someaistuff.
GoogleReleased Oct 28, 2026

Gemini 4 Carbon

Compare
Context window1M
Provider endpoints0
Benchmark results10
ReasoningImage input

Model overview

Gemini 4 Carbon is a language model from Google. Listed capabilities include reasoning and image input. The listed context window is 1,000,000 tokens.

Provider options and prices

No provider quote is listed in this catalog. Provider details and conditions →

Benchmark coverage

Published results cover 10 named benchmarks. Each example keeps its tested configuration. All results and configurations →

  • AA-Briefcase ↗1,609.49 · 1.1
    Tested identity and configuration909ed0ba-bcc5-4f38-8162-08a4e187a772

    Effort: high · High

    Independent result · Checked

  • AA-Omniscience ↗53.5 · 1.1
    Tested identity and configuration909ed0ba-bcc5-4f38-8162-08a4e187a772

    Effort: high · High

    Independent result · Checked

  • Artificial Analysis Intelligence Index ↗59.43 · 5.0
    Tested identity and configuration909ed0ba-bcc5-4f38-8162-08a4e187a772

    Effort: high · High

    Independent result · Checked

Reported dates · past 30 days
Measured performance

Benchmark results

All leaderboards ↗
AA-Briefcase ↗1.1
1,609.49

Effort: high · High

Independent result
GDP.pdf ↗AA Index 5.0 collection
28.4%

Effort: high · High

Independent result
HLE-Diamond ↗AA Index 5.0 collection
69.1%

Effort: high · High

Independent result
Provider measurements

Speed

1 configuration
≈10K input tokens1 requestmedian / 72h

Artificial Analysis · first-party providers · serving endpoint not reported

Google

Gemini 4 Carbon (High)

Reasoning high

Output rate
97.9884 tok/s
Time to first chunk
103.131 s
Last checked Source ↗
Methodology 2.2.0 & measurement details

First chunk includes request processing and network time, and may include reasoning.

Prompt
long · ≈10,000 input tokens
Parallel requests
1
Minimum answer
1,500 tokens
Aggregation
median over 72 hours
Token counting
o200k_base
Benchmark client
Google Cloud us-central1-a
Serving endpoint
Not reported
Serving region
Not reported
Sample size
Not reported
Window end
Not reported
Official methodology ↗
Access & cost

Prices across providers

0 quotes

No listed provider price

Artificial Analysis ↗

Model specifications

Developer
Google
Modality
Language
Context
1,000,000 tokens
Maximum output
Not reported
Weights
Closed weights
Released
Oct 28, 2026
First discovered
Oct 29, 2026

Exact identities

  • artificial-analysis909ed0ba-bcc5-4f38-8162-08a4e187a772

Sources

Artificial Analysis ↗

Updated Oct 29, 2026

More from Google

View all ↗