What is the IQ of grok-4?

grok-4 has an estimated IQ of 99, which ranks #132 out of 176 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 grok-4 best at?

Among the dimensions with published benchmark results, grok-4 ranks highest in Programmatic Reasoning (IQ 110, #93 of 177) and Reliability (IQ 112, #94 of 177). Its lowest-ranked measured dimension is Mathematical Reasoning (IQ 103, #118 of 176).

What is the EQ of grok-4?

grok-4 has an estimated EQ of 99. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.

Which benchmarks has grok-4 been tested on?

grok-4 has published results on 19 of the 39 benchmarks behind AI IQ's Composite IQ, including MMLU-Pro, AA Omniscience, GPQA Diamond, LiveCodeBench and AIME.

How much does grok-4 cost?

grok-4 costs $3.00 per million input tokens and $15.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $34.90 per million input-plus-output tokens.

Is grok-4 open source?

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

Who developed grok-4?

grok-4 was developed by xAI, based in the United States.

When was grok-4 released?

grok-4 was publicly released on July 9, 2025.

How large is the context window of grok-4?

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

In independent measurements, grok-4 generates about 78 tokens per second, with a typical response time of about 16 seconds.

xAIReleased Jul 9, 2025

Proprietary

grok-4

Its best results are in Programmatic Reasoning (#93 of 177) and Reliability (#94 of 177); weakest in Mathematical Reasoning (#118 of 176). Computer Use and Knowledge Work are estimated, because no results are published yet.

Composite IQ ?

#132 of 176 ranked models · ahead of 25%

xAI's #6 model, behind grok-4.7 (127)

Effective cost

$34.90/1M

$3 in · $15 out

Speed

78tok/s

16s typical response

Context

Unverified

Not in publisher docs

Evidence

5of 7 dims

19 of 39 benchmarks

Compare with gpt-6.1-solAPI 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

87measured

#117 / 201

3/5

-39.5

Mathematical ReasoningMath

103measured

#118 / 176

4/5

-44

Academic ReasoningAcademic

118measured

#115 / 203

6/6

-17.5

Programmatic ReasoningCoding

110measured

#93 / 177

1/6

-39.5

Computer UseComputer Use

75estimated

#151 / 176

0/5

-68

ReliabilityReliability

112measured

#94 / 177

5/6

-22

Knowledge WorkKnowledge Work

90estimated

#159 / 176

0/6

-41.5

grok-495% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

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

Abstract Reasoning IQ 87 · measuredBest: #36 of 76 on Chess Puzzles3/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 15

28.0%

#36 / 76

Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 15

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

66.7%

#47 / 68

Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Oct 23

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

16.0%

#48 / 68

Leader gpt-6-astra · 95.0%
Full source leaderboard reconciliation · Oct 23

Not yet reported

ARC-AGI-3Mystery Game Puzzles

Mathematical Reasoning IQ 103 · measuredBest: #25 of 56 on AIME4/5

BenchmarkScorePercentileRankLeader · source

AIME

90.6%

#25 / 56

Leader gemini-3.1-pro · 98.1%

MathArena

Full source leaderboard reconciliation · Oct 28

14.7%

#51 / 64

Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 28

FrontierMath Tier 1-3

Epoch AI FrontierMath Tiers 1-3 v2 · Sep 22

19.7%

#74 / 84

Leader gpt-6-astra · 93.7%
Epoch AI FrontierMath Tiers 1-3 v2 · Sep 22

FrontierMath Tier 4

Epoch AI FrontierMath Tier 4 v2 · Sep 22

2.1%

#66 / 72

Leader gpt-6.1-sol · 100%
Epoch AI FrontierMath Tier 4 v2 · Sep 22

Not yet reported

ProofBench 1.1

Academic Reasoning IQ 118 · measuredBest: #13 of 45 on MMLU-Pro6/6

BenchmarkScorePercentileRankLeader · source

MMLU-Pro

TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

86.6%

#13 / 45

Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

87.7%

#62 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27

SciCode

Artificial Analysis model leaderboard · Sep 10

46.0%

#87 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis model leaderboard · Sep 10

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

26.7%

#101 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27

CritPt

Artificial Analysis v4.3.2 · Oct 27

2.0%

#105 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 27

68.8%

#71 / 89

Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27

Programmatic Reasoning IQ 110 · measuredBest: #26 of 61 on LiveCodeBench1/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

83.3%

#26 / 61

Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4

Not yet reported

IOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 75 · estimatedNo published results0/5

No published results yet for Computer Use. The 75 shown is estimated from grok-4's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 112 · measuredBest: #61 of 158 on AA Omniscience5/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

2.1

#61 / 158

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27

SimpleQA Verified

Epoch AI SimpleQA Verified · Sep 22

47.9%

#36 / 80

Leader Gemini 4 Argon · 76.0%
Epoch AI SimpleQA Verified · Sep 22

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

68.0%

#118 / 154

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27

IFBench

Artificial Analysis v4.3.2 · Oct 27

53.7%

#77 / 96

Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27

FACTS Grounding

Full source leaderboard reconciliation · Oct 23

54.7%

#32 / 36

Leader gpt-6-sol · 85.2%
Full source leaderboard reconciliation · Oct 23

Not yet reported

BullshitBench v2

Knowledge Work IQ 90 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 90 shown is estimated from grok-4's other dimensions and will be replaced as results come in. How estimates work

AA-Briefcase v1.1GDPval-AA v2.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: Jul 9, 2025
Developer: xAI
Weights: ProprietaryHosted access only
API price: $3 in · $15 outper 1M tokens · full pricing

About this score

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

19/ 39benchmark results

5/ 7dimensions measured

2estimated

3/5Abstract

4/5Math

6/6Academic

1/6Coding

0/5Computer Use

5/6Reliability

0/6Knowledge 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

Computer Use and Knowledge Work have no published results yet, so their IQ is estimated from grok-4's other dimensions. Missing benchmarks can also draw on its predecessor, Grok 2; 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 grok-4

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

#1 overall

gpt-6.1-sol

IQ141 42 higherEffective cost$6.30 5.5× cheaper

IQ127 28 higherEffective cost$21.89 1.6× cheaper

Closest IQ

hy3

IQ99 same IQEffective cost$0.654 53.3× cheaper

Most similar profile

opus-4.1

IQ100 1 higherEffective cost$51.65 1.5× pricier

Similar price

gpt-6-astra

IQ140 41 higherEffective cost$34.22 about the same

grok-4Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about grok-4, 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 grok-4?: grok-4 has an estimated IQ of 99, which ranks #132 out of 176 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 grok-4 best at?: Among the dimensions with published benchmark results, grok-4 ranks highest in Programmatic Reasoning (IQ 110, #93 of 177) and Reliability (IQ 112, #94 of 177). Its lowest-ranked measured dimension is Mathematical Reasoning (IQ 103, #118 of 176).
What is the EQ of grok-4?: grok-4 has an estimated EQ of 99. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
Which benchmarks has grok-4 been tested on?: grok-4 has published results on 19 of the 39 benchmarks behind AI IQ's Composite IQ, including MMLU-Pro, AA Omniscience, GPQA Diamond, LiveCodeBench and AIME.
How much does grok-4 cost?: grok-4 costs $3.00 per million input tokens and $15.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $34.90 per million input-plus-output tokens.
Is grok-4 open source?: No — grok-4 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed grok-4?: grok-4 was developed by xAI, based in the United States.
When was grok-4 released?: grok-4 was publicly released on July 9, 2025.
How large is the context window of grok-4?: AI IQ hasn't verified an input context limit for grok-4 from its developer's documentation, so none is listed rather than guessing.
How fast is grok-4?: In independent measurements, grok-4 generates about 78 tokens per second, with a typical response time of about 16 seconds.