NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 4.6 Turbo (Thinking)

Added Oct 2, 2025Open weights

Compare models

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

Loading models…

Use in the app

GLM 4.6 Turbo with thinking mode enabled for enhanced reasoning; shows internal reasoning and supports long context.

  • Reasoning
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$1.00
Output
$3.00

Reference prices as published by the model provider. API example

Specifications

Context window
204.8K
Max output
131.1K
Average output (7 days)
1.9K tokens
Longer than 91% of 465 models

Side by side

GLM 4.6 Turbo (Thinking) 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 4.6 Turbo (Thinking)Z.aiThis modelGLM 5V Turbo ThinkingZ.aiRemove
ProviderZ.aiZ.ai
Discovery tierOpen weightsOpen weights
AddedOct 2, 2025Apr 2, 2026
Limits
Context window204.8KBest202.8K
Max output131.07K131.07K
Average output1.9K tokens942 tokens
Pricing, USD per 1M tokens
Input$1.00Best$1.20
Output$3.00Best$4.00
Cache read—$0.24
Performance
Throughput—41.0 tok/s
Time to first token—6.5 s
Request success (24h)—97.6%
Benchmark indexes
Intelligence Index18.523.5Best
Coding Index45.8—
Math Index86.0—
Capabilities
ReasoningYesYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Video inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 4.6 Turbo (Thinking)
  • GLM 5V Turbo Thinking

Intelligence Index

  • GLM 4.6 Turbo (Thinking)18.5
  • GLM 5V Turbo Thinking23.5

GLM 4.6 Turbo (Thinking): Better than 47% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 4.6 Turbo (Thinking): 45.8
    • GLM 5V Turbo Thinking: —

  • Math Index

    Composite of the math evaluations

    • GLM 4.6 Turbo (Thinking): 86.0
    • GLM 5V Turbo Thinking: —

Agentic work

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 4.6 Turbo (Thinking): 756 Elo
    • GLM 5V Turbo Thinking: —

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 4.6 Turbo (Thinking): 54.0%
    • GLM 5V Turbo Thinking: 70.3%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 4.6 Turbo (Thinking): 14.5%
    • GLM 5V Turbo Thinking: 17.1%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 4.6 Turbo (Thinking): 78.0%
    • GLM 5V Turbo Thinking: 80.9%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GLM 4.6 Turbo (Thinking): 82.9%
    • GLM 5V Turbo Thinking: —

  • IFBench

    Following precise output instructions

    • GLM 4.6 Turbo (Thinking): 43.4%
    • GLM 5V Turbo Thinking: 61.1%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GLM 4.6 Turbo (Thinking): 69.5%
    • GLM 5V Turbo Thinking: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GLM 4.6 Turbo (Thinking): 86.0%
    • GLM 5V Turbo Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 4.6 Turbo (Thinking): 25.0%
    • GLM 5V Turbo Thinking: 32.6%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 4.6 Turbo (Thinking): 70.5%
    • GLM 5V Turbo Thinking: 98.5%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 4.6 Turbo (Thinking): 54.0%
    • GLM 5V Turbo Thinking: 70.3%Top

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

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-4.6-turbo:thinking",
    "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-4.6-turbo: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.