Skip to content
trckr.ai

Loading…

Learn · Compare

Compare two models.

Side by side

Swap

Gemini 4 Carbon

Google's most powerful AI model so far, built for cybersecurity work and long, complicated tasks. For now only security teams in a Google programme can use it; others get it later, with no date yet.

Release page →

The basics

Released

Oct 28
May 28

What it does

Text and chat: Writes, answers questions and holds a conversation.
Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.Sees images: Understands pictures, screenshots and charts you share with it.Reads files: Reads documents such as PDFs.

Knowledge cutoff

The latest events it learned about

Not published
January 2026

Download

No: it runs on the maker's servers
No: it runs on the maker's servers

Where to use it

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

Price and limits, for developers

Input

Per million tokens

Not listed
$5.00

Output

Per million tokens

Not listed
$25.00

Cached input

Per million tokens

Not listed
$0.50

Context window

How much it takes in at once

Not listed
1M tokens about 750,000 words

Longest answer

Not listed
128K tokens about 96,000 words

How they score

Combined test score

Epoch Capabilities Index · Epoch AI

Not ranked
160#20 of 237

Only Claude Opus 4.8 is in this ranking.

Chat answers, by people's votes

LMArena text, adjusted for style · LMArena

1,527#1 of 86Higher
1,482#23 of 86

In blind votes, people pick Gemini 4 Carbon over Claude Opus 4.8 about 56% of the time.

Building apps, by people's votes

LMArena WebDev · LMArena

1,768#3 of 85Higher
1,555#42 of 85

In blind votes, people pick Gemini 4 Carbon over Claude Opus 4.8 about 77% of the time.

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 . 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.

Free alerts

Know the moment a new model drops.

Pick one or several. Each has its own settings for what you hear about.