What is the IQ of o3?

o3 has an estimated IQ of 103, which ranks #112 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.

Among the dimensions with published benchmark results, o3 ranks highest in Abstract Reasoning (IQ 92, #93 of 201) and Programmatic Reasoning (IQ 112, #86 of 177). Its lowest-ranked measured dimension is Computer Use (IQ 97, #125 of 176).

What is the EQ of o3?

o3 has an estimated EQ of 113. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.

Which benchmarks has o3 been tested on?

o3 has published results on 22 of the 39 benchmarks behind AI IQ's Composite IQ, including Chess Puzzles, LiveCodeBench, SimpleQA Verified, IFBench and MMLU-Pro.

How much does o3 cost?

o3 costs $2.00 per million input tokens and $8.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $8.72 per million input-plus-output tokens.

No — o3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

o3 was developed by OpenAI, based in the United States.

When was o3 released?

o3 was publicly released on April 16, 2025.

How large is the context window of o3?

o3 supports a context window of 200,000 tokens — the amount of text it can consider in a single request.

In independent measurements, o3 generates about 166 tokens per second, with a typical response time of about 9.6 seconds.

OpenAIReleased Apr 16, 2025

Proprietary

o3

Its best results are in Abstract Reasoning (#93 of 201) and Programmatic Reasoning (#86 of 177); weakest in Computer Use (#125 of 176). Knowledge Work is estimated, because no results are published yet.

Composite IQ ?

103

#112 of 176 ranked models · ahead of 37%

OpenAI's #17 model, behind gpt-6.1-sol (141)

Effective cost

$8.72/1M

$2 in · $8 out

Speed

166tok/s

10s typical response

Context

200Ktokens

200,000 tokens in

Evidence

6of 7 dims

22 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

92measured

#93 / 201

4/5

-34.5

Mathematical ReasoningMath

106measured

#104 / 176

4/5

-41

Academic ReasoningAcademic

115measured

#121 / 203

6/6

-20.5

Programmatic ReasoningCoding

112measured

#86 / 177

1/6

-37.5

Computer UseComputer Use

97measured

#125 / 176

1/5

-46

ReliabilityReliability

110measured

#107 / 177

6/6

-24

Knowledge WorkKnowledge Work

90estimated

#164 / 176

0/6

-41.5

o395% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

22 of 39 Composite IQ benchmarks have a published result for o3. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 92 · measuredBest: #24 of 76 on Chess Puzzles4/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

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

38.0%

#24 / 76

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

Mystery Game Puzzles

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

29.0%

#29 / 55

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

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

60.8%

#52 / 68

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

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

6.5%

#53 / 68

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

Not yet reported

ARC-AGI-3

Mathematical Reasoning IQ 106 · measuredBest: #34 of 56 on AIME4/5

BenchmarkScorePercentileRankLeader · source

AIME

85.3%

#34 / 56

Leader gemini-3.1-pro · 98.1%

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

33.3%

#62 / 84

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

MathArena

Full source leaderboard reconciliation · Oct 28

13.8%

#53 / 64

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

FrontierMath Tier 4

Epoch AI FrontierMath Tier 4 v2 · Sep 22

2.1%

#68 / 72

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

Not yet reported

ProofBench 1.1

Academic Reasoning IQ 115 · measuredBest: #22 of 45 on MMLU-Pro6/6

BenchmarkScorePercentileRankLeader · source

MMLU-Pro

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

85.3%

#22 / 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

82.7%

#94 / 147

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

SciCode

Artificial Analysis model leaderboard · Sep 10

41.0%

#115 / 167

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

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

20.1%

#119 / 167

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

CritPt

Artificial Analysis v4.3.2 · Oct 27

1.1%

#115 / 159

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

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 27

70.1%

#67 / 89

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

Programmatic Reasoning IQ 112 · measuredBest: #23 of 61 on LiveCodeBench1/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

83.9%

#23 / 61

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

Not yet reported

IOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 97 · measuredBest: #38 of 43 on BrowseComp1/5

BenchmarkScorePercentileRankLeader · source

BrowseComp

Full source leaderboard reconciliation · Oct 19

49.7%

#38 / 43

Leader Kimi K3.1 Pro · 92.1%
Full source leaderboard reconciliation · Oct 19

Not yet reported

OSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 110 · measuredBest: #32 of 80 on SimpleQA Verified6/6

BenchmarkScorePercentileRankLeader · source

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

49.4%

#32 / 80

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

IFBench

Artificial Analysis v4.3.2 · Oct 27

71.4%

#40 / 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

74.7%

#88 / 154

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

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

-15.5

#103 / 158

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

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

26.0%

#59 / 83

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

FACTS Grounding

Full source leaderboard reconciliation · Oct 23

36.2%

#34 / 36

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

Knowledge Work IQ 90 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 90 shown is estimated from o3'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: Apr 16, 2025
Developer: OpenAI
Weights: ProprietaryHosted access only
Context: 200,000 tokens
API price: $2 in · $8 outper 1M tokens · full pricing

About this score

How much of o3's IQ is measured, and how the rest is estimated.

22/ 39benchmark results

6/ 7dimensions measured

1estimated

4/5Abstract

4/5Math

6/6Academic

1/6Coding

1/5Computer Use

6/6Reliability

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

Knowledge Work has no published results yet, so its IQ is estimated from o3's other dimensions. Missing benchmarks can also draw on its predecessors, O1 and GPT 4o; 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 o3

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

#1 overall

gpt-6.1-sol

IQ141 38 higherEffective cost$6.30 1.4× cheaper

Predecessor

IQ95 8 lowerEffective cost$74.68 8.6× pricier

IQ126 23 higherEffective cost$8.88 about the same

#2 overall

opus-5.5

IQ141 38 higherEffective cost$35.73 4.1× pricier

o3Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about o3, 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 o3?: o3 has an estimated IQ of 103, which ranks #112 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 o3 best at?: Among the dimensions with published benchmark results, o3 ranks highest in Abstract Reasoning (IQ 92, #93 of 201) and Programmatic Reasoning (IQ 112, #86 of 177). Its lowest-ranked measured dimension is Computer Use (IQ 97, #125 of 176).
What is the EQ of o3?: o3 has an estimated EQ of 113. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
Which benchmarks has o3 been tested on?: o3 has published results on 22 of the 39 benchmarks behind AI IQ's Composite IQ, including Chess Puzzles, LiveCodeBench, SimpleQA Verified, IFBench and MMLU-Pro.
How much does o3 cost?: o3 costs $2.00 per million input tokens and $8.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $8.72 per million input-plus-output tokens.
Is o3 open source?: No — o3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed o3?: o3 was developed by OpenAI, based in the United States.
When was o3 released?: o3 was publicly released on April 16, 2025.
How large is the context window of o3?: o3 supports a context window of 200,000 tokens — the amount of text it can consider in a single request.
How fast is o3?: In independent measurements, o3 generates about 166 tokens per second, with a typical response time of about 9.6 seconds.