What is the IQ of gpt-5.4-nano?

gpt-5.4-nano has an estimated IQ of 106, which ranks #95 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-5.4-nano best at?

Among the dimensions with published benchmark results, gpt-5.4-nano ranks highest in Mathematical Reasoning (IQ 113, #82 of 176) and Academic Reasoning (IQ 120, #102 of 203). Its lowest-ranked measured dimension is Reliability (IQ 102, #141 of 177).

What is the EQ of gpt-5.4-nano?

gpt-5.4-nano 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-5.4-nano. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has gpt-5.4-nano been tested on?

gpt-5.4-nano has published results on 24 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, LiveCodeBench, CritPt, Chess Puzzles and SciCode.

How much does gpt-5.4-nano cost?

gpt-5.4-nano costs $0.20 per million input tokens and $1.25 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $1.63 per million input-plus-output tokens.

Is gpt-5.4-nano open source?

No — gpt-5.4-nano is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed gpt-5.4-nano?

gpt-5.4-nano was developed by OpenAI, based in the United States.

When was gpt-5.4-nano released?

gpt-5.4-nano was publicly released on March 17, 2026.

How large is the context window of gpt-5.4-nano?

gpt-5.4-nano supports a context window of 400,000 tokens — the amount of text it can consider in a single request.

How fast is gpt-5.4-nano?

In independent measurements, gpt-5.4-nano generates about 165 tokens per second, with a typical response time of about 81 seconds.

OpenAIReleased Mar 17, 2026

Proprietary

gpt-5.4-nano

Its best results are in Mathematical Reasoning (#82 of 176) and Academic Reasoning (#102 of 203); weakest in Reliability (#141 of 177). All seven dimensions are measured.

Composite IQ ?

106

#95 of 176 ranked models · ahead of 46%

OpenAI's #16 model, behind gpt-6.1-sol (141)

Effective cost

$1.63/1M

$0.20 in · $1.25 out

Speed

165tok/s

81s typical response

Context

400Ktokens

400,000 tokens in

Evidence

7of 7 dims

24 of 39 benchmarks

Compare with gpt-6.1-solAPI pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

Measured95% 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

85measured

#137 / 201

4/5

-41.5

Mathematical ReasoningMath

113measured

#82 / 176

3/5

-34

Academic ReasoningAcademic

120measured

#102 / 203

5/6

-15.5

Programmatic ReasoningCoding

110measured

#94 / 177

2/6

-39.5

Computer UseComputer Use

103measured

#108 / 176

1/5

-40

ReliabilityReliability

102measured

#141 / 177

5/6

-32

Knowledge WorkKnowledge Work

109measured

#93 / 176

4/6

-22.5

gpt-5.4-nano95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

24 of 39 Composite IQ benchmarks have a published result for gpt-5.4-nano. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 85 · measuredBest: #33 of 76 on Chess Puzzles4/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

30.0%

#33 / 76

Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 14

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

5.7%

#54 / 68

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

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

51.5%

#55 / 68

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

Mystery Game Puzzles

Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23

6.0%

#53 / 55

Leader gpt-6-astra · 84.0%
Full source leaderboard reconciliation vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 23

Not yet reported

ARC-AGI-3

Mathematical Reasoning IQ 113 · measuredBest: #28 of 56 on AIME3/5

BenchmarkScorePercentileRankLeader · source

AIME

88.8%

#28 / 56

Leader gemini-3.1-pro · 98.1%

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

44.9%

#51 / 84

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

FrontierMath Tier 4

Full source leaderboard reconciliation · Oct 23

12.2%

#54 / 72

Leader gpt-6.1-sol · 100%
Full source leaderboard reconciliation · Oct 23

Not yet reported

ProofBench 1.1MathArena

Academic Reasoning IQ 120 · measuredBest: #65 of 159 on CritPt5/6

BenchmarkScorePercentileRankLeader · source

CritPt

Artificial Analysis v4.3.2 · Oct 27

9.3%

#65 / 159

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

SciCode

Artificial Analysis v4.3.2 · Oct 27

47.2%

#79 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

28.3%

#96 / 167

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

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

81.7%

#97 / 147

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

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 27

65.4%

#74 / 89

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

Not yet reported

MMLU-Pro

Programmatic Reasoning IQ 110 · measuredBest: #22 of 61 on LiveCodeBench2/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

84.0%

#22 / 61

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

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 27

0.5%

#65 / 104

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

IOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 103 · measuredBest: #24 of 24 on OSWorld-Verified1/5

BenchmarkScorePercentileRankLeader · source

OSWorld-Verified

Full source leaderboard reconciliation · Oct 23

39.0%

#24 / 24

Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23

Not yet reported

BrowseCompMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 102 · measuredBest: #19 of 96 on IFBench5/6

BenchmarkScorePercentileRankLeader · source

IFBench

Artificial Analysis v4.3.2 · Oct 27

75.9%

#19 / 96

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

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 27

76.7%

#80 / 154

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

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-29.5

#123 / 158

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

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

10.0%

#74 / 83

Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

11.7%

#79 / 80

Leader Gemini 4 Argon · 76.0%
Full source leaderboard reconciliation · Oct 23

Not yet reported

FACTS Grounding

Knowledge Work IQ 109 · measuredBest: #78 of 124 on GDPval-AA v2.1 normalized score4/6

BenchmarkScorePercentileRankLeader · source

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 20

22.4%

#78 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20

GDP.pdf

Artificial Analysis v4.3.2 · Oct 27

7.8%

#70 / 106

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 27

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 27

6.0%

#74 / 106

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 27

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 27

673

#80 / 111

Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27

Not yet reported

AA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: Mar 17, 2026
Developer: OpenAI
Weights: ProprietaryHosted access only
Context: 400,000 tokens
API price: $0.20 in · $1.25 outper 1M tokens · full pricing

About this score

How much of gpt-5.4-nano's IQ is measured, and how the rest is estimated.

24/ 39benchmark results

7/ 7dimensions measured

0estimated

4/5Abstract

3/5Math

5/6Academic

2/6Coding

1/5Computer Use

5/6Reliability

4/6Knowledge 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.

How gaps are handled

Every dimension has at least one published result. Missing benchmarks can also draw on its predecessor, GPT 5 Nano; 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 gpt-5.4-nano

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

#1 overall

gpt-6.1-sol

IQ141 35 higherEffective cost$6.30 3.9× pricier

Predecessor

gpt-5-nano

IQ95 11 lowerEffective cost$0.273 6.0× cheaper

Closest IQ

Ember 1

IQ106 same IQEffective cost$15.87 9.7× pricier

Most similar profile

kat-coder-pro-v1

IQ103 3 lowerEffective cost$1.27 1.3× cheaper

Similar price

Qwen3.8 Flash

IQ115 9 higherEffective cost$1.61 about the same

#2 overall

opus-5.5

IQ141 35 higherEffective cost$35.73 21.9× pricier

gpt-5.4-nanoComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about gpt-5.4-nano, 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-5.4-nano?: gpt-5.4-nano has an estimated IQ of 106, which ranks #95 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-5.4-nano best at?: Among the dimensions with published benchmark results, gpt-5.4-nano ranks highest in Mathematical Reasoning (IQ 113, #82 of 176) and Academic Reasoning (IQ 120, #102 of 203). Its lowest-ranked measured dimension is Reliability (IQ 102, #141 of 177).
What is the EQ of gpt-5.4-nano?: gpt-5.4-nano 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-5.4-nano. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gpt-5.4-nano been tested on?: gpt-5.4-nano has published results on 24 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, LiveCodeBench, CritPt, Chess Puzzles and SciCode.
How much does gpt-5.4-nano cost?: gpt-5.4-nano costs $0.20 per million input tokens and $1.25 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $1.63 per million input-plus-output tokens.
Is gpt-5.4-nano open source?: No — gpt-5.4-nano is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gpt-5.4-nano?: gpt-5.4-nano was developed by OpenAI, based in the United States.
When was gpt-5.4-nano released?: gpt-5.4-nano was publicly released on March 17, 2026.
How large is the context window of gpt-5.4-nano?: gpt-5.4-nano supports a context window of 400,000 tokens — the amount of text it can consider in a single request.
How fast is gpt-5.4-nano?: In independent measurements, gpt-5.4-nano generates about 165 tokens per second, with a typical response time of about 81 seconds.