NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5.2

Added Jun 15, 2026Open weights

Compare models

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

Loading models…

Use in the app

GLM-5.2 is Z.AI's flagship model for long-horizon autonomous coding and engineering workflows. It is built to plan, execute, iterate, and optimize complex development tasks over extended runs. This variant keeps thinking disabled for faster direct responses.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Reasoning effort
none · 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)
839 tokens
Longer than 66% of 468 models

Side by side

GLM 5.2 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 5.2Z.aiThis modelGemini 3.5 Flash LiteGoogleRemove
ProviderZ.aiGoogle
Discovery tierOpen weightsEfficient
AddedJun 15, 2026Jul 21, 2026
Limits
Context window1.05M1.05M
Max output131.07KBest65.54K
Average output839 tokens178 tokens
Pricing, USD per 1M tokens
Input$0.42$0.30Best
Output$1.32Best$2.50
Cache read$0.078$0.03Best
Cache write—$0.0833
Performance
Throughput96.8 tok/s220.7 tok/sBest
Time to first token1.6 sBest2.2 s
Request success (24h)99.6%99.8%Best
Benchmark indexes
Intelligence Index22.4Best22.2
Coding Index46.549.3Best
Capabilities
ReasoningYesYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effortnone, high, maxminimal, low, medium, high

Public evaluations

Benchmarks

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

  • GLM 5.2
  • Gemini 3.5 Flash Lite

Intelligence Index

  • GLM 5.222.4
  • Gemini 3.5 Flash Lite22.2

GLM 5.2: Better than 54% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 5.2: 46.5
    • Gemini 3.5 Flash Lite: 49.3Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 25.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 3.3%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 650 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5.2: 1,244 EloTop
    • Gemini 3.5 Flash Lite: 985 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 13.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5.2: 42.3%
    • Gemini 3.5 Flash Lite: 76.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 10.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5.2: 9.8%
    • Gemini 3.5 Flash Lite: 18.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5.2: 68.6%
    • Gemini 3.5 Flash Lite: 83.8%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 1.0%

  • SciCode

    Scientific computing in Python

    • GLM 5.2: —
    • Gemini 3.5 Flash Lite: 41.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5.2: 42.3%
    • Gemini 3.5 Flash Lite: 76.0%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
96.8 tok/s
Faster than 62% of 253 models
Time to first token
1.6 s
Quicker than 87% of 253 models
Prompt cache hits
71.6%
About $0.18 per 1M input tokens with caching
Request success (24h)
99.6%
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 94.6%
  • 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",
    "reasoning_effort": "none",
    "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",
    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.