AlibabaReleased Sep 2, 2026
Proprietary

Qwen3.8 Max 0902

Strongest in Knowledge Work (#21 of 180) and Programmatic Reasoning (#23 of 181); weakest in Reliability (#48 of 181). Computer Use is estimated, because no results are published yet.

Composite IQ ?
125
#32 of 180 ranked models · ahead of 83%
Alibaba's top-ranked model
Effective cost
$20.79/1M
$2 in · $6 out
Speed
40tok/s
65s typical response
Context
1Mtokens
1,000,000 tokens in
Evidence
6of 7 dims
18 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract107#40● Math131#31● Academic130#35● Coding140#23● Computer Use120#53 · est.● Reliability120#48● Knowledge Work128#21
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
107measured
#40 / 209
1/5
-25
131measured
#31 / 180
2/5
-16
130measured
#35 / 211
5/6
-5
140measured
#23 / 181
1/6
-10
120estimated
#53 / 180
0/5
-24.5
120measured
#48 / 181
3/6
-14.5
128measured
#21 / 180
6/6
-4
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: #28 of 75 on FrontierMath Tier 42/5
BenchmarkScorePercentileRankLeader · source
FrontierMath Tier 4
Full source leaderboard reconciliation · Oct 23
34.1%
#28 / 75
Leader fable-5.2 · 100%
Full source leaderboard reconciliation · Oct 23
FrontierMath Tier 1-3
Full source leaderboard reconciliation · Oct 23
65.6%
#35 / 87
Leader fable-5.2 · 95.1%
Full source leaderboard reconciliation · Oct 23
Not yet reported
ProofBench 1.1MathArenaAIME
Academic Reasoning IQ 130 · measuredBest: #21 of 147 on GPQA Diamond5/6
BenchmarkScorePercentileRankLeader · source
GPQA Diamond
Artificial Analysis v5.0.1 · Nov 13
92.8%
#21 / 147
Leader gpt-6-astra · 96.1%
Artificial Analysis v5.0.1 · Nov 13
MMMU-Pro
Artificial Analysis v5.0.1 · Nov 13
82.8%
#16 / 90
Leader fable-5.1 · 90.6%
Artificial Analysis v5.0.1 · Nov 13
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 27
43.1%
#32 / 167
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27
CritPt
Artificial Analysis v4.3.2 · Oct 27
17.7%
#37 / 159
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27
SciCode
Artificial Analysis v4.3.2 · Oct 27
52.1%
#50 / 167
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 27
Not yet reported
MMLU-Pro
Programmatic Reasoning IQ 140 · measuredBest: #19 of 109 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v5.0.1 · Nov 13
38.9%
#19 / 109
Leader Kimi K3.1 Pro · 67.2%
Artificial Analysis v5.0.1 · Nov 13
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 120 · estimatedNo published results0/5
No published results yet for Computer Use. The 120 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: #41 of 158 on AA Omniscience3/6
BenchmarkScorePercentileRankLeader · source
AA Omniscience
Artificial Analysis v4.3.2 · Oct 27
12.0
#41 / 158
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 27
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 27
80.3%
#44 / 154
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27
SimpleQA Verified
Full source leaderboard reconciliation · Oct 23
47.3%
#40 / 83
Leader fable-5.2 · 94.0%
Full source leaderboard reconciliation · Oct 23
Not yet reported
BullshitBench v2IFBenchFACTS Grounding
Knowledge Work IQ 128 · measuredBest: #11 of 124 on GDPval-AA v2.1 normalized score6/6
BenchmarkScorePercentileRankLeader · source
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
AA-Briefcase v1.1 Elo
Artificial Analysis v5.0.1 · Nov 13
1,605
#11 / 116
Leader sonnet-5.5 · 1,816
Artificial Analysis v5.0.1 · Nov 13
EnterpriseOps-Gym-AA
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
47.6%
#6 / 31
Leader fable-5 · 51.1%
Full source leaderboard reconciliation v1117-task-strict-2026-09-29 · Oct 27
GDP.pdf
Artificial Analysis v5.0.1 · Nov 13
22.8%
#22 / 111
Leader Muse Wonder Full · 32.6%
Artificial Analysis v5.0.1 · Nov 13
AutomationBench-AA
Artificial Analysis v5.0.1 · Nov 13
56.2%
#35 / 112
Leader Gemini 4 Carbon · 77.8%
Artificial Analysis v5.0.1 · Nov 13
AA-AnalystAgent
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27
45.0%
#18 / 35
Leader gemini-3.7-flash · 60.0%
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 27

Release & availability

Facts from the publisher's announcement and documentation.

Released
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.

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.

Qwen3.8 Max 0902Comparison model
Browse 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 #32 out of 180 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 128, #21 of 180) and Programmatic Reasoning (IQ 140, #23 of 181). Its lowest-ranked measured dimension is Reliability (IQ 120, #48 of 181).
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 GDPval-AA v2.1 normalized score, AA-Briefcase v1.1 Elo, GPQA Diamond, Terminal-Bench 4.0 and MMMU-Pro.
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 $20.79 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 40 tokens per second, with a typical response time of about 65 seconds.