinforcement learning enhanced with a self-reflection mechanism.<n>Our approach substantially extends tool-use chains and improves answer accuracy.
  arXiv  Detail & Related papers  (2025-10-21T16:52:00Z)
• Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models [49.911784762244814]
  TraceRL is a trajectory-aware reinforcement learning framework for diffusion language models (DLMs)<n>We derive a series of state-of-the-art diffusion language models, namely TraDo.<n>TraDo-8B-Instruct achieves relative accuracy improvements of 6.1% over Qwen2.5-7B-Instruct and 51.3% over Llama3.1-8B-Instruct on mathematical reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• Matryoshka Model Learning for Improved Elastic Student Models [62.154536258259384]
  MatTA is a framework for training multiple accurate Student models using a novel Teacher-TA-Student recipe.<n>We demonstrate our method on GPT-2 Medium, a public model, and achieve relative improvements of over 24% on SAT Math and over 10% on the LAMBADA benchmark.
  arXiv  Detail & Related papers  (2025-05-29T10:54:58Z)
• Granite Embedding Models [26.86244952892162]
  We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks.<n>This report provides the technical details of training these highly effective 12 layer embedding models, along with their efficient 6 layer distilled counterparts.<n>We publicly release all our Granite Embedding models under the Apache 2.0 license, allowing both research and commercial use at https://huggingface.co/collections/ibm-granite.
  arXiv  Detail & Related papers  (2025-02-27T15:45:16Z)
• Scaling New Frontiers: Insights into Large Recommendation Models [74.77410470984168]
  Meta's generative recommendation model HSTU illustrates the scaling laws of recommendation systems by expanding parameters to thousands of billions.<n>We conduct comprehensive ablation studies to explore the origins of these scaling laws.<n>We offer insights into future directions for large recommendation models.
  arXiv  Detail & Related papers  (2024-12-01T07:27:20Z)
• Puzzle: Distillation-Based NAS for Inference-Optimized LLMs [17.72841008597783]
  Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption.<n>We present Puzzle, a hardware-aware framework that accelerates the inference of LLMs while preserving their capabilities.<n>We showcase our framework's impact via Llama-3.1-Nemotron-51B-Instruct (Nemotron-51B) and Llama-3.3-Nemotron-49B, two publicly available models.
  arXiv  Detail & Related papers  (2024-11-28T13:45:42Z)
• A Collaborative Ensemble Framework for CTR Prediction [73.59868761656317]
  We propose a novel framework, Collaborative Ensemble Training Network (CETNet), to leverage multiple distinct models. Unlike naive model scaling, our approach emphasizes diversity and collaboration through collaborative learning. We validate our framework on three public datasets and a large-scale industrial dataset from Meta.
  arXiv  Detail & Related papers  (2024-11-20T20:38:56Z)
• Characterizing Disparity Between Edge Models and High-Accuracy Base Models for Vision Tasks [5.081175754775484]
  We introduce XDELTA, a novel explainable AI tool that explains differences between a high-accuracy base model and a computationally efficient but lower-accuracy edge model. We conduct a comprehensive evaluation to test XDELTA's ability to explain model discrepancies, using over 1.2 million images and 24 models, and assessing real-world deployments with six participants.
  arXiv  Detail & Related papers  (2024-07-13T22:05:58Z)
• Yi: Open Foundation Models by 01.AI [40.985204944978385]
  Yi model family is based on 6B and 34B pretrained language models, then we extend them to chat models, 200K long context models, depth-upscaled models, and vision-language models.<n>Our base models achieve strong performance on a wide range of benchmarks like MMLU, and our fine chat models deliver strong human preference rate on major evaluation platforms like AlpacaEval and Arena.
  arXiv  Detail & Related papers  (2024-03-07T16:52:49Z)
• Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models [1.0878040851637998]
  With over 200, 000 models in the Hugging Face ecosystem, users grapple with selecting and optimizing models to suit multifaceted and data domains. Here, we propose a context-aware routing system, Tryage, that leverages a language model router for optimal selection of expert models from a model library.
  arXiv  Detail & Related papers  (2023-08-22T17:48:24Z)
• Ensembling Off-the-shelf Models for GAN Training [55.34705213104182]
  We find that pretrained computer vision models can significantly improve performance when used in an ensemble of discriminators. We propose an effective selection mechanism, by probing the linear separability between real and fake samples in pretrained model embeddings. Our method can improve GAN training in both limited data and large-scale settings.
  arXiv  Detail & Related papers  (2021-12-16T18:59:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.