Skip to main content
Van Data Team

text model comparison

Gemini 4 Hydrogen vs GPT-6.1 Terra

Gemini 4 Hydrogen and GPT-6.1 Terra are both current text models, from Google and OpenAI. GPT-6.1 Terra is 33% cheaper per 1M input tokens than Gemini 4 Hydrogen, $1 vs $1.50. On Arena WebDev, Gemini 4 Hydrogen scores 1704 Elo and GPT-6.1 Terra 1678 Elo (Arena, measured November 11, 2026). Both accept about 1.05M tokens of context (1,048,576 and 1,050,000).

Higher Arena WebDev
Gemini 4 Hydrogen1704 Elo against 1678 Elo
Lower price per 1M input tokens
GPT-6.1 Terra$1 against $1.50
Longer context window
GPT-6.1 Terra1.05M tokens against 1.05M tokens
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 Hydrogen and GPT-6.1 Terra, 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 HydrogenGPT-6.1 Terra
Price
Price per 1M input tokens$1.50$1 (better)
Price per 1M output tokens$7.50$5 (better)
Independent benchmarks
Arena WebDev1704 Elo (#7 of 45) (better)1678 Elo (#10 of 45)
Arena Text1490 Elo (#7 of 50)Not measured
GPQA DiamondNot measured94.3% (#8 of 40)
FrontierMath Tiers 1-3 (v2)Not measured90.9% (#5 of 39)
SimpleQA VerifiedNot measured57.3% (#15 of 36)
Specs
ProviderGoogleOpenAI
Release dateNovember 12, 2026October 26, 2026
AccessAPI onlyAPI only
Context window1,048,576 tokens1,050,000 tokens
Max output65,536 tokens128,000 tokens
Inputtext, image, audio, videotext, image
Outputtexttext

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

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 Hydrogen and GPT-6.1 Terra. 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 DeepMind, Gemini 4 Hydrogen model card table, November 12, 2026Google DeepMind · 2026-11-15

BenchmarkGemini 4 HydrogenGPT-6.1 Terra
SWE-sweep13.5% (better)5.8%
Agents' Last Exam v1.1score71.6% (better)69.8%
Vending-Bench 2bank balance$14,549 (better)$9,107
OSWorld-2.1offline subset77.6% (better)74.2%
Chartography66.6% (better)63.2%
Terminal-Bench-Science 0.151.4%58.3% (better)

Google's results table from the Gemini 4 Hydrogen model card, every model at its highest thinking setting; Google's methodology is at deepmind.google/models/evals-methodology/gemini-4-hydrogen. Left out here: AutomationBench-AA and HLE-Diamond, which Google takes from the Artificial Analysis leaderboard, and MKA Climb, where every score but Hydrogen's comes from Artificial Analysis.

Charts

Against every current text model

Where Gemini 4 Hydrogen and GPT-6.1 Terra land among the current models of their task, on every independent benchmark, on price and on context.

Where each stands

On Arena WebDev, Gemini 4 Hydrogen ranks #7 and GPT-6.1 Terra #10 of 45 current models. Each bar is the share of current models it beats: on score, price and context.

Gemini 4 Hydrogen and GPT-6.1 Terra among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

Gemini 4 Hydrogen:#7of 50

1,490 Elo · ahead of 88%

GPT-6.1 Terra: Not scored

Arena WebDev

Gemini 4 Hydrogen:#7of 45

1,704 Elo · ahead of 86%

GPT-6.1 Terra:#10of 45

1,678 Elo · ahead of 80%

GPQA Diamond

Gemini 4 Hydrogen: Not scored

GPT-6.1 Terra:#8of 40

94.3% · ahead of 79%

FrontierMath Tiers 1-3 (v2)

Gemini 4 Hydrogen: Not scored

GPT-6.1 Terra:#5of 39

90.9% · ahead of 89%

SimpleQA Verified

Gemini 4 Hydrogen: Not scored

GPT-6.1 Terra:#15of 36

57.3% · ahead of 60%

Price and context

Price per 1M input tokens

Gemini 4 Hydrogen:#32of 58

$1.50 · cheaper than 44%

GPT-6.1 Terra:#25of 58

$1 · cheaper than 56%

Price per 1M output tokens

Gemini 4 Hydrogen:#36of 58

$7.50 · cheaper than 37%

GPT-6.1 Terra:#31of 58

$5 · cheaper than 47%

Context window

Gemini 4 Hydrogen:#12of 68

1.05M tokens · longer than 61%

GPT-6.1 Terra:#1of 68

1.05M tokens · longer than 85%

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

Quality against price

Arena Text · measured November 11, 2026

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 Hydrogen and GPT-6.1 Terra 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 Hydrogen
Quality against price: the data
Arena Text score against price for 42 text models, Gemini 4 Hydrogen and GPT-6.1 Terra 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 Hydrogen costs 1.5 times as much as GPT-6.1 Terra, at each provider's listed rates.

What Gemini 4 Hydrogen and GPT-6.1 Terra cost for the same work, at the rates each provider lists.

  • 10M input and 2M output tokens

    Gemini 4 Hydrogen costs 1.5× as much

    Gemini 4 Hydrogen
    $30
    GPT-6.1 Terra
    $20

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

    Gemini 4 Hydrogen costs 1.5× as much

    Gemini 4 Hydrogen
    $17.18
    GPT-6.1 Terra
    $11.45
Workload or rateGemini 4 HydrogenGPT-6.1 Terra
Example workloads
10M input and 2M output tokens$30$20 (better)
The same, with 9M of the input tokens cached$17.18$11.45 (better)
The same, through the batch API$15Not listed
Other listed rates
1M input tokens, cached$0.075$0.05 (better)
1M input tokens, batch$0.75Not listed
1M output tokens, batch$3.75Not listed
1M input tokens, prompts over 272K tokensNot listed$2
1M output tokens, prompts over 272K tokensNot listed$7.50
1M input tokens, priority$2.70Not listed
1M output tokens, priority$13.50Not listed

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 Hydrogen

Where it leads

  • Higher Arena WebDev score, 1704 Elo vs 1678 Elo
  • Accepts audio and video input
  • Batch pricing, $0.75 input and $3.75 output per 1M 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

GPT-6.1 Terra

Where it leads

  • Lower input and output prices, $1 and $5 vs $1.50 and $7.50 per 1M tokens
  • Longer responses, up to 128,000 vs 65,536 output tokens
  • Cheaper cached input, $0.05 vs $0.075 per 1M tokens

Best for

  • Computer-use and tool-calling agents at half GPT-6.1 Sol's price
  • High-volume reasoning work that stays under the 272K long-context threshold

Watch out for

  • Prompts over 272,000 input tokens bill the whole request at $2 input and $7.50 output per 1M tokens
  • Reads text and images only: audio and video input are not supported
Full GPT-6.1 Terra profile

From benchmark to production

Building on Gemini 4 Hydrogen or GPT-6.1 Terra?

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 Hydrogen vs GPT-6.1 Terra FAQ

Which is cheaper, Gemini 4 Hydrogen or GPT-6.1 Terra?

GPT-6.1 Terra is 33% cheaper per 1M input tokens than Gemini 4 Hydrogen, $1 vs $1.50. For 10M input and 2M output tokens, Gemini 4 Hydrogen costs $30 and GPT-6.1 Terra $20 at standard rates.

Which is cheaper with prompt caching, Gemini 4 Hydrogen or GPT-6.1 Terra?

Gemini 4 Hydrogen charges $0.075 per 1M cached input tokens, 95% below its standard input rate, and GPT-6.1 Terra $0.05, 95% below. With 9M of 10M input tokens cached and 2M output tokens, Gemini 4 Hydrogen costs $17.18 and GPT-6.1 Terra $11.45.

Which scores higher on independent benchmarks, Gemini 4 Hydrogen or GPT-6.1 Terra?

Gemini 4 Hydrogen leads on Arena WebDev, 1704 Elo to 1678 Elo. Scores are independent evaluations, not either vendor's launch figures.

How do Gemini 4 Hydrogen and GPT-6.1 Terra compare in Google DeepMind's own results?

In the Gemini 4 Hydrogen model card table (November 12, 2026), Gemini 4 Hydrogen leads on SWE-sweep, 13.5% to 5.8%; Gemini 4 Hydrogen leads on Agents' Last Exam v1.1 (score), 71.6% to 69.8%; Gemini 4 Hydrogen leads on Vending-Bench 2 (bank balance), $14,549 to $9,107. These are Google DeepMind's figures, not independent measurements.

Which has the larger context window, Gemini 4 Hydrogen or GPT-6.1 Terra?

Both accept about 1.05M tokens of context (1,048,576 and 1,050,000). GPT-6.1 Terra returns up to 128,000 tokens per response, Gemini 4 Hydrogen 65,536.

How do Gemini 4 Hydrogen and GPT-6.1 Terra differ in features?

Gemini 4 Hydrogen takes text, image, audio and video input; GPT-6.1 Terra takes text and image.

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 Hydrogen and GPT-6.1 Terra

Articles on Gemini 4 Hydrogen and GPT-6.1 Terra

Related comparisons

Production evaluation

Choosing between Gemini 4 Hydrogen and GPT-6.1 Terra?

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