Imagen de Portada

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

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	OpenAI, :, Agarwal, Sandhini, Ahmad, Lama, Ai, Jason, Altman, Sam, Applebaum, Andy, Arbus, Edwin, Arora, Rahul K., Bai, Yu, Baker, Bowen, Bao, Haiming, Barak, Boaz, Bennett, Ally, Bertao, Tyler, Brett, Nivedita, Brevdo, Eugene, Brockman, Greg, Bubeck, Sebastien, Chang, Che, Chen, Kai, Chen, Mark, Cheung, Enoch, Clark, Aidan, Cook, Dan, Dukhan, Marat, Dvorak, Casey, Fives, Kevin, Fomenko, Vlad, Garipov, Timur, Georgiev, Kristian, Glaese, Mia, Gogineni, Tarun, Goucher, Adam, Gross, Lukas, Guzman, Katia Gil, Hallman, John, Hehir, Jackie, Heidecke, Johannes, Helyar, Alec, Hu, Haitang, Huet, Romain, Huh, Jacob, Jain, Saachi, Johnson, Zach, Koch, Chris, Kofman, Irina, Kundel, Dominik, Kwon, Jason, Kyrylov, Volodymyr, Le, Elaine Ya, Leclerc, Guillaume, Lennon, James Park, Lessans, Scott, Lezcano-Casado, Mario, Li, Yuanzhi, Li, Zhuohan, Lin, Ji, Liss, Jordan, Lily, Liu, Liu, Jiancheng, Lu, Kevin, Lu, Chris, Martinovic, Zoran, McCallum, Lindsay, McGrath, Josh, McKinney, Scott, McLaughlin, Aidan, Mei, Song, Mostovoy, Steve, Mu, Tong, Myles, Gideon, Neitz, Alexander, Nichol, Alex, Pachocki, Jakub, Paino, Alex, Palmie, Dana, Pantuliano, Ashley, Parascandolo, Giambattista, Park, Jongsoo, Pathak, Leher, Paz, Carolina, Peran, Ludovic, Pimenov, Dmitry, Pokrass, Michelle, Proehl, Elizabeth, Qiu, Huida, Raila, Gaby, Raso, Filippo, Ren, Hongyu, Richardson, Kimmy, Robinson, David, Rotsted, Bob, Salman, Hadi, Sanjeev, Suvansh, Schwarzer, Max, Sculley, D., Sikchi, Harshit, Simon, Kendal, Singhal, Karan, Song, Yang, Stuckey, Dane, Sun, Zhiqing, Tillet, Philippe, Toizer, Sam, Tsimpourlas, Foivos, Vyas, Nikhil, Wallace, Eric, Wang, Xin, Wang, Miles, Watkins, Olivia, Weil, Kevin, Wendling, Amy, Whinnery, Kevin, Whitney, Cedric, Wong, Hannah, Yang, Lin, Yang, Yu, Yasunaga, Michihiro, Ying, Kristen, Zaremba, Wojciech, Zhan, Wenting, Zhang, Cyril, Zhang, Brian, Zhang, Eddie, Zhao, Shengjia
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

_version_	1866911105777926144
author	OpenAI : Agarwal, Sandhini Ahmad, Lama Ai, Jason Altman, Sam Applebaum, Andy Arbus, Edwin Arora, Rahul K. Bai, Yu Baker, Bowen Bao, Haiming Barak, Boaz Bennett, Ally Bertao, Tyler Brett, Nivedita Brevdo, Eugene Brockman, Greg Bubeck, Sebastien Chang, Che Chen, Kai Chen, Mark Cheung, Enoch Clark, Aidan Cook, Dan Dukhan, Marat Dvorak, Casey Fives, Kevin Fomenko, Vlad Garipov, Timur Georgiev, Kristian Glaese, Mia Gogineni, Tarun Goucher, Adam Gross, Lukas Guzman, Katia Gil Hallman, John Hehir, Jackie Heidecke, Johannes Helyar, Alec Hu, Haitang Huet, Romain Huh, Jacob Jain, Saachi Johnson, Zach Koch, Chris Kofman, Irina Kundel, Dominik Kwon, Jason Kyrylov, Volodymyr Le, Elaine Ya Leclerc, Guillaume Lennon, James Park Lessans, Scott Lezcano-Casado, Mario Li, Yuanzhi Li, Zhuohan Lin, Ji Liss, Jordan Lily Liu Liu, Jiancheng Lu, Kevin Lu, Chris Martinovic, Zoran McCallum, Lindsay McGrath, Josh McKinney, Scott McLaughlin, Aidan Mei, Song Mostovoy, Steve Mu, Tong Myles, Gideon Neitz, Alexander Nichol, Alex Pachocki, Jakub Paino, Alex Palmie, Dana Pantuliano, Ashley Parascandolo, Giambattista Park, Jongsoo Pathak, Leher Paz, Carolina Peran, Ludovic Pimenov, Dmitry Pokrass, Michelle Proehl, Elizabeth Qiu, Huida Raila, Gaby Raso, Filippo Ren, Hongyu Richardson, Kimmy Robinson, David Rotsted, Bob Salman, Hadi Sanjeev, Suvansh Schwarzer, Max Sculley, D. Sikchi, Harshit Simon, Kendal Singhal, Karan Song, Yang Stuckey, Dane Sun, Zhiqing Tillet, Philippe Toizer, Sam Tsimpourlas, Foivos Vyas, Nikhil Wallace, Eric Wang, Xin Wang, Miles Watkins, Olivia Weil, Kevin Wendling, Amy Whinnery, Kevin Whitney, Cedric Wong, Hannah Yang, Lin Yang, Yu Yasunaga, Michihiro Ying, Kristen Zaremba, Wojciech Zhan, Wenting Zhang, Cyril Zhang, Brian Zhang, Eddie Zhao, Shengjia
author_facet	OpenAI : Agarwal, Sandhini Ahmad, Lama Ai, Jason Altman, Sam Applebaum, Andy Arbus, Edwin Arora, Rahul K. Bai, Yu Baker, Bowen Bao, Haiming Barak, Boaz Bennett, Ally Bertao, Tyler Brett, Nivedita Brevdo, Eugene Brockman, Greg Bubeck, Sebastien Chang, Che Chen, Kai Chen, Mark Cheung, Enoch Clark, Aidan Cook, Dan Dukhan, Marat Dvorak, Casey Fives, Kevin Fomenko, Vlad Garipov, Timur Georgiev, Kristian Glaese, Mia Gogineni, Tarun Goucher, Adam Gross, Lukas Guzman, Katia Gil Hallman, John Hehir, Jackie Heidecke, Johannes Helyar, Alec Hu, Haitang Huet, Romain Huh, Jacob Jain, Saachi Johnson, Zach Koch, Chris Kofman, Irina Kundel, Dominik Kwon, Jason Kyrylov, Volodymyr Le, Elaine Ya Leclerc, Guillaume Lennon, James Park Lessans, Scott Lezcano-Casado, Mario Li, Yuanzhi Li, Zhuohan Lin, Ji Liss, Jordan Lily Liu Liu, Jiancheng Lu, Kevin Lu, Chris Martinovic, Zoran McCallum, Lindsay McGrath, Josh McKinney, Scott McLaughlin, Aidan Mei, Song Mostovoy, Steve Mu, Tong Myles, Gideon Neitz, Alexander Nichol, Alex Pachocki, Jakub Paino, Alex Palmie, Dana Pantuliano, Ashley Parascandolo, Giambattista Park, Jongsoo Pathak, Leher Paz, Carolina Peran, Ludovic Pimenov, Dmitry Pokrass, Michelle Proehl, Elizabeth Qiu, Huida Raila, Gaby Raso, Filippo Ren, Hongyu Richardson, Kimmy Robinson, David Rotsted, Bob Salman, Hadi Sanjeev, Suvansh Schwarzer, Max Sculley, D. Sikchi, Harshit Simon, Kendal Singhal, Karan Song, Yang Stuckey, Dane Sun, Zhiqing Tillet, Philippe Toizer, Sam Tsimpourlas, Foivos Vyas, Nikhil Wallace, Eric Wang, Xin Wang, Miles Watkins, Olivia Weil, Kevin Wendling, Amy Whinnery, Kevin Whitney, Cedric Wong, Hannah Yang, Lin Yang, Yu Yasunaga, Michihiro Ying, Kristen Zaremba, Wojciech Zhan, Wenting Zhang, Cyril Zhang, Brian Zhang, Eddie Zhao, Shengjia
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2508_10925
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	gpt-oss-120b & gpt-oss-20b Model Card OpenAI : Agarwal, Sandhini Ahmad, Lama Ai, Jason Altman, Sam Applebaum, Andy Arbus, Edwin Arora, Rahul K. Bai, Yu Baker, Bowen Bao, Haiming Barak, Boaz Bennett, Ally Bertao, Tyler Brett, Nivedita Brevdo, Eugene Brockman, Greg Bubeck, Sebastien Chang, Che Chen, Kai Chen, Mark Cheung, Enoch Clark, Aidan Cook, Dan Dukhan, Marat Dvorak, Casey Fives, Kevin Fomenko, Vlad Garipov, Timur Georgiev, Kristian Glaese, Mia Gogineni, Tarun Goucher, Adam Gross, Lukas Guzman, Katia Gil Hallman, John Hehir, Jackie Heidecke, Johannes Helyar, Alec Hu, Haitang Huet, Romain Huh, Jacob Jain, Saachi Johnson, Zach Koch, Chris Kofman, Irina Kundel, Dominik Kwon, Jason Kyrylov, Volodymyr Le, Elaine Ya Leclerc, Guillaume Lennon, James Park Lessans, Scott Lezcano-Casado, Mario Li, Yuanzhi Li, Zhuohan Lin, Ji Liss, Jordan Lily Liu Liu, Jiancheng Lu, Kevin Lu, Chris Martinovic, Zoran McCallum, Lindsay McGrath, Josh McKinney, Scott McLaughlin, Aidan Mei, Song Mostovoy, Steve Mu, Tong Myles, Gideon Neitz, Alexander Nichol, Alex Pachocki, Jakub Paino, Alex Palmie, Dana Pantuliano, Ashley Parascandolo, Giambattista Park, Jongsoo Pathak, Leher Paz, Carolina Peran, Ludovic Pimenov, Dmitry Pokrass, Michelle Proehl, Elizabeth Qiu, Huida Raila, Gaby Raso, Filippo Ren, Hongyu Richardson, Kimmy Robinson, David Rotsted, Bob Salman, Hadi Sanjeev, Suvansh Schwarzer, Max Sculley, D. Sikchi, Harshit Simon, Kendal Singhal, Karan Song, Yang Stuckey, Dane Sun, Zhiqing Tillet, Philippe Toizer, Sam Tsimpourlas, Foivos Vyas, Nikhil Wallace, Eric Wang, Xin Wang, Miles Watkins, Olivia Weil, Kevin Wendling, Amy Whinnery, Kevin Whitney, Cedric Wong, Hannah Yang, Lin Yang, Yu Yasunaga, Michihiro Ying, Kristen Zaremba, Wojciech Zhan, Wenting Zhang, Cyril Zhang, Brian Zhang, Eddie Zhao, Shengjia Computation and Language Artificial Intelligence 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.
title	gpt-oss-120b & gpt-oss-20b Model Card
topic	Computation and Language Artificial Intelligence
url	https://arxiv.org/abs/2508.10925