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 modelKimi K2.6 TEEMoonshotRemove
ProviderZ.aiMoonshot
Discovery tierOpen weightsOpen weights
AddedFeb 11, 2026Apr 21, 2026
Limits
Context window200K262.14KBest
Max output128KBest65.54K
Average output279 tokens3.1K tokens
Pricing, USD per 1M tokens
Input$0.60Best$1.50
Output$1.90Best$5.25
Cache read$0.10Best$0.38
Performance
Throughput78.3 tok/s—
Time to first token3.4 s—
Request success (24h)99.9%100.0%Best
Benchmark indexes
Intelligence Index27.9Best27.0
Coding Index—61.8
Capabilities
ReasoningYesNo
ToolsYesYes
VisionNoYes
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 5
  • Kimi K2.6 TEE

Intelligence Index

  • GLM 527.9
  • Kimi K2.6 TEE27.0

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: —
    • Kimi K2.6 TEE: 61.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5: —
    • Kimi K2.6 TEE: 13.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5: —
    • Kimi K2.6 TEE: 1.8%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5: —
    • Kimi K2.6 TEE: 819 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5: —
    • Kimi K2.6 TEE: 1,038 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5: —
    • Kimi K2.6 TEE: 13.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5: 75.7%
    • Kimi K2.6 TEE: 81.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5: —
    • Kimi K2.6 TEE: 11.1%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5: 29.3%
    • Kimi K2.6 TEE: 37.5%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5: 82.0%
    • Kimi K2.6 TEE: 91.1%Top

  • IFBench

    Following precise output instructions

    • GLM 5: 72.3%
    • Kimi K2.6 TEE: 76.0%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5: —
    • Kimi K2.6 TEE: 0.5%

  • SciCode

    Scientific computing in Python

    • GLM 5: —
    • Kimi K2.6 TEE: 51.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5: 43.2%
    • Kimi K2.6 TEE: 43.9%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5: 98.2%Top
    • Kimi K2.6 TEE: 95.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5: 75.7%
    • Kimi K2.6 TEE: 81.0%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.