Skip to main content
Van Data Team

text model comparison

Gemini 4 Argon vs Gemini 4 Carbon

Gemini 4 Argon and Gemini 4 Carbon are both current text models, from Google. Both cost $2 per 1M input tokens. On Arena Text, Gemini 4 Argon scores 1520 Elo and Gemini 4 Carbon 1528 Elo (Arena, measured October 28, 2026).

Higher Arena Text
Gemini 4 Carbon1528 Elo against 1520 Elo
Newer release
Gemini 4 CarbonOct 2026 against Sep 2026

Data verified November 5, 2026 · Dataset 2026-11-05

Share this

Side by side

Gemini 4 Argon and Gemini 4 Carbon, line by line

Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.

FactGemini 4 ArgonGemini 4 Carbon
Price
Price per 1M input tokens$2$2
Price per 1M output tokens$10$10
Independent benchmarks
Arena Text1520 Elo (#2 of 52)1528 Elo (#1 of 52) (better)
Arena WebDev1679 Elo (#9 of 46)1768 Elo (#4 of 46) (better)
GPQA Diamond96.4% (#1 of 41)Not measured
FrontierMath Tiers 1-3 (v2)86% (#10 of 41)Not measured
SimpleQA Verified76% (#1 of 38)Not measured
Specs
ProviderGoogleGoogle
Release dateSeptember 30, 2026October 28, 2026
AccessAPI onlylimited access
Context window1,048,576 tokensNot reported
Max output1,000,000 tokensNot reported
Inputtext, image, videotext, image
Outputtexttext

Scores:Arena · 2026-11-03Epoch AI · 2026-11-03

Open both in the interactive comparison

Provider results

What the labs report

Results tables a lab published with one of its models, where it lists both Gemini 4 Argon and Gemini 4 Carbon. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.

Google, Gemini 4 Carbon launch table, October 28, 2026Google · 2026-11-05

BenchmarkGemini 4 ArgonGemini 4 Carbon
SEC-bench Pro83.4%88.2% (better)
ExploitGym42.0%54.8% (better)
CWE-bench68.0%71.0% (better)
SWE-sweep4.3%9.6% (better)
FrontierSWE 255.0%61.2% (better)
Agents' Last Exam v1.1score69.0%77.4% (better)
OSWorld-2.1offline subset74.7%81.5% (better)
AutomationBenchZapier51.3%53.9% (better)
Vending-Bench 2bank balance$13,718$16,484 (better)
Chartography71.6%72.5% (better)
Blueprint-Bench 2similarity score54.4%58.6% (better)
GraphWalks256K to 1M tokens, BFS F184.2%96.2% (better)
RiemannBench76.0%80.0% (better)

Google's table from the Gemini 4 Carbon announcement, evaluated without guardrails; Google publishes its methodology at deepmind.google/models/evals-methodology/gemini-4-carbon. The cybersecurity rows, Google's headline, come first. Left out here: the Artificial Analysis and Vals indexes and the two rows Artificial Analysis ran (Terminal-Bench 4.0 and Terminal-Bench-Science 0.1).

Charts

Against every current text model

Where Gemini 4 Argon and Gemini 4 Carbon land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena Text, Gemini 4 Argon ranks #2 and Gemini 4 Carbon #1 of 52 current models. Each bar is the share of current models it beats: on score, price and context.

Gemini 4 Argon and Gemini 4 Carbon among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

Gemini 4 Argon:#2of 52

1,520 Elo · ahead of 98%

Gemini 4 Carbon:#1of 52

1,528 Elo · ahead of 100%

Arena WebDev

Gemini 4 Argon:#9of 46

1,679 Elo · ahead of 82%

Gemini 4 Carbon:#4of 46

1,768 Elo · ahead of 93%

GPQA Diamond

Gemini 4 Argon:#1of 41

96.4% · ahead of 100%

Gemini 4 Carbon: Not scored

FrontierMath Tiers 1-3 (v2)

Gemini 4 Argon:#10of 41

86% · ahead of 75%

Gemini 4 Carbon: Not scored

SimpleQA Verified

Gemini 4 Argon:#1of 38

76% · ahead of 100%

Gemini 4 Carbon: Not scored

Price and context

Price per 1M input tokens

Gemini 4 Argon:#30of 55

$2 · cheaper than 24%

Gemini 4 Carbon:#30of 55

$2 · cheaper than 24%

Price per 1M output tokens

Gemini 4 Argon:#35of 55

$10 · cheaper than 26%

Gemini 4 Carbon:#35of 55

$10 · cheaper than 26%

Context window

Gemini 4 Argon:#11of 64

1.05M tokens · longer than 67%

Gemini 4 Carbon: Not listed

Scores fromArena · 2026-11-03Epoch AI · 2026-11-03

Quality against price

Arena Text · measured October 28, 2026

Gemini 4 Argon scores 1,520 at $4; Gemini 4 Carbon scores 1,528 at $4 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.

Quality against priceArena Text score against price for 44 text models, Gemini 4 Argon and Gemini 4 Carbon marked.1,2501,3001,3501,4001,4501,5001,550$0.30$1$3$10MOST ATTRACTIVE QUADRANTMedian price $3Median 1,476Blended price per 1M tokens (3 input : 1 output), log scaleArena Text (Elo)Gemini 4 CarbonGemini 4 Argon
Quality against price: the data
Arena Text score against price for 44 text models, Gemini 4 Argon and Gemini 4 Carbon marked.
ModelProviderBlended price per 1M tokensArena Text (Elo)
Gemini 4 CarbonGoogle$41,528
Gemini 4 ArgonGoogle$41,520
Claude Opus 5.5Anthropic$81,509
Muse WonderMeta$81,507
Claude Fable 5Anthropic$201,504
Claude Fable 5.1Anthropic$201,504
Gemini 3.8 FlashGoogle$1.501,496
Muse Spark 1.3Meta$21,495
Claude Opus 5Anthropic$101,492
Kimi K3Moonshot Kimi$61,488
GPT-5.6 SolOpenAI$81,485
Gemini 3.6 FlashGoogle$31,483
GPT-5.5OpenAI$111,482
Claude Opus 4.8Anthropic$101,482
Qwen3.8-MaxAlibaba Qwen$31,482
GPT-6.1 SolOpenAI$41,481
GLM-5.3Z.ai$2.151,481
MiMo-V2.6-ProXiaomi MiMo$0.541,480
Claude Sonnet 5.5Anthropic$41,477
GLM-5.3-FlashZ.ai$0.241,477
GPT-6 AstraOpenAI$201,476
DeepSeek-V4.1-FlashDeepSeek$0.521,476
GPT-5.4OpenAI$5.631,475
Gemini 3 Flash PreviewGoogle$1.131,473
Grok 4.20xAI$1.561,472
GPT-5.6 TerraOpenAI$4.501,467
Grok 4.5xAI$31,465
DeepSeek-V4-ProDeepSeek$1.981,465
Claude Sonnet 5Anthropic$41,462
GPT-6 SolOpenAI$41,458
Gemini 3.5 Flash-LiteGoogle$0.851,456
Grok 4.6xAI$31,455
GPT-5.6 LunaOpenAI$0.451,453
MiMo-V2.6-FlashXiaomi MiMo$0.181,448
Step 5 PreviewStepFun$1.431,448
Grok 4.3xAI$1.561,442
GPT-6 LunaOpenAI$0.201,441
Grok 4.7xAI$31,441
Mistral Large 4Mistral AI$1.051,432
Claude Haiku 5.5Anthropic$0.201,425
GPT-4.1OpenAI$3.501,415
Solar Pro 4Upstage$0.521,388
GPT-4.1 miniOpenAI$0.701,383
GPT-4.1 nanoOpenAI$0.181,322

Cost

What each costs

Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.

The same work, priced

At each provider's listed rates.

What Gemini 4 Argon and Gemini 4 Carbon cost for the same work, at the rates each provider lists.

  • 10M input and 2M output tokens

    The same price

    Gemini 4 Argon
    $40
    Gemini 4 Carbon
    $40

  • The same, with 9M of the input tokens cached

    The same price

    Gemini 4 Argon
    $22.90
    Gemini 4 Carbon
    $22.90
Workload or rateGemini 4 ArgonGemini 4 Carbon
Example workloads
10M input and 2M output tokens$40$40
The same, with 9M of the input tokens cached$22.90$22.90
Other listed rates
1M input tokens, cached$0.10$0.10

Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.

Launch price $100, regular price $150

Book the cost audit

Verdict

When to choose each

Gemini 4 Argon

Where it leads

  • Accepts video input

Best for

  • Long-horizon coding and knowledge work once it reaches general API access

Watch out for

  • The $2 input and $10 output rates are introductory and end on November 30, 2026; from December 1 Google charges $4 and $20 per 1M tokens
  • Not on the Gemini API free tier, and explicit context caching is not supported; implicit caching takes 95% off repeated input
  • Answers longer than 64K tokens need background execution, and Google advises client timeouts of at least 15 minutes for hard prompts
Full Gemini 4 Argon profile

Gemini 4 Carbon

Where it leads

  • Higher Arena Text score, 1528 Elo vs 1520 Elo
  • Higher Arena WebDev score, 1768 Elo vs 1679 Elo

Best for

  • Finding, validating and patching vulnerabilities, for teams in Google's Fairwind Program
  • Long-horizon engineering over very long inputs, once access opens

Watch out for

  • Limited access: Google gives it first to a small group of cyber defenders, then to more trusted partners through its Fairwind Program, which governments, healthcare providers and telecoms apply to; there is no public API or app access yet
  • The $2 and $10 rates are introductory, with cached input 95% off; after an introductory period Google has not dated, $4 input and $20 output per 1M tokens apply
  • In Google's own table it trails GPT-6 Astra on FrontierSWE 2 (61.2% against 65.5%) and Claude Opus 5.5 on OSWorld-2.1 (81.5% against 87.2%)
  • Google publishes no context window or output limit for Carbon yet
Full Gemini 4 Carbon profile

From benchmark to production

Building on Gemini 4 Argon or Gemini 4 Carbon?

Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.

AI Model Cost AuditLaunch price $100, regular price $150What the audit includes

Book the cost auditAI agent development

FAQ

Gemini 4 Argon vs Gemini 4 Carbon FAQ

Which is cheaper, Gemini 4 Argon or Gemini 4 Carbon?

Both cost $2 per 1M input tokens. For 10M input and 2M output tokens, Gemini 4 Argon costs $40 and Gemini 4 Carbon $40 at standard rates.

Which is cheaper with prompt caching, Gemini 4 Argon or Gemini 4 Carbon?

Gemini 4 Argon charges $0.10 per 1M cached input tokens, 95% below its standard input rate, and Gemini 4 Carbon $0.10, 95% below. With 9M of 10M input tokens cached and 2M output tokens, Gemini 4 Argon costs $22.90 and Gemini 4 Carbon $22.90.

Which scores higher on independent benchmarks, Gemini 4 Argon or Gemini 4 Carbon?

Gemini 4 Carbon leads on Arena Text, 1528 Elo to 1520 Elo; Gemini 4 Carbon leads on Arena WebDev, 1768 Elo to 1679 Elo. Scores are independent evaluations, not either vendor's launch figures.

How do Gemini 4 Argon and Gemini 4 Carbon compare in Google's own results?

In Gemini 4 Carbon launch table (October 28, 2026), Gemini 4 Carbon leads on SEC-bench Pro, 88.2% to 83.4%; Gemini 4 Carbon leads on ExploitGym, 54.8% to 42.0%; Gemini 4 Carbon leads on CWE-bench, 71.0% to 68.0%. These are Google's figures, not independent measurements.

How do Gemini 4 Argon and Gemini 4 Carbon differ in features?

Gemini 4 Argon takes text, image and video input; Gemini 4 Carbon takes text and image.

Further reading

More on Gemini 4 Argon and Gemini 4 Carbon

Articles on Gemini 4 Argon and Gemini 4 Carbon

Related comparisons

Production evaluation

Choosing between Gemini 4 Argon and Gemini 4 Carbon?

Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • A head-to-head evaluation on your real workload
  • Routing between models by cost and difficulty
Compare all modelsBook a consultation