NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5

Added Feb 11, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

GLM-5 is a capable open-weight model from Zhipu with advanced reasoning and instruction following.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.60
Output
$1.90
Cache read
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
128K
Average output (7 days)
279 tokens
Longer than 28% of 468 models

Side by side

GLM 5 compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

GLM 5Z.aiThis modelGLM 5.3 ThinkingZ.aiRemove
ProviderZ.aiZ.ai
Discovery tierOpen weightsOpen weights
AddedFeb 11, 2026Aug 14, 2026
Limits
Context window200K1.05MBest
Max output128K131.07KBest
Average output279 tokens2.3K tokens
Pricing, USD per 1M tokens
Input$0.60$0.60
Output$1.90$1.10Best
Cache read$0.10Best$0.20
Performance
Throughput78.3 tok/s123.3 tok/sBest
Time to first token3.4 sBest7.7 s
Request success (24h)99.9%Best99.7%
Benchmark indexes
Intelligence Index27.944.8Best
Coding Index—74.8
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effort—high, max

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • GLM 5
  • GLM 5.3 Thinking

Intelligence Index

  • GLM 527.9
  • GLM 5.3 Thinking44.8

GLM 5: Better than 69% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 5: —
    • GLM 5.3 Thinking: 74.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5: —
    • GLM 5.3 Thinking: 62.2%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5: —
    • GLM 5.3 Thinking: 29.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 5: —
    • GLM 5.3 Thinking: 0.3%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5: —
    • GLM 5.3 Thinking: 1,505 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5: —
    • GLM 5.3 Thinking: 1,649 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5: —
    • GLM 5.3 Thinking: 11.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5: 75.7%
    • GLM 5.3 Thinking: 79.7%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5: —
    • GLM 5.3 Thinking: 17.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5: 29.3%
    • GLM 5.3 Thinking: 42.3%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5: 82.0%
    • GLM 5.3 Thinking: 91.7%Top

  • IFBench

    Following precise output instructions

    • GLM 5: 72.3%
    • GLM 5.3 Thinking: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5: —
    • GLM 5.3 Thinking: 41.9%

  • SciCode

    Scientific computing in Python

    • GLM 5: —
    • GLM 5.3 Thinking: 59.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5: 43.2%
    • GLM 5.3 Thinking: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5: 98.2%
    • GLM 5.3 Thinking: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5: 75.7%
    • GLM 5.3 Thinking: 79.7%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
78.3 tok/s
Faster than 52% of 253 models
Time to first token
3.4 s
Quicker than 51% of 253 models
Prompt cache hits
65.5%
About $0.27 per 1M input tokens with caching
Request success (24h)
99.9%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 99.8%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="z-ai/glm-5",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Z.ai

Other Z.ai models, starting with the same family.