NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5.3

Added Aug 14, 2026Open weights

Compare models

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

Loading models…

Use in the app

GLM-5.3 for long-horizon autonomous coding and engineering workflows. This variant defaults to the model's low reasoning tier for faster responses.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
low · high · max
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.60
Output
$1.10
Cache read
$0.20

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K
Average output (7 days)
776 tokens
Longer than 64% of 468 models

Side by side

GLM 5.3 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 5.3Z.aiThis modelGLM 5.3 ThinkingZ.aiRemove
ProviderZ.aiZ.ai
Discovery tierOpen weightsOpen weights
AddedAug 14, 2026Aug 14, 2026
Limits
Context window1.05M1.05M
Max output131.07K131.07K
Average output776 tokens2.3K tokens
Pricing, USD per 1M tokens
Input$0.60$0.60
Output$1.10$1.10
Cache read$0.20$0.20
Performance
Throughput168.2 tok/sBest123.3 tok/s
Time to first token8.5 s7.7 sBest
Request success (24h)99.7%99.7%
Benchmark indexes
Intelligence Index44.844.8
Coding Index74.874.8
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effortlow, high, maxhigh, max

Public evaluations

Benchmarks

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

  • GLM 5.3
  • GLM 5.3 Thinking

Intelligence Index

  • GLM 5.344.8
  • GLM 5.3 Thinking44.8

GLM 5.3 tested at max reasoning effort

GLM 5.3: Better than 90% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 5.3: 74.8Top
    • GLM 5.3 Thinking: 74.8Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5.3: 62.2%Top
    • GLM 5.3 Thinking: 62.2%Top

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5.3: 29.4%Top
    • GLM 5.3 Thinking: 29.4%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 5.3: 0.3%Top
    • GLM 5.3 Thinking: 0.3%Top

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5.3: 1,505 EloTop
    • GLM 5.3 Thinking: 1,505 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5.3: 1,649 EloTop
    • GLM 5.3 Thinking: 1,649 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5.3: 11.2%Top
    • GLM 5.3 Thinking: 11.2%Top

  • AA-LCRv1.1

    Reasoning across long documents

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

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5.3: 17.2%Top
    • GLM 5.3 Thinking: 17.2%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

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

  • GPQA Diamond

    Graduate-level science questions

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

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5.3: 41.9%Top
    • GLM 5.3 Thinking: 41.9%Top

  • SciCode

    Scientific computing in Python

    • GLM 5.3: 59.0%Top
    • GLM 5.3 Thinking: 59.0%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

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

Scores from Artificial Analysis, updated Oct 26, 2026. GLM 5.3 was tested at max reasoning effort; compare scores measured at the same effort.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
168.2 tok/s
Faster than 78% of 254 models
Time to first token
8.5 s
Quicker than 16% of 254 models
Prompt cache hits
61.1%
About $0.36 per 1M input tokens with caching
Request success (24h)
99.7%
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 93.3%
  • 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-5.3",
    "reasoning_effort": "low",
    "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-5.3",
    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.