What is the IQ of GLM-5.3?

GLM-5.3 has an estimated IQ of 123, which ranks #19 out of 131 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions, each measured from source-backed benchmark results.

How much does GLM-5.3 cost?

GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $35.95 per million input-plus-output tokens.

Is GLM-5.3 open source?

No — GLM-5.3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.

When was GLM-5.3 released?

GLM-5.3 was publicly released on August 18, 2026.

How large is the context window of GLM-5.3?

GLM-5.3 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.

In independent measurements, GLM-5.3 generates about 83 tokens per second, with a typical response time of about 32 seconds.

Z.ai

GLM-5.3

Public AI IQ model profile with source-backed benchmark results and derived ranking context.

IQ

123

EQ

n/a

Effective Cost

$35.95

IQ Rank

#19

GLM-5.3 API pricing — full price table, workload cost examples, and cheaper alternatives.

IQ Dimensions

Dimension	IQ	Coverage
Abstract Reasoning	104	0/3
Mathematical Reasoning	126	0/5
Academic Reasoning	138	4/6
Programmatic Reasoning	131	2/6
Computer Use	130	0/6
Reliability	110	2/7

Benchmark Results

Benchmark	Score	Dimension
AA Long Context Reasoning	76.333	Reliability
AA Omniscience	14.3	Reliability
CritPt	19.143	Academic Reasoning
GPQA Diamond	91.717	Academic Reasoning
Humanity's Last Exam	42.261	Academic Reasoning
ProgramBench	16.5	Programmatic Reasoning
SciCode	56.481	Academic Reasoning
Terminal-Bench 2.1	83.895	Programmatic Reasoning

Compare

Frequently Asked Questions

What is the IQ of GLM-5.3?: GLM-5.3 has an estimated IQ of 123, which ranks #19 out of 131 public models on the AI IQ leaderboard. The score combines six equally weighted reasoning dimensions, each measured from source-backed benchmark results.
How much does GLM-5.3 cost?: GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens. Adjusted for how many tokens it actually consumes on real tasks, its effective cost works out to $35.95 per million input-plus-output tokens.
Is GLM-5.3 open source?: No — GLM-5.3 is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
When was GLM-5.3 released?: GLM-5.3 was publicly released on August 18, 2026.
How large is the context window of GLM-5.3?: GLM-5.3 supports a context window of 1,000,000 tokens — the amount of text it can consider in a single request.
How fast is GLM-5.3?: In independent measurements, GLM-5.3 generates about 83 tokens per second, with a typical response time of about 32 seconds.