OpenAIReleased Nov 17, 2026
NewProprietary

gpt-6.2-astra

Strongest in Abstract Reasoning (#2 of 221) and Mathematical Reasoning (#2 of 186); weakest in Reliability (#6 of 188). Three of seven dimensions are estimated, because no results are published yet.

Composite IQ ?
142
#3 of 186 ranked models · ahead of 99%
OpenAI's top-ranked model
Effective cost
$28.10/1M
$8 in · $40 out
Speed
Not measured
No speed data yet
Context
1Mtokens
1,050,000 tokens in
Evidence
4of 7 dims
9 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract134#2● Math153#2● Academic134#15 · est.● Coding150#6 · est.● Computer Use151#4● Reliability137#6● Knowledge Work132#11 · est.
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
134measured
#2 / 221
3/5
+1.5
153measured
#2 / 186
3/5
+3.5
134estimated
#15 / 223
0/6
-1
150estimated
#6 / 187
0/6
-1
151measured
#4 / 186
1/5
+4.5
137measured
#6 / 188
2/6
+1.5
132estimated
#11 / 186
0/6
0
gpt-6.2-astra95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

9 of 39 Composite IQ benchmarks have a published result for gpt-6.2-astra. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 134 · measuredBest: #1 of 73 on ARC-AGI-23/5
BenchmarkScorePercentileRankLeader · source
ARC-AGI-2
Full source leaderboard reconciliation · Nov 18
95.8%
#1 / 73
Leader on this benchmark
Full source leaderboard reconciliation · Nov 18
ARC-AGI-3
Full source leaderboard reconciliation · Nov 18
70.3%
#2 / 29
Leader fable-5.2 · 81.2%
Full source leaderboard reconciliation · Nov 18
ARC-AGI-1
Full source leaderboard reconciliation · Nov 18
98.5%
#8 / 73
Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Nov 18
Not yet reported
Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 153 · measuredBest: #1 of 70 on MathArena3/5
BenchmarkScorePercentileRankLeader · source
MathArena
Full source leaderboard reconciliation · Nov 18
92.2%
#1 / 70
Leader on this benchmark
Full source leaderboard reconciliation · Nov 18
FrontierMath Tier 4
Full source leaderboard reconciliation · Nov 19
100%
#3 / 77
Leader fable-5.2 · 100%
Full source leaderboard reconciliation · Nov 19
FrontierMath Tier 1-3
Full source leaderboard reconciliation · Nov 19
92.6%
#4 / 89
Leader fable-5.2 · 95.1%
Full source leaderboard reconciliation · Nov 19
Not yet reported
ProofBench 1.1AIME
Academic Reasoning IQ 134 · estimatedNo published results0/6
No published results yet for Academic Reasoning. The 134 shown is estimated from gpt-6.2-astra's other dimensions and will be replaced as results come in. How estimates work
Humanity's Last ExamGPQA DiamondCritPtSciCodeMMLU-ProMMMU-Pro
Programmatic Reasoning IQ 150 · estimatedNo published results0/6
No published results yet for Programmatic Reasoning. The 150 shown is estimated from gpt-6.2-astra's other dimensions and will be replaced as results come in. How estimates work
LiveCodeBenchIOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 151 · measuredBest: #6 of 77 on Arena.ai Agent Arena1/5
BenchmarkScorePercentileRankLeader · source
Arena.ai Agent Arena
Arena.ai Agent Arena · Nov 19
15.2
#6 / 77
Leader fable-5.2 · 27.4
Arena.ai Agent Arena · Nov 19
Not yet reported
BrowseCompOSWorld-VerifiedMCP AtlasAgents' Last Exam
Reliability IQ 137 · measuredBest: #2 of 85 on SimpleQA Verified2/6
BenchmarkScorePercentileRankLeader · source
SimpleQA Verified
Full source leaderboard reconciliation · Nov 19
78.5%
#2 / 85
Leader fable-5.2 · 94.0%
Full source leaderboard reconciliation · Nov 19
BullshitBench v2
Full source leaderboard reconciliation · Nov 19
55.0%
#37 / 96
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Nov 19
Not yet reported
aaOmniscienceIFBenchAA Long Context Reasoning v1.1FACTS Grounding
Knowledge Work IQ 132 · estimatedNo published results0/6
No published results yet for Knowledge Work. The 132 shown is estimated from gpt-6.2-astra'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

Facts from the publisher's announcement and documentation.

Released
Developer
OpenAI
Access
Available as gpt-6.2-astra through the OpenAI API and in ChatGPT Work and Codex for eligible Plus, Pro, Enterprise, and Edu users; Enterprise and Edu access depends on workspace settings.
Weights
ProprietaryHosted access only
Inputs
textimage
Context
1,050,000 tokens
API price
$8 in · $40 outper 1M tokens · full pricing

What OpenAI says

  • OpenAI announced GPT-6.2 Astra on November 17, 2026 for complex coding and professional work.
  • The API model supports a 1,050,000-token context window and low through max reasoning effort.
  • Standard short-context API rates are $8 per million input tokens and $40 per million output tokens.

Limitations

  • Audio and video inputs are not supported.
  • The API rejects reasoning effort none.
  • Requests above 272K input tokens incur higher rates for the full request.

Publisher statements, not AI IQ measurements.

About this score

How much of gpt-6.2-astra's IQ is measured, and how the rest is estimated.

9/ 39benchmark results
4/ 7dimensions measured
3estimated
3/5Abstract
3/5Math
0/6Academic
0/6Coding
1/5Computer Use
2/6Reliability
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

Academic Reasoning, Programmatic Reasoning and Knowledge Work have no published results yet, so their IQ is estimated from gpt-6.2-astra's other dimensions. Missing benchmarks can also draw on its predecessor, GPT 6 Astra; 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-6.2-astra

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

gpt-6.2-astraComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about gpt-6.2-astra, 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-6.2-astra?
gpt-6.2-astra has an estimated IQ of 142, which ranks #3 out of 186 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-6.2-astra best at?
Among the dimensions with published benchmark results, gpt-6.2-astra ranks highest in Abstract Reasoning (IQ 134, #2 of 221) and Mathematical Reasoning (IQ 153, #2 of 186). Its lowest-ranked measured dimension is Reliability (IQ 137, #6 of 188).
What is the EQ of gpt-6.2-astra?
gpt-6.2-astra 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-6.2-astra. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has gpt-6.2-astra been tested on?
gpt-6.2-astra has published results on 9 of the 39 benchmarks behind AI IQ's Composite IQ, including ARC-AGI-2, MathArena, SimpleQA Verified, FrontierMath Tier 4 and FrontierMath Tier 1-3.
How much does gpt-6.2-astra cost?
gpt-6.2-astra costs $8.00 per million input tokens and $40.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $28.10 per million input-plus-output tokens.
Is gpt-6.2-astra open source?
No — gpt-6.2-astra is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed gpt-6.2-astra?
gpt-6.2-astra was developed by OpenAI, based in the United States.
When was gpt-6.2-astra released?
gpt-6.2-astra was publicly released on November 17, 2026.
How large is the context window of gpt-6.2-astra?
gpt-6.2-astra supports a context window of 1,050,000 tokens — the amount of text it can consider in a single request.
How fast is gpt-6.2-astra?
AI IQ doesn't have independent speed measurements for gpt-6.2-astra yet. Speed comes from independent tests of a model's hosted API, which aren't available for every model — especially new, restricted-access, or self-hosted ones.