NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5 Original Thinking

Added Feb 11, 2026Open weights

Compare models

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

Loading models…

Use in the app

GLM-5 original with extended thinking capabilities for complex reasoning.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.60
Output
$1.90
Cache read
$0.10

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
128K
Average output (7 days)
1.2K tokens
Longer than 79% of 468 models

Side by side

GLM 5 Original 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 5 Original ThinkingZ.aiThis modelGLM 4.7 Original ThinkingZ.aiRemove
ProviderZ.aiZ.ai
Discovery tierOpen weightsOpen weights
AddedFeb 11, 2026Dec 22, 2025
Limits
Context window200K200K
Max output128KBest65.54K
Average output1.2K tokens1.9K tokens
Pricing, USD per 1M tokens
Input$0.60$0.40Best
Output$1.90Best$1.93
Cache read$0.10$0.0801Best
Performance
Throughput—38.8 tok/s
Time to first token—2.3 s
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index27.9Best22.2
Coding Index—45.3
Math Index—95.0
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 5 Original Thinking
  • GLM 4.7 Original Thinking

Intelligence Index

  • GLM 5 Original Thinking27.9
  • GLM 4.7 Original Thinking22.2

GLM 5 Original Thinking: Better than 69% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 45.3

  • Math Index

    Composite of the math evaluations

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 95.0

Agentic work

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 1,013 Elo

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5 Original Thinking: 75.7%Top
    • GLM 4.7 Original Thinking: 71.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5 Original Thinking: 29.3%Top
    • GLM 4.7 Original Thinking: 27.4%

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5 Original Thinking: 82.0%
    • GLM 4.7 Original Thinking: 85.9%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 85.6%

  • IFBench

    Following precise output instructions

    • GLM 5 Original Thinking: 72.3%Top
    • GLM 4.7 Original Thinking: 67.9%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 89.4%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GLM 5 Original Thinking: —
    • GLM 4.7 Original Thinking: 95.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5 Original Thinking: 43.2%Top
    • GLM 4.7 Original Thinking: 31.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5 Original Thinking: 98.2%Top
    • GLM 4.7 Original Thinking: 95.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5 Original Thinking: 75.7%Top
    • GLM 4.7 Original Thinking: 71.0%

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.

Prompt cache hits
68.2%
About $0.26 per 1M input tokens with caching

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.

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-original: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-5-original: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.