AlibabaReleased Nov 16, 2026
NewProprietary

Qwen4 Max

Strongest in Reliability (#4 of 188). Six of seven dimensions are estimated, because no results are published yet.

Composite IQ ?
128
#24 of 186 ranked models · ahead of 88%
Alibaba's top-ranked model
Effective cost
$15.59/1M
$1.50 in · $4.50 out
Speed
Not measured
No speed data yet
Context
1Mtokens
1,000,000 tokens in
Evidence
1of 7 dims
1 of 39 benchmarks

IQ profile

Seven dimensions, averaged equally into Composite IQ
Compare shape with
100 avg human130160● Abstract106#46 · est.● Math131#36 · est.● Academic130#38 · est.● Coding140#26 · est.● Computer Use119#62 · est.● Reliability140#4● Knowledge Work128#24 · 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
106estimated
#46 / 221
0/5
-26.5
131estimated
#36 / 186
0/5
-18.5
130estimated
#38 / 223
0/6
-5
140estimated
#26 / 187
0/6
-11
119estimated
#62 / 186
0/5
-27.5
140measured
#4 / 188
1/6
+4.5
128estimated
#24 / 186
0/6
-4
Qwen4 Max95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

1 of 39 Composite IQ benchmarks have a published result for Qwen4 Max. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 106 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 106 shown is estimated from Qwen4 Max'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 131 · estimatedNo published results0/5
No published results yet for Mathematical Reasoning. The 131 shown is estimated from Qwen4 Max'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 130 · estimatedNo published results0/6
No published results yet for Academic Reasoning. The 130 shown is estimated from Qwen4 Max's other dimensions and will be replaced as results come in. How estimates work
Humanity's Last ExamGPQA DiamondCritPtSciCodeMMLU-ProMMMU-Pro
Programmatic Reasoning IQ 140 · estimatedNo published results0/6
No published results yet for Programmatic Reasoning. The 140 shown is estimated from Qwen4 Max's other dimensions and will be replaced as results come in. How estimates work
LiveCodeBenchIOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 119 · estimatedNo published results0/5
No published results yet for Computer Use. The 119 shown is estimated from Qwen4 Max's other dimensions and will be replaced as results come in. How estimates work
BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 140 · measuredBest: #5 of 96 on BullshitBench v21/6
BenchmarkScorePercentileRankLeader · source
BullshitBench v2
Full source leaderboard reconciliation · Nov 19
90.0%
#5 / 96
Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Nov 19
Not yet reported
SimpleQA VerifiedaaOmniscienceIFBenchAA Long Context Reasoning v1.1FACTS Grounding
Knowledge Work IQ 128 · estimatedNo published results0/6
No published results yet for Knowledge Work. The 128 shown is estimated from Qwen4 Max'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
Alibaba
Access
Available through the QwenCloud hosted API and Token Plan as qwen4-max.
Weights
ProprietaryHosted access only
Inputs
textimagevideo
Context
1,000,000 tokens
API price
$1.50 in · $4.50 outper 1M tokens · full pricing

What Alibaba says

  • Qwen4 Max is the first model in the Qwen4 family, with native vision and reasoning effort controls.
  • The hosted model supports a one-million-token context window and tool use.

Limitations

  • Qwen4 Max weights have not been released; announced future open-weight Qwen4 models are separate.
  • Stored prices are Singapore standard real-time rates; other regions and promotional terms differ.

Publisher statements, not AI IQ measurements.

About this score

How much of Qwen4 Max's IQ is measured, and how the rest is estimated.

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

Abstract Reasoning, Mathematical Reasoning, Academic Reasoning, Programmatic Reasoning, Computer Use and Knowledge Work have no published results yet, so their IQ is estimated from Qwen4 Max's other dimensions. Missing benchmarks can also draw on its predecessors, Qwen3.8 Max 0902 and Qwen3.8 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 Qwen4 Max

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

Qwen4 MaxComparison model
Browse all comparisons →

Frequently asked questions

Quick answers about Qwen4 Max, 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 Qwen4 Max?
Qwen4 Max has an estimated IQ of 128, which ranks #24 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 Qwen4 Max best at?
There isn't enough published data to say yet. Qwen4 Max has measured benchmark results in only 1 of the seven dimension AI IQ scores, and strengths are only compared once at least two dimensions are measured and ranked.
What is the EQ of Qwen4 Max?
Qwen4 Max 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 Qwen4 Max. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has Qwen4 Max been tested on?
Qwen4 Max has published results on 1 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2.
How much does Qwen4 Max cost?
Qwen4 Max costs $1.50 per million input tokens and $4.50 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $15.59 per million input-plus-output tokens.
Is Qwen4 Max open source?
No — Qwen4 Max is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed Qwen4 Max?
Qwen4 Max was developed by Alibaba, based in China.
When was Qwen4 Max released?
Qwen4 Max was publicly released on November 16, 2026.
How large is the context window of Qwen4 Max?
Qwen4 Max supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is Qwen4 Max?
AI IQ doesn't have independent speed measurements for Qwen4 Max 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.