Skip to main content
BenchLM
Data

Data as of November 12, 2026 · How the score is built

CurrentProprietaryReasoning

Released Nov 12, 20261M contextGoogle DeepMind Gemini 4 Hydrogen model card

Gemini 4 Hydrogen

Decision readingGemini 4 Hydrogen is tracked, but not publicly ranked yet. The profile exposes 5 sourced benchmark rows and leaves unsupported fields blank until a published record exists.

Released Nov 12, 2026 — see all recent releases

Email me when its price, rank or availability changes.

Find alternativesCompare Gemini 4 Hydrogen
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

Unranked

field median 49.6Not eligible for a public rank

Price

$1.50input / $7.50 output

input median $0.60cached $0.075 · batch + cache $0.037 · blended $4.50

Speed

Not measured

field median 92 tok/sTime to first token not measured

Context

1Mtokens

field median 256,000Maximum output length is tracked separately

Strongest published evidence

Published rows are visible, but no category has enough eligible evidence for a comparative rank.

Validate before choosing

5 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.

Source-linked · 5 displayable benchmark rows

Is Gemini 4 Hydrogen right for your job?

Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticWeight 22%3 benchmarksVerified
Score pending
CodingWeight 20%1 benchmarkVerified
Score pending
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalWeight 12%1 benchmarkVerified
Score pending
KnowledgeWeight 12%0 benchmarksNot measured
Not measured
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingWeight 5%0 benchmarksNot measured
Not measured
MathWeight 5%0 benchmarksNot measured
Not measured

5 of 899 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic3/3 verified
  2. Coding1/1 verified
  3. ReasoningNot measured
  4. Multimodal1/1 verified
  5. KnowledgeNot measured
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. MathNot measured
Verified sourceProvisionalNot measured

Benchmark ledger

Every result says who ran the test. For this model, Google ran 7 of 8. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank
Not publicly ranked
Reported by Google
7
Shown with that label
Run by a benchmark
1
The benchmark’s own run
Independent runs
0
None yet
Coding1 row
Coding benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
FrontierCode 2.038.2%

Best verified: Claude Fable 5.2 · 49.1%

Gap10.9 behindRun by FrontierCode 2.0
Cognition: FrontierCode 2.0
Weighted benchmark4% ref. weight
Agentic3 rows
Agentic benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
OSWorld 2.1 OfflineOSWorld 2.1 offline subset (82 tasks)77.6%

Best verified: Claude Fable 5.2 · 89.3%

Gap11.7 behindReported by Google
Google DeepMind: Gemini 4 Hydrogen model card and evaluation methodology
Shown only
MKAMultimodal Knowledge Agent Benchmark53.4%

Best verified: Gemini 4 Hydrogen · 53.4%

GapHighest listedReported by Google
Google DeepMind: Gemini 4 Hydrogen model card and evaluation methodology
Shown only
Terminal-Bench-Science 0.151.4%

Best verified: Claude Mythos 5.2 · 75.3%

Gap23.9 behindReported by Google
Google DeepMind: Gemini 4 Hydrogen model card and evaluation methodology
Shown only
Multimodal1 row
Multimodal benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Chartography (no tools)Chartography without tools66.6%

Best verified: Claude Fable 5.2 · 73.4%

Gap6.8 behindReported by Google
Google DeepMind: Gemini 4 Hydrogen model card and evaluation methodology
Shown only
Other lab-reported results3 rowsAnother metric, split or setting, or a test without a page
Results the lab reported, with the metric and setup, who ran each test, and that none counts toward a rank
Agents' Last Exam v1.1Averaged rubric score · 122-task release, Antigravity CLI, five-hour window; the stored field is the binary pass rate71.6%Reported by Google
Gemini 4 Hydrogen model card
Shown only
Terminal-Bench 4.1Cheating-adjusted average reward · Google's own mini-swe-agent vision harness, five attempts per task, high effort; the stored field follows the official leaderboard57.0%Reported by Google
Gemini 4 Hydrogen model card
Shown only
SWE-sweepSubtask-weighted reward · Google's own run with the Antigravity CLI (agy) 1.4.8, not the public leaderboard13.5%Reported by Google
Gemini 4 Hydrogen model card
Shown only

Outlined bars are lab-reported. Filled bars are benchmark-run or independent. Bars run 0–100; the dark tick marks the best source-verified value.

How we label sourcesAll 5 rows

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Jul 21, 2026

    Gemini 3.6 Flash

    Score 62.4 · $0.75 / $3.75

  2. Aug 13, 2026

    Gemini 3.7 Flash

    Score 66.1 · $0.75 / $3.75

  3. Sep 2, 2026

    Gemini 3.8 Flash

    Score 63.7 · 2.4 points below Gemini 3.7 Flash · $0.75 / $3.75

  4. Nov 12, 2026 · you are here

    Gemini 4 Hydrogen

    Not publicly ranked · $1.5 / $7.5

Base entry

Gemini 4 Carbon · 89.2Gemini 4 Argon · 79.1

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
gemini-4-hydrogenGoogle Gemini 4 Hydrogen model documentation
Context window
1MGoogle Gemini 4 Hydrogen model documentation
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
text, image, video, audio, pdfGoogle Gemini 4 Hydrogen model documentation
Output modalities
textGoogle Gemini 4 Hydrogen model documentation
Parameters
Not disclosed by the provider
Availability
Gemini API · Google AI StudioGoogle Gemini 4 Hydrogen model documentation
Cloud regions
Not tracked yet
Lifecycle
activeGoogle Gemini 4 Hydrogen model documentation
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $0.075 per million cached input tokensGoogle Gemini API pricing
Self-host
Weights are not published
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

We track Gemini 4 Hydrogen, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.

Gemini 4 Hydrogen is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Google lists Gemini 4 Hydrogen (gemini-4-hydrogen) as generally available since November 12, 2026 on the Gemini API and Google AI Studio, on the free and paid tiers, and as the default model for the Antigravity agent in Gemini Managed Agents.

Gemini 4 Hydrogen sits in the Gemini 4 family with Gemini 4 Carbon, Gemini 4 Argon. Its explicit predecessor is Gemini 3.8 Flash. 5 of 899 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Last updated November 12, 2026. Runtime fields remain blank until a sourced snapshot exists.

Questions

How does Gemini 4 Hydrogen perform overall in AI benchmarks?

Gemini 4 Hydrogen has 5 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.

Is Gemini 4 Hydrogen good for coding and programming?

Gemini 4 Hydrogen has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Gemini 4 Hydrogen good for agentic tool use and computer tasks?

Gemini 4 Hydrogen has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Gemini 4 Hydrogen good for multimodal and grounded tasks?

Gemini 4 Hydrogen has source-displayable benchmark coverage for multimodal and grounded tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Which sibling models are related to Gemini 4 Hydrogen?

Gemini 4 Hydrogen belongs to the Gemini 4 family. Related tracked variants include Gemini 4 Carbon, Gemini 4 Argon. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Gemini 4 Hydrogen have full benchmark coverage on BenchLM?

No. Gemini 4 Hydrogen currently has 6 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Gemini 4 Hydrogen?

Gemini 4 Hydrogen has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare Gemini 4 Hydrogen with every tracked model1028 comparisons