Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d67, 15 pendingSources1,015

GLM-5.1

Z.aiReleased Apr 7, 2026Current

Score basis

GLM-5.1 is capable in instruction following, long context, and coding; and behind the leaders in reasoning, factuality, and agentic tasks. Too few results yet to rate 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.

Capable3 capabilities
  1. Instruction Following−17.6%2 of 3
  2. Long Context−20.8%1 of 3
  3. Coding−21.0%8 of 10
Limited3 capabilities
  1. Reasoning−26.4%4 of 6
  2. Factuality−27.4%3 of 4
  3. Agentic−32.4%5 of 7
Not rated4 capabilities

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

Price

$1.38input$4.40outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

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

Evidence

133results on85benchmarks

  • 11 independently verified
  • 34 aggregator
  • 31 vendor-reported
  • 57 cross-referenced

From 20 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

10 papers reference GLM-5.1

GLM-5.1 benchmark results

133 results on 85 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Instruction Following

CapableFull instruction following ranking

17.6% behind the leader2 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Long Context

CapableFull long context ranking

20.8% behind the leader1 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Coding

CapableFull coding ranking

21.0% behind the leader8 of 10 ranked benchmarks measured

Show 9 more coding resultsHide 9 coding results

Reasoning

LimitedFull reasoning ranking

26.4% behind the leader4 of 6 ranked benchmarks measured

Show 11 more reasoning resultsHide 11 reasoning results

Factuality

LimitedFull factuality ranking

27.4% behind the leader3 of 4 ranked benchmarks measured

Show 3 more factuality resultsHide 3 factuality results

Agentic

LimitedFull agentic ranking

32.4% behind the leader5 of 7 ranked benchmarks measured

Show 8 more agentic resultsHide 8 agentic results

Math

Not enough dataFull math ranking

0 of 5 ranked benchmarks measured

Show 7 more math resultsHide 7 math results

More results

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

Show 61 more resultsHide 61 results

GLM-5.1: common questions

Who makes GLM-5.1?

GLM-5.1 is made by Z.ai.

When was GLM-5.1 released?

GLM-5.1 was released on Apr 7, 2026, according to Artificial Analysis.

What is GLM-5.1 good at?

GLM-5.1 is capable in instruction following, long context, and coding; and behind the leaders in reasoning, factuality, and agentic tasks. Too few results yet to rate safety, math, multimodal tasks, or multilingual tasks.

How much does GLM-5.1 cost?

GLM-5.1 costs $1.38 per million input tokens and $4.40 per million output tokens, according to Artificial Analysis. We track its price at 3 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-5.1 been tested on?

We track 133 results for GLM-5.1 on 85 benchmarks from 20 sources, 11 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does GLM-5.1 support?

OpenRouter lists tool calling, structured outputs, and reasoning for GLM-5.1.

About this record

Where GLM-5.1's numbers come from, and every name it appears under.

Tracked since
Apr 25, 2026
Newest source mention
Aug 23, 2026

Where the results come from

Verification: 133 scores · 11 independently verified · 34 aggregator-attributed · 57 vendor cross-reference · 31 vendor-reported. How these tiers are assigned

From 20 sources on 9 sites. Hugging Face supplies 71 of them; the 11 independently verified results come from 6 sites. Bars are coloured by trust tier.

  • huggingface.co71
  • artificialanalysis.ai34
  • api.llm-stats.com17
  • matharena.ai4
  • epoch.ai3
  • datasets-server.huggingface.co1
  • labs.scale.com1
  • lmarena.ai1
  • simple-bench.com1

Also known as

glm-5-1glm-5-1-non-reasoningglm-5.1 (non-reasoning)glm-5.1 (reasoning)glm-5.1 (w/o explore)glm-5.1 thinkingglm-5.1 w/o exploreglm-5p1zai-org/glm-5.1GLM-5.1-744B-A40B