gemma-4-31b vs gpt-oss-120b
gpt-oss-120b is paused.A paused model is switched off for now and cannot be called. Its figures below are the latest this site has for it.
- gemma-4-31b
- 3 advantages
- gpt-oss-120b
- No edge in the figures
How to choose
gemma-4-31bLonger context: 256K tokensReads imagesNo training on conversations
gpt-oss-120bNo edge in the figures
gemma-4-31b
By GoogleNew in the last two weeks
gpt-oss-120b
By OpenAI
Use in chatDetails
Where they differ
gemma-4-31bgpt-oss-120b
On this site
98%102 callsAvailability, last 3 days—
96%193 testsAvailability, this week's tests—
2.1sAverage response this week—
#8Place in this week's rankingUnranked
The model itself
256K tokensContext length128K tokens
256K tokensLongest reply128K tokens
YesReads imagesNo
Not used for training.Conversations used for trainingThe provider does not say.
Jan 2025Knowledge cutoffJun 2024
2 Apr 2026Released5 Aug 2025
Where they match
- Reference price per million output tokensFree
- Calls toolsYes
- Thinks before answeringYes
- Open weightsYes
- Reference price per million input tokensFree
- Reference price per million cache-read tokensFree
Availability over 3 days counts every call made through the site; this week's availability counts every call over the last 7 days, scheduled tests included, and response time comes from the site's own scheduled tests. Models marked as free are counted in calls; paid models are charged by usage, in US dollars.
Compare next
gemma-4-31b against other models
Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.