What is the IQ of Qwen3.8 Max 0902?

Qwen3.8 Max 0902 has an estimated IQ of 125, which ranks #27 out of 174 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 Qwen3.8 Max 0902 best at?

Among the dimensions with published benchmark results, Qwen3.8 Max 0902 ranks highest in Knowledge Work (IQ 129, #17 of 174) and Programmatic Reasoning (IQ 140, #19 of 175). Its lowest-ranked measured dimension is Reliability (IQ 120, #43 of 175).

What is the EQ of Qwen3.8 Max 0902?

Qwen3.8 Max 0902 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 Qwen3.8 Max 0902. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has Qwen3.8 Max 0902 been tested on?

Qwen3.8 Max 0902 has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including AA-Briefcase v1.1 Elo, GDPval-AA v2.1 normalized score, GPQA Diamond, Terminal-Bench 4.0 and GDP.pdf.

How much does Qwen3.8 Max 0902 cost?

Qwen3.8 Max 0902 costs $2.00 per million input tokens and $6.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $20.14 per million input-plus-output tokens.

Is Qwen3.8 Max 0902 open source?

No — Qwen3.8 Max 0902 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed Qwen3.8 Max 0902?

Qwen3.8 Max 0902 was developed by Alibaba, based in China.

When was Qwen3.8 Max 0902 released?

Qwen3.8 Max 0902 was publicly released on September 2, 2026.

How large is the context window of Qwen3.8 Max 0902?

Qwen3.8 Max 0902 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is Qwen3.8 Max 0902?

In independent measurements, Qwen3.8 Max 0902 generates about 42 tokens per second, with a typical response time of about 63 seconds.

AlibabaReleased Sep 2, 2026

Proprietary

Qwen3.8 Max 0902

Strongest in Knowledge Work (#17 of 174) and Programmatic Reasoning (#19 of 175); weakest in Reliability (#43 of 175). Computer Use is estimated, because no results are published yet.

Composite IQ ?

125

#27 of 174 ranked models · ahead of 85%

Alibaba's top-ranked model

Effective cost

$20.14/1M

$2 in · $6 out

Speed

42tok/s

63s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

6of 7 dims

18 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

107measured

#33 / 199

1/5

-20.5

Mathematical ReasoningMath

131measured

#30 / 174

2/5

-15

Academic ReasoningAcademic

131measured

#31 / 201

5/6

-4

Programmatic ReasoningCoding

140measured

#19 / 175

1/6

-8.5

Computer UseComputer Use

122estimated

#43 / 174

0/5

-20

ReliabilityReliability

120measured

#43 / 175

3/6

-12.5

Knowledge WorkKnowledge Work

129measured

#17 / 174

6/6

-2

Qwen3.8 Max 090295% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

18 of 39 Composite IQ benchmarks have a published result for Qwen3.8 Max 0902. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 107 · measuredBest: #20 of 76 on Chess Puzzles1/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

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

40.0%

#20 / 76

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

Not yet reported

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

Mathematical Reasoning IQ 131 · measuredBest: #24 of 71 on FrontierMath Tier 42/5

BenchmarkScorePercentileRankLeader · source

FrontierMath Tier 4

Full source leaderboard reconciliation · Oct 23

34.1%

#24 / 71

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

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

65.6%

#31 / 83

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

Not yet reported

ProofBench 1.1MathArenaAIME

Academic Reasoning IQ 131 · measuredBest: #21 of 147 on GPQA Diamond5/6

BenchmarkScorePercentileRankLeader · source

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 26

92.8%

#21 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 26

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 26

82.8%

#15 / 88

Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 26

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 26

43.1%

#31 / 166

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 26

CritPt

Artificial Analysis v4.3.2 · Oct 26

17.7%

#36 / 158

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 26

SciCode

Artificial Analysis v4.3.2 · Oct 26

52.1%

#49 / 166

Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 26

Not yet reported

MMLU-Pro

Programmatic Reasoning IQ 140 · measuredBest: #15 of 103 on Terminal-Bench 4.01/6

BenchmarkScorePercentileRankLeader · source

Terminal-Bench 4.0

Artificial Analysis v4.3.2 · Oct 26

38.9%

#15 / 103

Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v4.3.2 · Oct 26

Not yet reported

LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 122 · estimatedNo published results0/5

No published results yet for Computer Use. The 122 shown is estimated from Qwen3.8 Max 0902's other dimensions and will be replaced as results come in. How estimates work

BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 120 · measuredBest: #40 of 157 on AA Omniscience3/6

BenchmarkScorePercentileRankLeader · source

AA Omniscience

Artificial Analysis v4.3.2 · Oct 26

12.0

#40 / 157

Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 26

AA Long Context Reasoning v1.1

Artificial Analysis v4.3.2 · Oct 26

80.3%

#43 / 153

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 26

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

47.3%

#36 / 79

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

Not yet reported

BullshitBench v2IFBenchFACTS Grounding

Knowledge Work IQ 129 · measuredBest: #9 of 110 on AA-Briefcase v1.1 Elo6/6

BenchmarkScorePercentileRankLeader · source

AA-Briefcase v1.1 Elo

Artificial Analysis v4.3.2 · Oct 26

1,611

#9 / 110

Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 26

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 23

58.3%

#11 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 23

GDP.pdf

Artificial Analysis v4.3.2 · Oct 26

22.8%

#17 / 105

Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 26

EnterpriseOps-Gym-AA

Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 26

47.6%

#6 / 30

Leader fable-5 · 51.1%
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 26

AutomationBench-AA

Artificial Analysis v4.3.2 · Oct 26

56.2%

#31 / 105

Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 26

AA-AnalystAgent

Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 26

45.0%

#18 / 34

Leader gemini-3.7-flash · 60.0%
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 26

Release & availability

Facts from the publisher's announcement and documentation.

Released: Sep 2, 2026
Developer: Alibaba
Access: Hosted API checkpoint qwen3.8-max-0902 on Alibaba Cloud Model Studio.
Weights: ProprietaryHosted access only
Inputs: textimagevideo
Context: 1,000,000 tokens
API price: $2 in · $6 outper 1M tokens · full pricing

What Alibaba says

A separately addressable upgraded snapshot of Qwen3.8 Max, also named qwen3.8-max-2026-09-02.
Improves long-horizon coding, multi-tool coordination, chart reasoning, and document parsing.

Limitations

Hosted checkpoint; not the downloadable Qwen3.8-2.4T-A95B model.

Publisher statements, not AI IQ measurements.

Sourcesalibabacloud.com/help/en/model-studio/newly-released-models alibabacloud.com/help/en/model-studio/qwen3-8-max

About this score

How much of Qwen3.8 Max 0902's IQ is measured, and how the rest is estimated.

18/ 39benchmark results

6/ 7dimensions measured

1estimated

1/5Abstract

2/5Math

5/6Academic

1/6Coding

0/5Computer Use

3/6Reliability

6/6Knowledge 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

Computer Use has no published results yet, so its IQ is estimated from Qwen3.8 Max 0902's other dimensions. Missing benchmarks can also draw on its predecessors, Qwen3.8 Max and Qwen3.7 Max; 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 Qwen3.8 Max 0902

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

#1 overall

gpt-6.1-sol

IQ141 16 higherEffective cost$6.20 3.2× cheaper

Predecessor

Qwen3.8 Max

IQ123 2 lowerEffective cost$10.98 1.8× cheaper

Closest IQ

gpt-6-luna

IQ125 same IQEffective cost$0.756 26.6× cheaper

Most similar profile

grok-4.6

IQ126 1 higherEffective cost$8.74 2.3× cheaper

Similar price

kimi-k3

IQ127 2 higherEffective cost$19.88 about the same

#2 overall

opus-5.5

IQ141 16 higherEffective cost$35.16 1.7× pricier

Qwen3.8 Max 0902Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about Qwen3.8 Max 0902, 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 Qwen3.8 Max 0902?: Qwen3.8 Max 0902 has an estimated IQ of 125, which ranks #27 out of 174 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 Qwen3.8 Max 0902 best at?: Among the dimensions with published benchmark results, Qwen3.8 Max 0902 ranks highest in Knowledge Work (IQ 129, #17 of 174) and Programmatic Reasoning (IQ 140, #19 of 175). Its lowest-ranked measured dimension is Reliability (IQ 120, #43 of 175).
What is the EQ of Qwen3.8 Max 0902?: Qwen3.8 Max 0902 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 Qwen3.8 Max 0902. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Qwen3.8 Max 0902 been tested on?: Qwen3.8 Max 0902 has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including AA-Briefcase v1.1 Elo, GDPval-AA v2.1 normalized score, GPQA Diamond, Terminal-Bench 4.0 and GDP.pdf.
How much does Qwen3.8 Max 0902 cost?: Qwen3.8 Max 0902 costs $2.00 per million input tokens and $6.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $20.14 per million input-plus-output tokens.
Is Qwen3.8 Max 0902 open source?: No — Qwen3.8 Max 0902 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed Qwen3.8 Max 0902?: Qwen3.8 Max 0902 was developed by Alibaba, based in China.
When was Qwen3.8 Max 0902 released?: Qwen3.8 Max 0902 was publicly released on September 2, 2026.
How large is the context window of Qwen3.8 Max 0902?: Qwen3.8 Max 0902 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is Qwen3.8 Max 0902?: In independent measurements, Qwen3.8 Max 0902 generates about 42 tokens per second, with a typical response time of about 63 seconds.