What is the IQ of Gemini 4 Hydrogen?

Gemini 4 Hydrogen has an estimated IQ of 131, which ranks #16 out of 180 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.

What is Gemini 4 Hydrogen best at?

Among the dimensions with published benchmark results, Gemini 4 Hydrogen ranks highest in Knowledge Work (IQ 133, #7 of 180) and Programmatic Reasoning (IQ 143, #14 of 181).

What is the EQ of Gemini 4 Hydrogen?

Gemini 4 Hydrogen doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for Gemini 4 Hydrogen. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has Gemini 4 Hydrogen been tested on?

Gemini 4 Hydrogen has published results on 4 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, GDP.pdf, Terminal-Bench 4.0 and AA-Briefcase v1.1 Elo.

How much does Gemini 4 Hydrogen cost?

Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $15.92 per million input-plus-output tokens.

Is Gemini 4 Hydrogen open source?

No — Gemini 4 Hydrogen is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed Gemini 4 Hydrogen?

Gemini 4 Hydrogen was developed by Google, based in the United States.

When was Gemini 4 Hydrogen released?

Gemini 4 Hydrogen was publicly released on November 12, 2026.

How large is the context window of Gemini 4 Hydrogen?

AI IQ hasn't verified an input context limit for Gemini 4 Hydrogen from its developer's documentation, so none is listed rather than guessing.

How fast is Gemini 4 Hydrogen?

AI IQ doesn't have independent speed measurements for Gemini 4 Hydrogen yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.

GoogleReleased Nov 12, 2026

NewProprietary

Gemini 4 Hydrogen

Strongest in Knowledge Work (#7 of 180) and Programmatic Reasoning (#14 of 181). Five of seven dimensions are estimated, because no results are published yet.

Composite IQ ?

131

#16 of 180 ranked models · ahead of 92%

Google's #3 model, behind Gemini 4 Carbon (142)

Effective cost

$15.92/1M

$1.50 in · $7.50 out

Speed

Not measured

No speed data yet

Context

Unverified

Not in publisher docs

Evidence

2of 7 dims

4 of 39 benchmarks

Compare with fable-5.2API pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

MeasuredEstimated95% range

#1 in dimensionTop-10 median

IQ dimensions

Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.

DimensionIQPosition · 70–160RankEvidencevs Top 10

Abstract ReasoningAbstract

126estimated

#10 / 209

0/5

-6

Mathematical ReasoningMath

127estimated

#42 / 180

0/5

-20

Academic ReasoningAcademic

132estimated

#20 / 211

0/6

-3

Programmatic ReasoningCoding

143measured

#14 / 181

1/6

-7

Computer UseComputer Use

124estimated

#35 / 180

0/5

-20.5

ReliabilityReliability

130estimated

#11 / 181

0/6

-4.5

Knowledge WorkKnowledge Work

133measured

#7 / 180

3/6

Gemini 4 Hydrogen95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

4 of 39 Composite IQ benchmarks have a published result for Gemini 4 Hydrogen. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 126 · estimatedNo published results0/5

No published results yet for Abstract Reasoning. The 126 shown is estimated from Gemini 4 Hydrogen's other dimensions and will be replaced as results come in. How estimates work

ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles

Mathematical Reasoning IQ 127 · estimatedNo published results0/5

No published results yet for Mathematical Reasoning. The 127 shown is estimated from Gemini 4 Hydrogen's other dimensions and will be replaced as results come in. How estimates work

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME

Academic Reasoning IQ 132 · estimatedNo published results0/6

No published results yet for Academic Reasoning. The 132 shown is estimated from Gemini 4 Hydrogen's other dimensions and will be replaced as results come in. How estimates work

Humanity's Last ExamGPQA DiamondCritPtSciCodeMMLU-ProMMMU-Pro

Programmatic Reasoning IQ 143 · measuredBest: #11 of 109 on Terminal-Bench 4.01/6

BenchmarkScorePercentileRankLeader · source

Terminal-Bench 4.0

Artificial Analysis v5.0.1 · Nov 13

53.5%

#11 / 109

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v5.0.1 · Nov 13

Not yet reported

LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 124 · estimatedNo published results0/5

No published results yet for Computer Use. The 124 shown is estimated from Gemini 4 Hydrogen's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 130 · estimatedNo published results0/6

No published results yet for Reliability. The 130 shown is estimated from Gemini 4 Hydrogen's other dimensions and will be replaced as results come in. How estimates work

SimpleQA VerifiedaaOmniscienceBullshitBench v2IFBenchAA Long Context Reasoning v1.1FACTS Grounding

Knowledge Work IQ 133 · measuredBest: #4 of 112 on AutomationBench-AA3/6

BenchmarkScorePercentileRankLeader · source

AutomationBench-AA

Artificial Analysis v5.0.1 · Nov 13

76.1%

#4 / 112

Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13

GDP.pdf

Artificial Analysis v5.0.1 · Nov 13

27.6%

#8 / 111

Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13

AA-Briefcase v1.1 Elo

Artificial Analysis v5.0.1 · Nov 13

1,567

#17 / 116

Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13

Not yet reported

GDPval-AA v2.1AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Facts from the publisher's announcement and documentation.

Released: Nov 12, 2026
Developer: Google
Access: Generally available through the Gemini API and Google AI Studio, including the API free tier; also rolling out in eligible Google products.
Weights: ProprietaryHosted access only
Inputs: textimagevideoaudio
Context: Not published1,000,000 tokens shared by input and output; available input depends on output length.
API price: $1.50 in · $7.50 outper 1M tokens · full pricing

What Google says

Google announced Gemini 4 Hydrogen on November 12, 2026 for everyday coding and agentic workflows.
The stable Gemini API identifier is gemini-4-hydrogen, with low, medium, high and xhigh thinking settings.
Google documents a unified one-million-token context budget and paid Standard pricing of $1.50 input and $7.50 output per million tokens.

Limitations

The one-million-token context budget is shared by input and output, so it is not a separate input allowance.
Free tier usage is subject to rate limits; publisher benchmark claims are not imported as independent measurements.

Publisher statements, not AI IQ measurements.

Sourcesblog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen ai.google.dev/gemini-api/docs/changelogai.google.dev/gemini-api/docs/pricing

About this score

How much of Gemini 4 Hydrogen's IQ is measured, and how the rest is estimated.

4/ 39benchmark results

2/ 7dimensions measured

5estimated

0/5Abstract

0/5Math

0/6Academic

1/6Coding

0/5Computer Use

0/6Reliability

3/6Knowledge Work

Bar height = share of benchmarks with resultsEstimatedNo score

Measured results are shown as published

Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.

Estimates fill the gaps

Abstract Reasoning, Mathematical Reasoning, Academic Reasoning, Computer Use and Reliability have no published results yet, so their IQ is estimated from Gemini 4 Hydrogen's other dimensions. Missing benchmarks can also draw on its predecessor, Gemini 3.8 Flash; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.

A missing result is not a zero

Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.

Read the scoring methodology →

Compare Gemini 4 Hydrogen

Side-by-side pages for the models it is most often weighed against.

#1 overall

fable-5.2

IQ144 13 higherEffective cost$73.69 4.6× pricier

Predecessor

Gemini 3.8 Flash

IQ129 2 lowerEffective cost$7.96 2.0× cheaper

DeepSeek V4.1 Flash 1017

IQ128 3 lowerEffective cost$2.38 6.7× cheaper

Similar price

gpt-5.6-terra

IQ130 1 lowerEffective cost$13.78 1.2× cheaper

Gemini 4 HydrogenComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about Gemini 4 Hydrogen, drawn from the same data as the rest of this page.

How AI IQ scores models →Get this data from the API →

What is the IQ of Gemini 4 Hydrogen?: Gemini 4 Hydrogen has an estimated IQ of 131, which ranks #16 out of 180 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
What is Gemini 4 Hydrogen best at?: Among the dimensions with published benchmark results, Gemini 4 Hydrogen ranks highest in Knowledge Work (IQ 133, #7 of 180) and Programmatic Reasoning (IQ 143, #14 of 181).
What is the EQ of Gemini 4 Hydrogen?: Gemini 4 Hydrogen doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for Gemini 4 Hydrogen. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Gemini 4 Hydrogen been tested on?: Gemini 4 Hydrogen has published results on 4 of the 39 benchmarks behind AI IQ's Composite IQ, including AutomationBench-AA, GDP.pdf, Terminal-Bench 4.0 and AA-Briefcase v1.1 Elo.
How much does Gemini 4 Hydrogen cost?: Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $15.92 per million input-plus-output tokens.
Is Gemini 4 Hydrogen open source?: No — Gemini 4 Hydrogen is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed Gemini 4 Hydrogen?: Gemini 4 Hydrogen was developed by Google, based in the United States.
When was Gemini 4 Hydrogen released?: Gemini 4 Hydrogen was publicly released on November 12, 2026.
How large is the context window of Gemini 4 Hydrogen?: AI IQ hasn't verified an input context limit for Gemini 4 Hydrogen from its developer's documentation, so none is listed rather than guessing.
How fast is Gemini 4 Hydrogen?: AI IQ doesn't have independent speed measurements for Gemini 4 Hydrogen yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.