OpenAI
gpt-oss-120b
OpenAI's Apache 2.0 open-weight reasoning model (August 2025) that fits on a single 80GB GPU, with configurable reasoning effort.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Overall rank
- #70
- Tier
- A
- Score
- 70.5
- Main category
- Reasoning
Strengths
- Apache 2.0 license allows commercial use, fine-tuning and self-hosting
- Mixture-of-experts design with about 5.1B active parameters runs on one 80GB GPU
- Configurable reasoning effort, full chain-of-thought access and function calling
Considerations
- Released in August 2025 with no update since; newer open-weight models now score well above it
- 131K-token context window and a June 2024 knowledge cutoff
Price
Free open weights (Apache 2.0); hosted API pricing varies by provider
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 68.0
- 55% of score
- Reputation
- 78.0
- 35% of score
- Recency
- 58.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
Sources
Similar models
- Nemotron 3 SuperNVIDIA#37 · Tier A · Score 81.8Compare
- Gemini 3.1 ProGoogle#48 · Tier A · Score 79.0Compare
- Gemini 2.5 ProGoogle#61 · Tier A · Score 74.3Compare
- OpenAI o3OpenAI#65 · Tier A · Score 72.8Compare