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 modelMiniMax M2.7MiniMaxRemove
ProviderZ.aiMiniMax
Discovery tierOpen weightsOpen weights
AddedJun 15, 2026Mar 18, 2026
Limits
Context window1.05MBest204.8K
Max output131.07K131.07K
Average output839 tokens556 tokens
Pricing, USD per 1M tokens
Input$0.42$0.21Best
Output$1.32$0.84Best
Cache read$0.078$0.042Best
Performance
Throughput96.8 tok/sBest23.3 tok/s
Time to first token1.6 s0.9 sBest
Request success (24h)99.6%100.0%Best
Benchmark indexes
Intelligence Index22.422.8Best
Coding Index46.552.6Best
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effortnone, high, max—

Public evaluations

Benchmarks

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

  • GLM 5.2
  • MiniMax M2.7

Intelligence Index

  • GLM 5.222.4
  • MiniMax M2.722.8

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
    • MiniMax M2.7: 52.6Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5.2: —
    • MiniMax M2.7: 4.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5.2: —
    • MiniMax M2.7: 0.3%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5.2: —
    • MiniMax M2.7: 718 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5.2: 1,244 EloTop
    • MiniMax M2.7: 1,008 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5.2: —
    • MiniMax M2.7: 6.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5.2: 42.3%
    • MiniMax M2.7: 78.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5.2: —
    • MiniMax M2.7: 5.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5.2: 9.8%
    • MiniMax M2.7: 29.6%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5.2: 68.6%
    • MiniMax M2.7: 87.4%Top

  • IFBench

    Following precise output instructions

    • GLM 5.2: —
    • MiniMax M2.7: 75.7%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5.2: —
    • MiniMax M2.7: 0.0%

  • SciCode

    Scientific computing in Python

    • GLM 5.2: —
    • MiniMax M2.7: 50.1%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5.2: —
    • MiniMax M2.7: 39.4%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5.2: —
    • MiniMax M2.7: 84.8%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5.2: 42.3%
    • MiniMax M2.7: 78.3%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 61% of 254 models
Time to first token
1.6 s
Quicker than 87% of 254 models
Prompt cache hits
66.4%
About $0.19 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.