OpenAIReleased Feb 5, 2026
Proprietary
gpt-5.3-codex
Strongest in Academic Reasoning (#48 of 203) and Programmatic Reasoning (#52 of 177); weakest in Computer Use (#80 of 176). Abstract Reasoning and Mathematical Reasoning are estimated, because no results are published yet.
Composite IQ ?
112
Effective cost
$18.57/1M
$1.75 in · $14 out
Speed
103tok/s
61s typical response
Context
400Ktokens
400,000 tokens in
Evidence
5of 7 dims
13 of 39 benchmarks
IQ profile
Seven dimensions, averaged equally into Composite IQ
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
gpt-5.3-codex95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human
Benchmark results
13 of 39 Composite IQ benchmarks have a published result for gpt-5.3-codex. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 84 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 84 shown is estimated from gpt-5.3-codex's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 103 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 103 shown is estimated from gpt-5.3-codex's other dimensions and will be replaced as results come in. How estimates work
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 129 · measuredBest: #32 of 147 on GPQA Diamond5/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v4.3.2 · Oct 27
91.5%
#32 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
42.5%
#37 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
16.9%
#39 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis model leaderboard · Sep 10
53.2%
#47 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis model leaderboard · Sep 10
Artificial Analysis model leaderboard · Sep 10
MMMU-Pro
Artificial Analysis v4.3.2 · Oct 27
78.5%
#37 / 89
Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 124 · measuredBest: #7 of 61 on LiveCodeBench2/6
BenchmarkScorePercentileRankLeader · source
IOI V2
Full source leaderboard reconciliation v2 · Oct 27
53.8%
#22 / 43
Leader Gemini 4 Argon · 100%
Full source leaderboard reconciliation v2 · Oct 27
Full source leaderboard reconciliation v2 · Oct 27
Not yet reported
Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 113 · measuredBest: #20 of 24 on OSWorld-Verified1/5
BenchmarkScorePercentileRankLeader · source
OSWorld-Verified
Full source leaderboard reconciliation · Oct 23
64.7%
#20 / 24
Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Not yet reported
BrowseCompMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 115 · measuredBest: #12 of 154 on AA Long Context Reasoning v1.14/6
BenchmarkScorePercentileRankLeader · source
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
83.3%
#12 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
IFBench
Artificial Analysis v4.3.2 · Oct 27
75.4%
#25 / 96
Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
10.9
#42 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
BullshitBench v2
Full source leaderboard reconciliation · Oct 23
19.0%
#67 / 83
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23
Full source leaderboard reconciliation · Oct 23
Not yet reported
SimpleQA VerifiedFACTS Grounding
Knowledge Work IQ 113 · measuredBest: #66 of 111 on AA-Briefcase v1.1 Elo1/6
BenchmarkScorePercentileRankLeader · source
AA-Briefcase v1.1 Elo
Artificial Analysis v4.3.2 · Oct 27
868
#66 / 111
Leader sonnet-5.5 · 1,812
Artificial Analysis v4.3.2 · Oct 27
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
GDPval-AA v2.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA
Release & availability
Release details on record for this model.
- Released
- Developer
- OpenAI
- Weights
- ProprietaryHosted access only
- Context
- 400,000 tokens
- API price
- $1.75 in · $14 outper 1M tokens · full pricing
About this score
How much of gpt-5.3-codex's IQ is measured, and how the rest is estimated.
13/ 39benchmark results
5/ 7dimensions measured
2estimated
0/5Abstract
0/5Math
5/6Academic
2/6Coding
1/5Computer Use
4/6Reliability
1/6Knowledge 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
Abstract Reasoning and Mathematical Reasoning have no published results yet, so their IQ is estimated from gpt-5.3-codex's other dimensions. Missing benchmarks can also draw on its predecessor, GPT 5.2 Codex; 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.
Compare gpt-5.3-codex
Side-by-side pages for the models it is most often weighed against.
#1 overall
gpt-6.1-sol
IQ141 29 higherEffective cost$6.30 2.9× cheaper
Closest IQ
Hy4 Preview
IQ112 same IQEffective cost$3.30 5.6× cheaper
Most similar profile
kimi-k2.5
IQ110 2 lowerEffective cost$2.79 6.7× cheaper
Similar price
kimi-k3
IQ127 15 higherEffective cost$20.20 about the same
#2 overall
opus-5.5
IQ141 29 higherEffective cost$35.73 1.9× pricier
#3 overall
Gemini 4 Argon
IQ140 28 higher
gpt-5.3-codexComparison model
Frequently asked questions
Quick answers about gpt-5.3-codex, 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-5.3-codex?
- gpt-5.3-codex has an estimated IQ of 112, which ranks #68 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-5.3-codex best at?
- Among the dimensions with published benchmark results, gpt-5.3-codex ranks highest in Academic Reasoning (IQ 129, #48 of 203) and Programmatic Reasoning (IQ 124, #52 of 177). Its lowest-ranked measured dimension is Computer Use (IQ 113, #80 of 176).
- What is the EQ of gpt-5.3-codex?
- gpt-5.3-codex 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-5.3-codex. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has gpt-5.3-codex been tested on?
- gpt-5.3-codex has published results on 13 of the 39 benchmarks behind AI IQ's Composite IQ, including AA Long Context Reasoning v1.1, LiveCodeBench, GPQA Diamond, Humanity's Last Exam and CritPt.
- How much does gpt-5.3-codex cost?
- gpt-5.3-codex costs $1.75 per million input tokens and $14.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $18.57 per million input-plus-output tokens.
- Is gpt-5.3-codex open source?
- No — gpt-5.3-codex is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- Who developed gpt-5.3-codex?
- gpt-5.3-codex was developed by OpenAI, based in the United States.
- When was gpt-5.3-codex released?
- gpt-5.3-codex was publicly released on February 5, 2026.
- How large is the context window of gpt-5.3-codex?
- gpt-5.3-codex supports a context window of 400,000 tokens — the amount of text it can consider in a single request.
- How fast is gpt-5.3-codex?
- In independent measurements, gpt-5.3-codex generates about 103 tokens per second, with a typical response time of about 61 seconds.