gpt-oss-120b

gpt-oss-120b

OpenAI🇺🇸openai/gpt-oss-120b
Compare

GPT-OSS-120B is OpenAI's open-weight mixture-of-experts model (around 120B parameters) released under a permissive license for self-hosted deployment. It offers strong reasoning and coding performance for teams that need to run OpenAI-quality models on their own infrastructure.

Released
Aug 5, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs

Performance

Median latency and throughput measured across recent requests.

Intelligence3.8Rank #152
Throughput205 tok/s
Latency1.36s

Best at

The categories where this model ranks highest.

Mathematical

#193 · top 48%

Business, Management, & Finance

#218 · top 53%

Medicine & Healthcare

#224 · top 57%

Software & IT Services

#225 · top 53%

DomainScoreRank
Software & IT Services1385#225
Writing, Literature, & Language1310#248
Life, Physical, & Social Science1361#230
Entertainment, Sports, & Media1287#257
Business, Management, & Finance1352#218
Mathematical1384#193
Legal & Government1341#247
Medicine & Healthcare1366#224
CategoryWin rateRank
Data Visualization43.6%#125
Game Development40.5%#131
3D29.4%#133
UI Component35.7%#137
Code Categories33.4%#141
Website32.5%#144

Latest news about gpt-oss-120b

Recent articles and community posts, linked to their original sources.