Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

GLM-5.3

Z.aiReleased Aug 18, 2026Current

Score basis

GLM-5.3 is capable in agentic tasks, long context, reasoning, factuality, and coding; and behind the leaders in math and instruction following. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Capable5 capabilities
  1. Agentic−10.5%4 of 7
  2. Long Context−11.7%1 of 3
  3. Reasoning−14.9%5 of 6
  4. Factuality−18.5%3 of 4
  5. Coding−22.1%5 of 10
Limited2 capabilities
  1. Math−35.2%3 of 5
  2. Instruction Following−40.6%1 of 3
Not rated3 capabilities

Too few results yet to rate Safety, Multimodal or Multilingual.

Price

$1.40input$4.40outputper million tokens

From Artificial Analysis · 8 providers tracked · All prices

Costs more than 73% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

70results on49benchmarks

  • 15 independently verified
  • 26 aggregator
  • 18 vendor-reported
  • 11 cross-referenced

From 13 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

14 papers reference GLM-5.3

GLM-5.3 benchmark results

70 results on 49 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Agentic

CapableFull agentic ranking

10.5% behind the leader4 of 7 ranked benchmarks measured

Show 3 more agentic resultsHide 3 agentic results

Long Context

CapableFull long context ranking

11.7% behind the leader1 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Reasoning

CapableFull reasoning ranking

14.9% behind the leader5 of 6 ranked benchmarks measured

Show 5 more reasoning resultsHide 5 reasoning results

Factuality

CapableFull factuality ranking

18.5% behind the leader3 of 4 ranked benchmarks measured

Show 2 more factuality resultsHide 2 factuality results

Coding

CapableFull coding ranking

22.1% behind the leader5 of 10 ranked benchmarks measured

Show 3 more coding resultsHide 3 coding results

Math

LimitedFull math ranking

35.2% behind the leader3 of 5 ranked benchmarks measured

Instruction Following

LimitedFull instruction following ranking

40.6% behind the leader1 of 3 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 28 more resultsHide 28 results

GLM-5.3: common questions

Who makes GLM-5.3?

GLM-5.3 is made by Z.ai.

When was GLM-5.3 released?

GLM-5.3 was released on Aug 18, 2026, according to Artificial Analysis.

What is GLM-5.3 good at?

GLM-5.3 is capable in agentic tasks, long context, reasoning, factuality, and coding; and behind the leaders in math and instruction following. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

How much does GLM-5.3 cost?

GLM-5.3 costs $1.40 per million input tokens and $4.40 per million output tokens, according to Artificial Analysis. We track its price at 8 providers. At a mix of three input tokens to one output token, it costs more than 73% of the 330 priced models we track.

How many benchmarks has GLM-5.3 been tested on?

We track 70 results for GLM-5.3 on 49 benchmarks from 13 sources, 15 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does GLM-5.3 support?

OpenRouter lists tool calling, structured outputs, and reasoning for GLM-5.3.

About this record

Where GLM-5.3's numbers come from, and every name it appears under.

Tracked since
Aug 14, 2026
Newest source mention
Oct 8, 2026

Where the results come from

Verification: 70 scores · 15 independently verified · 26 aggregator-attributed · 11 vendor cross-reference · 18 vendor-reported. How these tiers are assigned

From 13 sources on 9 sites. Artificial Analysis supplies 27 of them; the 15 independently verified results come from 7 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai27
  • huggingface.co17
  • api.llm-stats.com12
  • livebench.ai7
  • epoch.ai3
  • datasets-server.huggingface.co1
  • labs.scale.com1
  • lmarena.ai1
  • simple-bench.com1

Also known as

How our sources name GLM-5.3 at each reasoning setting.

SettingShort formAPI id
low—glm-5-3-low glm-5.3 (low)
maxglm-5p3 maxglm-5.3 (max) glm-5.3-max
Also listed asglm-5-3GLM-5.3-BF16glm-5p3zai-org/glm-5.3zai-glm-5.3glm5.3