Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d269Policy30d65, 14 pendingSources1,014

GLM-4.5

Z.aiWeights published Jul 20, 2025Deprecated

Score basis

GLM-4.5 is behind the leaders in factuality, long context, coding, and instruction following. Too few results yet to rate reasoning, agentic tasks, safety, math, 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.

Limited4 capabilities
  1. Factuality−29.7%2 of 4
  2. Long Context−35.6%1 of 3
  3. Coding−41.0%4 of 10
  4. Instruction Following−41.9%1 of 3
Not rated6 capabilities

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

Price

$0.60input$2.20outputper million tokens

From Z.ai's own price page · 2 providers tracked · All prices

Costs more than 58% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

36results on29benchmarks

  • 4 independently verified
  • 15 aggregator
  • 12 vendor-reported
  • 5 cross-referenced

From 5 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingJSON modeReasoning

As listed by OpenRouter

Research

5 papers reference GLM-4.5

GLM-4.5 benchmark results

36 results on 29 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

LimitedFull factuality ranking

29.7% behind the leader2 of 4 ranked benchmarks measured

Long Context

LimitedFull long context ranking

35.6% behind the leader1 of 3 ranked benchmarks measured

Coding

LimitedFull coding ranking

41.0% behind the leader4 of 10 ranked benchmarks measured

Show 4 more coding resultsHide 4 coding results

Instruction Following

LimitedFull instruction following ranking

41.9% behind the leader1 of 3 ranked benchmarks measured

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

Show 2 more reasoning resultsHide 2 reasoning results

Agentic

Not enough dataFull agentic ranking

0 of 7 ranked benchmarks measured

More results

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

Show 11 more resultsHide 11 results

GLM-4.5: common questions

Who makes GLM-4.5?

GLM-4.5 is made by Z.ai.

When was GLM-4.5 released?

GLM-4.5's weights were first published on Hugging Face on Jul 20, 2025.

What is GLM-4.5 good at?

GLM-4.5 is behind the leaders in factuality, long context, coding, and instruction following. Too few results yet to rate reasoning, agentic tasks, safety, math, multimodal tasks, or multilingual tasks.

How much does GLM-4.5 cost?

GLM-4.5 costs $0.60 per million input tokens and $2.20 per million output tokens, according to Z.ai's own price page. We track its price at 2 providers. At a mix of three input tokens to one output token, it costs more than 58% of the 331 priced models we track.

How many benchmarks has GLM-4.5 been tested on?

We track 36 results for GLM-4.5 on 29 benchmarks from 5 sources, 4 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does GLM-4.5 support?

OpenRouter lists tool calling, json mode, and reasoning for GLM-4.5.

About this record

Where GLM-4.5's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
Aug 24, 2026

Where the results come from

Verification: 36 scores · 4 independently verified · 15 aggregator-attributed · 5 vendor cross-reference · 12 vendor-reported. How these tiers are assigned

From 5 sources on 5 sites. Artificial Analysis supplies 15 of them; the 4 independently verified results come from 2 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai15
  • api.llm-stats.com12
  • huggingface.co5
  • swebench.com3
  • matharena.ai1

Also known as

glm-4-5GLM-4.5 (2025-08-22)glm-4.5 (reasoning)glm-4p5