GPT OSS 120B
Open GPT reasoning model for self-hosted agents and controllable deployments
ECI STANDING#109 of 266
SCORE140.1136.28–142.7 CI
FRONTIER LAGLaunched 7.6 months behindScores about what o1 did in December 2024.
SCORES LIKE THESE MODELSo3-miniOpenAI · Jan 2025140.35
Full Epoch Capabilities Index ranking ↗Kimi K2 (Jul 2025)Moonshot · Jul 2025140.11
Gemini 2.5 Flash (Apr 2025)Google DeepMind · Apr 2025139.97
DeepSeek-V3.1DeepSeek · Aug 2025139.92RELEASE DATEAug 5, 2025
WEIGHTSOpen weights
CONTEXT WINDOW131.1K
MAX OUTPUT32.8K
REASONINGYes
TOOL CALLINGYes
INPUTStext
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.