gemma-4-31b vs gpt-6-luna
- gemma-4-31b
- 2 advantages
- gpt-6-luna
- 4 advantages
How to choose
gemma-4-31bNo training on conversationsOpen weights
gpt-6-lunaSteadier this week: 100% of tests passedFaster: 1.1s on averageHigher in this week's ranking: #1Longer context: 1.1M tokens
gemma-4-31b
By GoogleNew in the last two weeks
gpt-6-luna
By OpenAI
Where they differ
gemma-4-31bgpt-6-luna
On this site
98%102 callsAvailability, last 3 days100%80 calls
96%193 testsAvailability, this week's tests100%143 tests
2.1sAverage response this week1.1s
FreeReference price per million output tokens$0.75
#8Place in this week's ranking#1
FreeReference price per million input tokens$0.15
The model itself
256K tokensContext length1.1M tokens
256K tokensLongest reply128K tokens
Not used for training.Conversations used for trainingUsed to train and improve the provider’s models.
Jan 2025Knowledge cutoffMay 2026
2 Apr 2026Released22 Sep 2026
YesOpen weightsNo
FreeReference price per million cache-read tokens$0.015
Where they match
- Reads imagesYes
- Calls toolsYes
- Thinks before answeringYes
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
gpt-6-luna against other models
- vs claude-haiku-5.5$0.75Reference price per million output tokens
- vs glm-5.3-flash$0.75Reference price per million output tokens
- vs qwen3.8-flash$0.70Reference price per million output tokens
- vs mistral-small-2603$0.90Reference price per million output tokens
- vs mimo-v2.6-flash$0.42Reference price per million output tokens
- vs mimo-v2.6-pro$1.30Reference price per million output tokens
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 Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.