What is the IQ of glm-5?

glm-5 has an estimated IQ of 106, which ranks #94 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 glm-5 best at?

Among the dimensions with published benchmark results, glm-5 ranks highest in Computer Use (IQ 120, #54 of 176) and Programmatic Reasoning (IQ 116, #69 of 177). Its lowest-ranked measured dimension is Abstract Reasoning (IQ 77, #170 of 201).

What is the EQ of glm-5?

glm-5 has an estimated EQ of 115. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.

Which benchmarks has glm-5 been tested on?

glm-5 has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, AIME, MMLU-Pro, AA Omniscience and LiveCodeBench.

How much does glm-5 cost?

glm-5 costs $1.00 per million input tokens and $3.20 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $6.38 per million input-plus-output tokens.

Is glm-5 open source?

Yes — glm-5 is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.

glm-5 was developed by Z.ai, based in China.

When was glm-5 released?

glm-5 was publicly released on February 11, 2026.

How large is the context window of glm-5?

AI IQ hasn't verified an input context limit for glm-5 from its developer's documentation, so none is listed rather than guessing.

In independent measurements, glm-5 generates about 71 tokens per second, with a typical response time of about 53 seconds.

Z.aiReleased Feb 11, 2026

Open weights

glm-5

Strongest in Computer Use (#54 of 176) and Programmatic Reasoning (#69 of 177); weakest in Abstract Reasoning (#170 of 201). Knowledge Work is estimated, because no results are published yet.

Composite IQ ?

106

#94 of 176 ranked models · ahead of 47%

Z.ai's #5 model, behind GLM-5.3 (124)

Effective cost

$6.38/1M

$1 in · $3.20 out

Speed

71tok/s

53s typical response

Context

Unverified

Not in publisher docs

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

77measured

#170 / 201

3/5

-49.5

Mathematical ReasoningMath

105measured

#106 / 176

4/5

-42

Academic ReasoningAcademic

120measured

#103 / 203

5/6

-15.5

Programmatic ReasoningCoding

116measured

#69 / 177

1/6

-33.5

Computer UseComputer Use

120measured

#54 / 176

1/5

-23

ReliabilityReliability

113measured

#85 / 177

4/6

-21

Knowledge WorkKnowledge Work

94estimated

#140 / 176

0/6

-37.5

glm-595% 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 glm-5. Benchmarks without a result stay listed so gaps are visible.

Abstract Reasoning IQ 77 · measuredBest: #56 of 68 on ARC-AGI-23/5

BenchmarkScorePercentileRankLeader · source

ARC-AGI-2

Full source leaderboard reconciliation · Oct 23

4.9%

#56 / 68

Leader gpt-6-astra · 95.0%
Full source leaderboard reconciliation · Oct 23

ARC-AGI-1

Full source leaderboard reconciliation · Oct 23

44.7%

#57 / 68

Leader fable-5 · 98.5%
Full source leaderboard reconciliation · Oct 23

Chess Puzzles

Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 15

10.0%

#70 / 76

Leader gpt-6-astra · 72.0%
Epoch AI vEpoch 100-position leaderboard (task implementation versions recorded per run) · Oct 15

Not yet reported

ARC-AGI-3Mystery Game Puzzles

Mathematical Reasoning IQ 105 · measuredBest: #22 of 56 on AIME4/5

BenchmarkScorePercentileRankLeader · source

AIME

91.7%

#22 / 56

Leader gemini-3.1-pro · 98.1%

MathArena

Full source leaderboard reconciliation · Oct 28

19.5%

#42 / 64

Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 28

FrontierMath Tier 4

Epoch AI FrontierMath Tier 4 v2 · Sep 22

2.1%

#65 / 72

Leader gpt-6.1-sol · 100%
Epoch AI FrontierMath Tier 4 v2 · Sep 22

FrontierMath Tier 1-3

Epoch AI FrontierMath Tiers 1-3 v2 · Sep 22

16.4%

#76 / 84

Leader gpt-6-astra · 93.7%
Epoch AI FrontierMath Tiers 1-3 v2 · Sep 22

Not yet reported

ProofBench 1.1

Academic Reasoning IQ 120 · measuredBest: #18 of 45 on MMLU-Pro5/6

BenchmarkScorePercentileRankLeader · source

MMLU-Pro

TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

86.0%

#18 / 45

Leader fable-5.1 · 92.4%
TIGER-Lab MMLU-Pro leaderboard (missing rows only) · Sep 22

SciCode

Artificial Analysis model leaderboard · Sep 10

46.2%

#85 / 167

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

Humanity's Last Exam

Artificial Analysis v4.3.2 · Oct 27

29.3%

#90 / 167

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

GPQA Diamond

Artificial Analysis v4.3.2 · Oct 27

82.0%

#96 / 147

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

CritPt

Artificial Analysis v4.3.2 · Oct 27

2.0%

#104 / 159

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

Not yet reported

MMMU-Pro

Programmatic Reasoning IQ 116 · measuredBest: #31 of 61 on LiveCodeBench1/6

BenchmarkScorePercentileRankLeader · source

LiveCodeBench

Vals.ai · Aug 4

81.9%

#31 / 61

Leader Fugu Ultra v1.0 · 93.2%
Vals.ai · Aug 4

Not yet reported

IOI V2Terminal-Bench 4.0ProgramBenchSWE-rebenchMirrorCode

Computer Use IQ 120 · measuredBest: #25 of 43 on BrowseComp1/5

BenchmarkScorePercentileRankLeader · source

BrowseComp

Full source leaderboard reconciliation · Oct 23

75.9%

#25 / 43

Leader Kimi K3.1 Pro · 92.1%
Full source leaderboard reconciliation · Oct 23

Not yet reported

OSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam

Reliability IQ 113 · measuredBest: #37 of 96 on IFBench4/6

BenchmarkScorePercentileRankLeader · source

IFBench

Artificial Analysis v4.3.2 · Oct 27

72.3%

#37 / 96

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

AA Omniscience

Artificial Analysis v4.3.2 · Oct 27

0.3

#71 / 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

75.7%

#86 / 154

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

BullshitBench v2

Full source leaderboard reconciliation · Oct 23

28.0%

#57 / 83

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

Not yet reported

SimpleQA VerifiedFACTS Grounding

Knowledge Work IQ 94 · estimatedNo published results0/6

No published results yet for Knowledge Work. The 94 shown is estimated from glm-5'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

Release details on record for this model.

Released: Feb 11, 2026
Developer: Z.ai
Weights: Open weightsDownloadable and self-hostable
API price: $1 in · $3.20 outper 1M tokens · full pricing

About this score

How much of glm-5's IQ is measured, and how the rest is estimated.

18/ 39benchmark results

6/ 7dimensions measured

1estimated

3/5Abstract

4/5Math

5/6Academic

1/6Coding

1/5Computer Use

4/6Reliability

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

Knowledge Work has no published results yet, so its IQ is estimated from glm-5's other dimensions.

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 glm-5

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

#1 overall

gpt-6.1-sol

IQ141 35 higherEffective cost$6.30 about the same

Z.ai #1

GLM-5.3

IQ124 18 higherEffective cost$13.19 2.1× pricier

Closest IQ

Ember 1

IQ106 same IQEffective cost$15.87 2.5× pricier

Most similar profile

minimax-m2.1

IQ104 2 lowerEffective cost$2.23 2.9× cheaper

Similar price

gpt-5.4-mini

IQ111 5 higherEffective cost$6.36 about the same

#2 overall

opus-5.5

IQ141 35 higherEffective cost$35.73 5.6× pricier

glm-5Comparison model

Compare with any modelBrowse all comparisons →

Frequently asked questions

Quick answers about glm-5, 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 glm-5?: glm-5 has an estimated IQ of 106, which ranks #94 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 glm-5 best at?: Among the dimensions with published benchmark results, glm-5 ranks highest in Computer Use (IQ 120, #54 of 176) and Programmatic Reasoning (IQ 116, #69 of 177). Its lowest-ranked measured dimension is Abstract Reasoning (IQ 77, #170 of 201).
What is the EQ of glm-5?: glm-5 has an estimated EQ of 115. EQ measures emotional reasoning — how well a model reads and responds to emotional context — and is scored separately from IQ.
Which benchmarks has glm-5 been tested on?: glm-5 has published results on 18 of the 39 benchmarks behind AI IQ's Composite IQ, including IFBench, AIME, MMLU-Pro, AA Omniscience and LiveCodeBench.
How much does glm-5 cost?: glm-5 costs $1.00 per million input tokens and $3.20 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $6.38 per million input-plus-output tokens.
Is glm-5 open source?: Yes — glm-5 is an open-weights model: its trained weights are published, so it can be downloaded and self-hosted.
Who developed glm-5?: glm-5 was developed by Z.ai, based in China.
When was glm-5 released?: glm-5 was publicly released on February 11, 2026.
How large is the context window of glm-5?: AI IQ hasn't verified an input context limit for glm-5 from its developer's documentation, so none is listed rather than guessing.
How fast is glm-5?: In independent measurements, glm-5 generates about 71 tokens per second, with a typical response time of about 53 seconds.