What is the IQ of gpt-4-turbo?

gpt-4-turbo has an estimated IQ of 78, which ranks #176 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 gpt-4-turbo best at?

Among the dimensions with published benchmark results, gpt-4-turbo ranks highest in Abstract Reasoning (IQ 76, #179 of 201) and Academic Reasoning (IQ 94, #200 of 203). Its lowest-ranked measured dimension is Mathematical Reasoning (IQ 76, #174 of 176).

What is the EQ of gpt-4-turbo?

gpt-4-turbo 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 gpt-4-turbo. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has gpt-4-turbo been tested on?

gpt-4-turbo has published results on 7 of the 39 benchmarks behind AI IQ's Composite IQ, including SciCode, Chess Puzzles, AIME, GPQA Diamond and FrontierMath Tier 1-3.

How much does gpt-4-turbo cost?

gpt-4-turbo costs $10.00 per million input tokens and $30.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $50.29 per million input-plus-output tokens.

Is gpt-4-turbo open source?

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

Who developed gpt-4-turbo?

gpt-4-turbo was developed by OpenAI, based in the United States.

When was gpt-4-turbo released?

gpt-4-turbo was publicly released on November 6, 2023.

How large is the context window of gpt-4-turbo?

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

How fast is gpt-4-turbo?

In independent measurements, gpt-4-turbo generates about 156 tokens per second, with a typical response time of about 4.8 seconds.

OpenAIReleased Nov 6, 2023

Proprietary

gpt-4-turbo

Its best results are in Abstract Reasoning (#179 of 201) and Academic Reasoning (#200 of 203); weakest in Mathematical Reasoning (#174 of 176). Four of seven dimensions are estimated, because no results are published yet.

Composite IQ ?

#176 of 176 ranked models · ahead of 0%

OpenAI's #24 model, behind gpt-6.1-sol (141)

Effective cost

$50.29/1M

$10 in · $30 out

Speed

156tok/s

5s typical response

Context

Unverified

Not in publisher docs

Evidence

3of 7 dims

7 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

76measured

#179 / 201

1/5

-50.5

Mathematical ReasoningMath

76measured

#174 / 176

2/5

-71

Academic ReasoningAcademic

94measured

#200 / 203

4/6

-41.5

Programmatic ReasoningCoding

76estimated

#177 / 177

0/6

-73.5

Computer UseComputer Use

75estimated

#148 / 176

0/5

-68

ReliabilityReliability

76estimated

#176 / 177

0/6

-58

Knowledge WorkKnowledge Work

76estimated

#176 / 176

0/6

-55.5

gpt-4-turbo95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

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

Abstract Reasoning IQ 76 · measuredBest: #73 of 76 on Chess Puzzles1/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

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

6.0%

#73 / 76

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

Not yet reported

ARC-AGI-3ARC-AGI-2ARC-AGI-1Mystery Game Puzzles

Mathematical Reasoning IQ 76 · measuredBest: #54 of 56 on AIME2/5

BenchmarkScorePercentileRankLeader · source

AIME

15.0%

#54 / 56

Leader gemini-3.1-pro · 98.1%

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

0.7%

#82 / 84

Leader gpt-6-astra · 93.7%
Full source leaderboard reconciliation · Oct 23

Not yet reported

FrontierMath Tier 4ProofBench 1.1MathArena

Academic Reasoning IQ 94 · measuredBest: #150 of 167 on SciCode4/6

BenchmarkScorePercentileRankLeader · source

SciCode

Artificial Analysis model leaderboard · Sep 10

31.9%

#150 / 167

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

GPQA Diamond

Artificial Analysis model leaderboard · Sep 10

49.7%

#143 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis model leaderboard · Sep 10

MMLU-Pro

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

63.7%

#44 / 45

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

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

3.1%

#164 / 167

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

Not yet reported

CritPtMMMU-Pro

Programmatic Reasoning IQ 76 · estimatedNo published results0/6

No published results yet for Programmatic Reasoning. The 76 shown is estimated from gpt-4-turbo's other dimensions and will be replaced as results come in. How estimates work

LiveCodeBenchIOI 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 gpt-4-turbo's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 76 · estimatedNo published results0/6

No published results yet for Reliability. The 76 shown is estimated from gpt-4-turbo'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 76 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 76 shown is estimated from gpt-4-turbo'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: Nov 6, 2023
Developer: OpenAI
Weights: ProprietaryHosted access only
API price: $10 in · $30 outper 1M tokens · full pricing

About this score

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

7/ 39benchmark results

3/ 7dimensions measured

4estimated

1/5Abstract

2/5Math

4/6Academic

0/6Coding

0/5Computer Use

0/6Reliability

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, Computer Use, Reliability and Knowledge Work have no published results yet, so their IQ is estimated from gpt-4-turbo'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 gpt-4-turbo

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

#1 overall

gpt-6.1-sol

IQ141 63 higherEffective cost$6.30 8.0× cheaper

Closest IQ

opus-3

IQ80 2 higherEffective cost$51.65 about the same

IQ117 39 higherEffective cost$50.06 about the same

#2 overall

opus-5.5

IQ141 63 higherEffective cost$35.73 1.4× cheaper

#3 overall

Gemini 4 Argon

IQ140 62 higher

gpt-4-turboComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about gpt-4-turbo, 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 gpt-4-turbo?: gpt-4-turbo has an estimated IQ of 78, which ranks #176 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 gpt-4-turbo best at?: Among the dimensions with published benchmark results, gpt-4-turbo ranks highest in Abstract Reasoning (IQ 76, #179 of 201) and Academic Reasoning (IQ 94, #200 of 203). Its lowest-ranked measured dimension is Mathematical Reasoning (IQ 76, #174 of 176).
What is the EQ of gpt-4-turbo?: gpt-4-turbo 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 gpt-4-turbo. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gpt-4-turbo been tested on?: gpt-4-turbo has published results on 7 of the 39 benchmarks behind AI IQ's Composite IQ, including SciCode, Chess Puzzles, AIME, GPQA Diamond and FrontierMath Tier 1-3.
How much does gpt-4-turbo cost?: gpt-4-turbo costs $10.00 per million input tokens and $30.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $50.29 per million input-plus-output tokens.
Is gpt-4-turbo open source?: No — gpt-4-turbo is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gpt-4-turbo?: gpt-4-turbo was developed by OpenAI, based in the United States.
When was gpt-4-turbo released?: gpt-4-turbo was publicly released on November 6, 2023.
How large is the context window of gpt-4-turbo?: AI IQ hasn't verified an input context limit for gpt-4-turbo from its developer's documentation, so none is listed rather than guessing.
How fast is gpt-4-turbo?: In independent measurements, gpt-4-turbo generates about 156 tokens per second, with a typical response time of about 4.8 seconds.