Skip to main content
Van Data Team

text model comparison

Gemini 4 Carbon vs Gemini 4 Hydrogen

Gemini 4 Carbon and Gemini 4 Hydrogen are both current text models, from Google. Gemini 4 Hydrogen is 25% cheaper per 1M input tokens than Gemini 4 Carbon, $1.50 vs $2. On Arena Text, Gemini 4 Carbon scores 1526 Elo and Gemini 4 Hydrogen 1490 Elo (Arena, measured November 11, 2026). Both accept 1,048,576 tokens of context.

Higher Arena Text
Gemini 4 Carbon1526 Elo against 1490 Elo
Lower price per 1M input tokens
Gemini 4 Hydrogen$1.50 against $2
Newer release
Gemini 4 HydrogenNov 2026 against Oct 2026

Data verified November 15, 2026 · Dataset 2026-11-15

Share this

Side by side

Gemini 4 Carbon and Gemini 4 Hydrogen, 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 CarbonGemini 4 Hydrogen
Price
Price per 1M input tokens$2$1.50 (better)
Price per 1M output tokens$10$7.50 (better)
Independent benchmarks
Arena Text1526 Elo (#1 of 50) (better)1490 Elo (#7 of 50)
Arena WebDev1768 Elo (#4 of 45) (better)1704 Elo (#7 of 45)
GPQA Diamond96.5% (#1 of 40)Not measured
FrontierMath Tiers 1-3 (v2)90.5% (#6 of 39)Not measured
SimpleQA Verified77.7% (#2 of 36)Not measured
Specs
ProviderGoogleGoogle
Release dateOctober 28, 2026November 12, 2026
AccessAPI onlyAPI only
Context window1,048,576 tokens1,048,576 tokens
Max output65,536 tokens65,536 tokens
Inputtext, image, audio, videotext, image, audio, video
Outputtexttext

Scores:Arena · 2026-11-15Epoch AI · 2026-11-11

Open both in the interactive comparison

Charts

Against every current text model

Where Gemini 4 Carbon and Gemini 4 Hydrogen 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 Carbon ranks #1 and Gemini 4 Hydrogen #7 of 50 current models. Each bar is the share of current models it beats: on score, price and context.

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

Independent benchmarks

Arena Text

Gemini 4 Carbon:#1of 50

1,526 Elo · ahead of 100%

Gemini 4 Hydrogen:#7of 50

1,490 Elo · ahead of 88%

Arena WebDev

Gemini 4 Carbon:#4of 45

1,768 Elo · ahead of 93%

Gemini 4 Hydrogen:#7of 45

1,704 Elo · ahead of 86%

GPQA Diamond

Gemini 4 Carbon:#1of 40

96.5% · ahead of 100%

Gemini 4 Hydrogen: Not scored

FrontierMath Tiers 1-3 (v2)

Gemini 4 Carbon:#6of 39

90.5% · ahead of 87%

Gemini 4 Hydrogen: Not scored

SimpleQA Verified

Gemini 4 Carbon:#2of 36

77.7% · ahead of 97%

Gemini 4 Hydrogen: Not scored

Price and context

Price per 1M input tokens

Gemini 4 Carbon:#34of 58

$2 · cheaper than 23%

Gemini 4 Hydrogen:#32of 58

$1.50 · cheaper than 44%

Price per 1M output tokens

Gemini 4 Carbon:#39of 58

$10 · cheaper than 25%

Gemini 4 Hydrogen:#36of 58

$7.50 · cheaper than 37%

Context window

Gemini 4 Carbon:#12of 68

1.05M tokens · longer than 61%

Gemini 4 Hydrogen:#12of 68

1.05M tokens · longer than 61%

Scores fromArena · 2026-11-15Epoch AI · 2026-11-11

Quality against price

Arena Text · measured November 11, 2026

Gemini 4 Carbon scores 1,526 at $4; Gemini 4 Hydrogen scores 1,490 at $3 (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 42 text models, Gemini 4 Carbon and Gemini 4 Hydrogen marked.1,2501,3001,3501,4001,4501,5001,550$0.30$1$3$10MOST ATTRACTIVE QUADRANTMedian price $2.58Median 1,473Blended price per 1M tokens (3 input : 1 output), log scaleArena Text (Elo)Gemini 4 CarbonGemini 4 Hydrogen
Quality against price: the data
Arena Text score against price for 42 text models, Gemini 4 Carbon and Gemini 4 Hydrogen marked.
ModelProviderBlended price per 1M tokensArena Text (Elo)
Gemini 4 CarbonGoogle$41,526
Gemini 4 ArgonGoogle$41,522
Muse WonderMeta$81,511
Claude Opus 5.5Anthropic$81,507
Gemini 3.8 FlashGoogle$1.501,497
Muse Spark 1.3Meta$21,497
Gemini 4 HydrogenGoogle$31,490
Kimi K3Moonshot Kimi$61,487
GPT-5.6 SolOpenAI$81,485
Kimi K3.1 ProMoonshot Kimi$41,485
Qwen3.8-MaxAlibaba Qwen$31,484
Gemini 3.6 FlashGoogle$31,483
GLM-5.3Z.ai$2.151,482
GPT-5.5OpenAI$111,481
GPT-6.1 SolOpenAI$41,481
MiMo-V2.6-ProXiaomi MiMo$0.541,480
GPT-5.4OpenAI$5.631,475
DeepSeek-V4.1-FlashDeepSeek$0.521,475
GLM-5.3-FlashZ.ai$0.241,475
GPT-6 AstraOpenAI$201,474
Gemini 3 Flash PreviewGoogle$1.131,473
Claude Sonnet 5.5Anthropic$41,473
Grok 4.20xAI$1.561,472
GPT-5.6 TerraOpenAI$4.501,468
Grok 4.5xAI$31,466
DeepSeek-V4-ProDeepSeek$1.981,464
Grok 4.6xAI$31,457
GPT-6 SolOpenAI$41,457
Gemini 3.5 Flash-LiteGoogle$0.851,455
GPT-5.6 LunaOpenAI$0.451,453
Step 5 PreviewStepFun$1.431,449
MiMo-V2.6-FlashXiaomi MiMo$0.181,448
Grok 4.7xAI$31,443
Grok 4.3xAI$1.561,442
GPT-6 LunaOpenAI$0.201,441
Claude Haiku 5.5Anthropic$0.201,421
Mistral Large 4Mistral AI$1.051,420
GPT-4.1OpenAI$3.501,415
Inkling 2 SmallThinking Machines Lab$0.471,412
Solar Pro 4Upstage$0.521,387
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

For 10M input and 2M output tokens, Gemini 4 Carbon costs 1.3 times as much as Gemini 4 Hydrogen, at each provider's listed rates.

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

  • 10M input and 2M output tokens

    Gemini 4 Carbon costs 1.3× as much

    Gemini 4 Carbon
    $40
    Gemini 4 Hydrogen
    $30

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

    Gemini 4 Carbon costs 1.3× as much

    Gemini 4 Carbon
    $22.90
    Gemini 4 Hydrogen
    $17.18

  • The same, through the batch API

    Gemini 4 Carbon costs 1.3× as much

    Gemini 4 Carbon
    $20
    Gemini 4 Hydrogen
    $15
Workload or rateGemini 4 CarbonGemini 4 Hydrogen
Example workloads
10M input and 2M output tokens$40$30 (better)
The same, with 9M of the input tokens cached$22.90$17.18 (better)
The same, through the batch API$20$15 (better)
Other listed rates
1M input tokens, cached$0.10$0.075 (better)
1M input tokens, batch$1$0.75 (better)
1M output tokens, batch$5$3.75 (better)
1M input tokens, priorityNot listed$2.70
1M output tokens, priorityNot listed$13.50

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

See the cost audit

Verdict

When to choose each

Gemini 4 Carbon

Where it leads

  • Higher Arena Text score, 1526 Elo vs 1490 Elo
  • Higher Arena WebDev score, 1768 Elo vs 1704 Elo

Best for

  • Finding, validating and patching vulnerabilities
  • Long-horizon engineering and research over very long inputs

Watch out for

  • Generally available in the Gemini API since November 10, 2026, on the paid tier only (there is no free tier), after two weeks open only to cyber defenders in its Fairwind Program
  • The $2 and $10 rates are introductory and end on November 30, 2026: from December 1, input, output and cached input double, to $4, $20 and $0.20 per 1M tokens (Batch from $1 and $5 to $2 and $10)
  • 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%)
  • A request returns at most 65,536 output tokens by default; longer outputs, up to 1,048,576 tokens, need Google long-decode mode
Full Gemini 4 Carbon profile

Gemini 4 Hydrogen

Where it leads

  • Lower input and output prices, $1.50 and $7.50 vs $2 and $10 per 1M tokens
  • Cheaper cached input, $0.075 vs $0.10 per 1M tokens
  • Cheaper batch processing, $15 vs $20 for 10M input and 2M output tokens

Best for

  • Everyday coding, tool-using agents and parallel sub-agents at a mid-tier price
  • Document, chart and video workflows over very long multimodal inputs

Watch out for

  • In Google's own table Claude Sonnet 5.5 scores higher on Terminal-Bench 4.1 (63.9% against 57.0%), OSWorld-2.1 (83.9% against 77.6%) and Terminal-Bench-Science 0.1 (59.9% against 51.4%)
  • A request returns at most 65,536 output tokens by default; longer outputs, up to 1,048,576 tokens, need Google long-decode mode, and only implicit context caching is supported
  • Arena places it below Claude Sonnet 5.5 on WebDev (1704 against 1772) and just below Gemini 3.8 Flash on Arena Text (1490 against 1497), on 4,741 text and 1,997 WebDev votes so far; Epoch AI has not measured it yet
Full Gemini 4 Hydrogen profile

From benchmark to production

Building on Gemini 4 Carbon or Gemini 4 Hydrogen?

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 $150

See the cost auditAI agent development

FAQ

Gemini 4 Carbon vs Gemini 4 Hydrogen FAQ

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

Gemini 4 Hydrogen is 25% cheaper per 1M input tokens than Gemini 4 Carbon, $1.50 vs $2. For 10M input and 2M output tokens, Gemini 4 Carbon costs $40 and Gemini 4 Hydrogen $30 at standard rates.

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

Gemini 4 Carbon charges $0.10 per 1M cached input tokens, 95% below its standard input rate, and Gemini 4 Hydrogen $0.075, 95% below. With 9M of 10M input tokens cached and 2M output tokens, Gemini 4 Carbon costs $22.90 and Gemini 4 Hydrogen $17.18.

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

Gemini 4 Carbon leads on Arena Text, 1526 Elo to 1490 Elo; Gemini 4 Carbon leads on Arena WebDev, 1768 Elo to 1704 Elo. Scores are independent evaluations, not either vendor's launch figures.

Which has the larger context window, Gemini 4 Carbon or Gemini 4 Hydrogen?

Both accept 1,048,576 tokens of context. Both return up to 65,536 tokens per response.

AI Model Brief

The AI models worth knowing, once a week

What shipped, how it scores on independent benchmarks, what it costs per million tokens and what was deprecated, from the data behind our AI model benchmarks.

One email a week. We send a confirmation link first, and every issue has a one-click unsubscribe.

We use your address only to send the brief. See our privacy policy.

See this week’s brief

Further reading

More on Gemini 4 Carbon and Gemini 4 Hydrogen

Articles on Gemini 4 Carbon and Gemini 4 Hydrogen

Related comparisons

Production evaluation

Choosing between Gemini 4 Carbon and Gemini 4 Hydrogen?

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