Learn · Compare

Compare two models.

Side by side

Swap

Google

Gemma 4 31B IT

Release page →

Google

Gemini 3.1 Flash-Lite

Release page →

The basics

Released

Apr 2

Mar 3

What it does

Knowledge cutoff

The latest events it learned about

Not published

January 2025

Download

FreeOpen weights, licence has limits

No: it runs on the maker's servers

Where to use it

Google's app: Gemini ↗

Google's app: Gemini ↗Also for developers, through an API

Price and limits, for developers

Input

Per million tokens

$0.20Cheaper

$0.25

Output

Per million tokens

$0.40Cheaper

$1.50

Cached input

Per million tokens

Not listed

$0.025

Context window

How much it takes in at once

262K tokens about 200,000 words

1.05M tokens about 790,000 wordsBigger

Longest answer

33K tokens about 25,000 words

66K tokens about 49,000 wordsLonger

How they score

Combined test score

Epoch Capabilities Index · Epoch AI

144#98 of 237

145#93 of 237

Too close to call: Gemma 4 31B IT and Gemini 3.1 Flash-Lite are within the margin of error.

Green marks the better of the two on each row, red the other. Rows where one side isn't listed, or where the gap is too close to call, stay plain.

Popular comparisons

Not sure where to start? Which AI should I use? gives a pick for what you want to do. How to read AI rankings explains the numbers.

Rankings from LMArena and Epoch AI, both CC BY 4.0, updated 50m ago. Developer prices, context windows and knowledge cutoffs from the labs' own listings on models.dev and from OpenRouter. The app links go to each maker's own app when no source says exactly where the model is available.