NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5.2 Thinking

Added Jun 15, 2026Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

GLM-5.2 with thinking enabled for harder long-horizon coding, autonomous agent workflows, complex engineering optimization, and real-world development tasks.

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

Pricing

USD per 1M tokens
Input
$0.42
Output
$1.32
Cache read
$0.078

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K
Average output (7 days)
1.8K tokens
Longer than 89% of 465 models

Side by side

Compare models

Put GLM 5.2 Thinking next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryMuse Spark 1.1Gemini 3.6 FlashDeepSeek V4 Flash Vision ExpAll 3

Public evaluations

Benchmarks

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

Intelligence Index

33.7

Tested at max reasoning effort

Better than 76% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    68.8

    Composite of the coding evaluations

    Better than 66% of 168 scored models

Agentic work

  • AutomationBench-AA

    28.4%

    Workflow automation, penalized for guardrail violations

    Better than 48% of 173 scored models

  • AutomationBench-AA tasks completed

    6.2%

    Workflows finished end to end without a guardrail violation

    Better than 48% of 173 scored models

  • AA-Briefcasev1.1

    1,227 Elo

    Agentic knowledge work, rated head to head

    Better than 59% of 166 scored models

  • GDPval-AAv2.1

    1,373 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 62% of 187 scored models

Document reasoning

  • GDP.pdf

    10.4%

    Professional reasoning over PDF documents, all-pass rate

    Better than 43% of 171 scored models

  • AA-LCRv1.1

    78.3%

    Reasoning across long documents

    Better than 69% of 309 scored models

  • MLCR-AA

    12.8%

    Long-context reasoning over medical records

    Better than 57% of 121 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    41.1%

    Expert-level questions across academic fields

    Better than 80% of 323 scored models

  • GPQA Diamond

    89.5%

    Graduate-level science questions

    Better than 73% of 291 scored models

  • IFBench

    73.3%

    Following precise output instructions

    Better than 82% of 215 scored models

Coding

  • Terminal-Benchv4.0

    1.0%

    Practical software engineering in a terminal

    Better than 37% of 171 scored models

  • SciCode

    51.2%

    Scientific computing in Python

    Better than 57% of 174 scored models

Legacy evaluations

  • Terminal-Bench Hard

    50.8%

    Earlier terminal task suite

    Better than 91% of 212 scored models

  • τ²-Bench Telecom

    99.1%

    Tool use in a customer-support simulation

    Better than 99% of 214 scored models

  • AA-LCR (unversioned)

    78.3%

    Long-context reasoning, earlier grading

    Better than 69% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. GLM 5.2 Thinking 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
108.8 tok/s
Faster than 66% of 250 models
Time to first token
1.8 s
Quicker than 82% of 250 models
Prompt cache hits
57.6%
About $0.22 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 98.2%
  • 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-5.2:thinking",
    "reasoning_effort": "high",
    "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-5.2:thinking",
    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.