What is the IQ of grok-3?

grok-3 has an estimated IQ of 90, which ranks #161 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-3 best at?

Among the dimensions with published benchmark results, grok-3 ranks highest in Computer Use (IQ 95, #132 of 176) and Mathematical Reasoning (IQ 97, #133 of 176). Its lowest-ranked measured dimension is Abstract Reasoning (IQ 71, #199 of 201).

What is the EQ of grok-3?

grok-3 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 grok-3. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has grok-3 been tested on?

grok-3 has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Omniscience, SciCode, AIME, AA Long Context Reasoning v1.1 and IFBench.

How much does grok-3 cost?

grok-3 costs $4.00 per million input tokens and $20.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $19.78 per million input-plus-output tokens.

Is grok-3 open source?

No — grok-3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed grok-3?

grok-3 was developed by xAI, based in the United States.

When was grok-3 released?

grok-3 was publicly released on February 17, 2025.

How large is the context window of grok-3?

AI IQ hasn't verified an input context limit for grok-3 from its developer's documentation, so none is listed rather than guessing.

In independent measurements, grok-3 generates about 89 tokens per second, with a typical response time of about 7.3 seconds.

xAIReleased Feb 17, 2025

Proprietary

grok-3

Its best results are in Computer Use (#132 of 176) and Mathematical Reasoning (#133 of 176); weakest in Abstract Reasoning (#199 of 201). Programmatic Reasoning and Knowledge Work are estimated, because no results are published yet.

Composite IQ ?

#161 of 176 ranked models · ahead of 9%

xAI's #7 model, behind grok-4.7 (127)

Effective cost

$19.78/1M

$4 in · $20 out

Speed

89tok/s

7s typical response

Context

Unverified

Not in publisher docs

Evidence

5of 7 dims

12 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

71measured

#199 / 201

2/5

-55.5

Mathematical ReasoningMath

97measured

#133 / 176

1/5

-50

Academic ReasoningAcademic

100measured

#193 / 203

4/6

-35.5

Programmatic ReasoningCoding

79estimated

#172 / 177

0/6

-70.5

Computer UseComputer Use

95measured

#132 / 176

1/5

-48

ReliabilityReliability

100measured

#151 / 177

4/6

-34

Knowledge WorkKnowledge Work

89estimated

#168 / 176

0/6

-42.5

grok-395% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

12 of 39 Composite IQ benchmarks have a published result for grok-3. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 71 · measuredBest: #66 of 68 on ARC-AGI-22/5

BenchmarkScorePercentileRankLeader · source

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

0.0%

#66 / 68

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

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

5.5%

#66 / 68

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

Not yet reported

ARC-AGI-3Chess PuzzlesMystery Game Puzzles

Mathematical Reasoning IQ 97 · measuredBest: #46 of 56 on AIME1/5

BenchmarkScorePercentileRankLeader · source

AIME

58.8%

#46 / 56

Leader gemini-3.1-pro · 98.1%

Not yet reported

FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArena

Academic Reasoning IQ 100 · measuredBest: #137 of 167 on SciCode4/6

BenchmarkScorePercentileRankLeader · source

SciCode

Artificial Analysis model leaderboard · Sep 10

36.8%

#137 / 167

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

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

69.3%

#128 / 147

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

CritPt

Artificial Analysis v4.3.2 · Oct 27

0.0%

#145 / 159

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

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

4.1%

#160 / 167

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

Not yet reported

MMLU-ProMMMU-Pro

Programmatic Reasoning IQ 79 · estimatedNo published results0/6

No published results yet for Programmatic Reasoning. The 79 shown is estimated from grok-3's other dimensions and will be replaced as results come in. How estimates work

LiveCodeBenchIOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 95 · measuredBest: #29 of 29 on Agents' Last Exam1/5

BenchmarkScorePercentileRankLeader · source

Agents' Last Exam

Full source leaderboard reconciliation · Oct 23

4.6%

#29 / 29

Leader opus-5.5 · 38.2%
Full source leaderboard reconciliation · Oct 23

Not yet reported

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent Arena

Reliability IQ 100 · measuredBest: #129 of 158 on AA Omniscience4/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-33.2

#129 / 158

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

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

58.0%

#131 / 154

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

IFBench

Artificial Analysis v4.3.2 · Oct 27

46.9%

#82 / 96

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

SimpleQA Verified

Epoch AI SimpleQA Verified · Sep 22

21.1%

#72 / 80

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

Not yet reported

BullshitBench v2FACTS Grounding

Knowledge Work IQ 89 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 89 shown is estimated from grok-3'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: Feb 17, 2025
Developer: xAI
Weights: ProprietaryHosted access only
API price: $4 in · $20 outper 1M tokens · full pricing

About this score

How much of grok-3's IQ is measured, and how the rest is estimated.

12/ 39benchmark results

5/ 7dimensions measured

2estimated

2/5Abstract

1/5Math

4/6Academic

0/6Coding

1/5Computer Use

4/6Reliability

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

Programmatic Reasoning and Knowledge Work have no published results yet, so their IQ is estimated from grok-3's other dimensions.

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-3

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

#1 overall

gpt-6.1-sol

IQ141 51 higherEffective cost$6.30 3.1× cheaper

xAI #1

grok-4.7

IQ127 37 higherEffective cost$21.89 1.1× pricier

Closest IQ

qwen3.5-4b

IQ90 same IQEffective cost$0.078 252.6× cheaper

Most similar profile

mistral-large-3

IQ91 1 higherEffective cost$0.44 44.9× cheaper

Similar price

kimi-k3

IQ127 37 higherEffective cost$20.20 about the same

#2 overall

opus-5.5

IQ141 51 higherEffective cost$35.73 1.8× pricier

grok-3Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about grok-3, 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-3?: grok-3 has an estimated IQ of 90, which ranks #161 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-3 best at?: Among the dimensions with published benchmark results, grok-3 ranks highest in Computer Use (IQ 95, #132 of 176) and Mathematical Reasoning (IQ 97, #133 of 176). Its lowest-ranked measured dimension is Abstract Reasoning (IQ 71, #199 of 201).
What is the EQ of grok-3?: grok-3 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 grok-3. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has grok-3 been tested on?: grok-3 has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Omniscience, SciCode, AIME, AA Long Context Reasoning v1.1 and IFBench.
How much does grok-3 cost?: grok-3 costs $4.00 per million input tokens and $20.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $19.78 per million input-plus-output tokens.
Is grok-3 open source?: No — grok-3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed grok-3?: grok-3 was developed by xAI, based in the United States.
When was grok-3 released?: grok-3 was publicly released on February 17, 2025.
How large is the context window of grok-3?: AI IQ hasn't verified an input context limit for grok-3 from its developer's documentation, so none is listed rather than guessing.
How fast is grok-3?: In independent measurements, grok-3 generates about 89 tokens per second, with a typical response time of about 7.3 seconds.