What is the IQ of qwen3.6-plus?

qwen3.6-plus has an estimated IQ of 110, which ranks #84 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 qwen3.6-plus best at?

Among the dimensions with published benchmark results, qwen3.6-plus ranks highest in Reliability (IQ 119, #50 of 177) and Knowledge Work (IQ 113, #71 of 176). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 102, #115 of 177).

What is the EQ of qwen3.6-plus?

qwen3.6-plus 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 qwen3.6-plus. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.

Which benchmarks has qwen3.6-plus been tested on?

qwen3.6-plus has published results on 17 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, AIME, IFBench, GPQA Diamond and AA Omniscience.

How much does qwen3.6-plus cost?

qwen3.6-plus costs $0.50 per million input tokens and $3.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $3.74 per million input-plus-output tokens.

Is qwen3.6-plus open source?

No — qwen3.6-plus is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

Who developed qwen3.6-plus?

qwen3.6-plus was developed by Alibaba, based in China.

When was qwen3.6-plus released?

qwen3.6-plus was publicly released on April 1, 2026.

How large is the context window of qwen3.6-plus?

qwen3.6-plus supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

How fast is qwen3.6-plus?

In independent measurements, qwen3.6-plus generates about 55 tokens per second, with a typical response time of about 111 seconds.

AlibabaReleased Apr 1, 2026

Proprietary

qwen3.6-plus

Strongest in Reliability (#50 of 177) and Knowledge Work (#71 of 176); weakest in Programmatic Reasoning (#115 of 177). All seven dimensions are measured.

Composite IQ ?

110

#84 of 176 ranked models · ahead of 53%

Alibaba's #10 model, behind Qwen3.8 Max 0902 (125)

Effective cost

$3.74/1M

$0.50 in · $3 out

Speed

55tok/s

111s typical response

Context

1Mtokens

1,000,000 tokens in

Evidence

7of 7 dims

17 of 39 benchmarks

Compare with gpt-6.1-solAPI pricing

IQ profile

Seven dimensions, averaged equally into Composite IQ

Compare shape with

Measured95% 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

86measured

#128 / 201

1/5

-40.5

Mathematical ReasoningMath

115measured

#75 / 176

2/5

-32

Academic ReasoningAcademic

122measured

#92 / 203

5/6

-13.5

Programmatic ReasoningCoding

102measured

#115 / 177

1/6

-47.5

Computer UseComputer Use

110measured

#89 / 176

2/5

-33

ReliabilityReliability

119measured

#50 / 177

5/6

-15

Knowledge WorkKnowledge Work

113measured

#71 / 176

1/6

-18.5

qwen3.6-plus95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human

Benchmark results

17 of 39 Composite IQ benchmarks have a published result for qwen3.6-plus. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 86 · measuredBest: #59 of 76 on Chess Puzzles1/5

BenchmarkScorePercentileRankLeader · source

Chess Puzzles

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

17.0%

#59 / 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 115 · measuredBest: #15 of 56 on AIME2/5

BenchmarkScorePercentileRankLeader · source

AIME

94.6%

#15 / 56

Leader gemini-3.1-pro · 98.1%

FrontierMath Tier 1-3

Full source leaderboard reconciliation · Oct 23

38.2%

#55 / 84

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

Not yet reported

FrontierMath Tier 4ProofBench 1.1MathArena

Academic Reasoning IQ 122 · measuredBest: #60 of 147 on GPQA Diamond5/6

BenchmarkScorePercentileRankLeader · source

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

88.2%

#60 / 147

Leader gpt-6-astra · 96.1%
Artificial Analysis v4.3.2 · Oct 27

MMMU-Pro

Artificial Analysis v4.3.2 · Oct 27

78.0%

#40 / 89

Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 27

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

27.8%

#98 / 167

Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 27

CritPt

Artificial Analysis v4.3.2 · Oct 27

2.9%

#97 / 159

Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 27

SciCode

Artificial Analysis model leaderboard · Sep 10

41.0%

#116 / 167

Leader opus-5.5 · 66.9%
Artificial Analysis model leaderboard · Sep 10

Not yet reported

MMLU-Pro

Programmatic Reasoning IQ 102 · measuredBest: #46 of 61 on ProgramBench1/6

BenchmarkScorePercentileRankLeader · source

ProgramBench

Full source leaderboard reconciliation · Oct 23

1.0%

#46 / 61

Leader opus-5.5 · 65.0%
Full source leaderboard reconciliation · Oct 23

Not yet reported

LiveCodeBenchIOI V2Terminal-Bench 4.0SWE-rebenchMirrorCode

Computer Use IQ 110 · measuredBest: #26 of 29 on Agents' Last Exam2/5

BenchmarkScorePercentileRankLeader · source

Agents' Last Exam

Full source leaderboard reconciliation · Oct 23

8.6%

#26 / 29

Leader opus-5.5 · 38.2%
Full source leaderboard reconciliation · Oct 23

OSWorld-Verified

Full source leaderboard reconciliation · Oct 23

62.5%

#22 / 24

Leader fable-5 · 85.0%
Full source leaderboard reconciliation · Oct 23

Not yet reported

BrowseCompMCP AtlasArena.ai Agent Arena

Reliability IQ 119 · measuredBest: #21 of 83 on BullshitBench v25/6

BenchmarkScorePercentileRankLeader · source

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

59.0%

#21 / 83

Leader opus-4.8 · 94.0%
Full source leaderboard reconciliation · Oct 23

IFBench

Artificial Analysis v4.3.2 · Oct 27

75.2%

#26 / 96

Leader minimax-m3 · 82.9%
Artificial Analysis v4.3.2 · Oct 27

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

0.9

#66 / 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

78.3%

#65 / 154

Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 27

SimpleQA Verified

Full source leaderboard reconciliation · Oct 23

44.1%

#42 / 80

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

Not yet reported

FACTS Grounding

Knowledge Work IQ 113 · measuredBest: #73 of 124 on GDPval-AA v2.1 normalized score1/6

BenchmarkScorePercentileRankLeader · source

GDPval-AA v2.1 normalized score

Artificial Analysis v4.3.2 · Oct 20

24.5%

#73 / 124

Leader opus-5.5 · 68.3%
Artificial Analysis v4.3.2 · Oct 20

Not yet reported

AA-Briefcase v1.1AutomationBench-AAGDP.pdfAA-AnalystAgentEnterpriseOps-Gym-AA

Release & availability

Release details on record for this model.

Released: Apr 1, 2026
Developer: Alibaba
Weights: ProprietaryHosted access only
Context: 1,000,000 tokens
API price: $0.50 in · $3 outper 1M tokens · full pricing

About this score

How much of qwen3.6-plus's IQ is measured, and how the rest is estimated.

17/ 39benchmark results

7/ 7dimensions measured

0estimated

1/5Abstract

2/5Math

5/6Academic

1/6Coding

2/5Computer Use

5/6Reliability

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.

How gaps are handled

Every dimension has at least one published result.

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 qwen3.6-plus

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

#1 overall

gpt-6.1-sol

IQ141 31 higherEffective cost$6.30 1.7× pricier

Alibaba #1

Qwen3.8 Max 0902

IQ125 15 higherEffective cost$20.79 5.6× pricier

Closest IQ

Agnes 2.5 Pro Beta

IQ110 same IQEffective cost$0.82 4.6× cheaper

Most similar profile

grok-4.3

IQ112 2 higherEffective cost$1.69 2.2× cheaper

Similar price

glm-4.7

IQ104 6 lowerEffective cost$3.69 about the same

#2 overall

opus-5.5

IQ141 31 higherEffective cost$35.73 9.5× pricier

qwen3.6-plusComparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about qwen3.6-plus, 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 qwen3.6-plus?: qwen3.6-plus has an estimated IQ of 110, which ranks #84 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 qwen3.6-plus best at?: Among the dimensions with published benchmark results, qwen3.6-plus ranks highest in Reliability (IQ 119, #50 of 177) and Knowledge Work (IQ 113, #71 of 176). Its lowest-ranked measured dimension is Programmatic Reasoning (IQ 102, #115 of 177).
What is the EQ of qwen3.6-plus?: qwen3.6-plus 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 qwen3.6-plus. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
Which benchmarks has qwen3.6-plus been tested on?: qwen3.6-plus has published results on 17 of the 39 benchmarks behind AI IQ's Composite IQ, including BullshitBench v2, AIME, IFBench, GPQA Diamond and AA Omniscience.
How much does qwen3.6-plus cost?: qwen3.6-plus costs $0.50 per million input tokens and $3.00 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $3.74 per million input-plus-output tokens.
Is qwen3.6-plus open source?: No — qwen3.6-plus is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
Who developed qwen3.6-plus?: qwen3.6-plus was developed by Alibaba, based in China.
When was qwen3.6-plus released?: qwen3.6-plus was publicly released on April 1, 2026.
How large is the context window of qwen3.6-plus?: qwen3.6-plus supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is qwen3.6-plus?: In independent measurements, qwen3.6-plus generates about 55 tokens per second, with a typical response time of about 111 seconds.