onomeoonomeoBeta

gemma-4-31b vs mistral-small-3.1

gemma-4-31b
5 advantages
mistral-small-3.1
1 advantage

How to choose

gemma-4-31bFaster: 2.1s on averageLonger context: 256K tokensThinks before answeringNo training on conversationsOpen weights
mistral-small-3.1Higher in this week's ranking: #6

gemma-4-31b

By Google

mistral-small-3.1

By Mistral AI

Where they differ

gemma-4-31bmistral-small-3.1
On this site
98%102 callsAvailability, last 3 days99%102 calls
96%193 testsAvailability, this week's tests98%183 tests
2.1sAverage response this week9.2s
#8Place in this week's ranking#6
The model itself
256K tokensContext length128K tokens
256K tokensLongest reply32K tokens
YesThinks before answeringNo
Not used for training.Conversations used for trainingThe provider does not say.
Jan 2025Knowledge cutoffSep 2024
2 Apr 2026Released1 Mar 2025
YesOpen weightsNo

Where they match

  • Reference price per million output tokensFree
  • Reads imagesYes
  • Calls toolsYes
  • 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

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 Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.