NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 4.7 Original Thinking

Added Dec 22, 2025Open weights

Compare models

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

Loading models…

Use in the app

GLM-4.7 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
$0.40
Output
$1.93
Cache read
$0.0801

Reference prices as published by the model provider. API example

Specifications

Context window
200K
Max output
65.5K
Average output (7 days)
1.9K tokens
Longer than 90% of 468 models

Side by side

GLM 4.7 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 4.7 Original ThinkingZ.aiThis modelGemini 3.5 Flash LiteGoogleRemove
ProviderZ.aiGoogle
Discovery tierOpen weightsEfficient
AddedDec 22, 2025Jul 21, 2026
Limits
Context window200K1.05MBest
Max output65.54K65.54KBest
Average output1.9K tokens178 tokens
Pricing, USD per 1M tokens
Input$0.40$0.30Best
Output$1.93Best$2.50
Cache read$0.0801$0.03Best
Cache write—$0.0833
Performance
Throughput31.8 tok/s220.7 tok/sBest
Time to first token8.3 s2.2 sBest
Request success (24h)100.0%Best99.8%
Benchmark indexes
Intelligence Index22.222.2
Coding Index45.349.3Best
Math Index95.0—
Capabilities
ReasoningYesYes
ToolsYesYes
VisionNoYes
Structured outputYesYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—minimal, low, medium, high

Public evaluations

Benchmarks

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

  • GLM 4.7 Original Thinking
  • Gemini 3.5 Flash Lite

Intelligence Index

  • GLM 4.7 Original Thinking22.2
  • Gemini 3.5 Flash Lite22.2

GLM 4.7 Original Thinking: Better than 53% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 4.7 Original Thinking: 45.3
    • Gemini 3.5 Flash Lite: 49.3Top

  • Math Index

    Composite of the math evaluations

    • GLM 4.7 Original Thinking: 95.0
    • Gemini 3.5 Flash Lite: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 25.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 3.3%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 650 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 4.7 Original Thinking: 1,013 EloTop
    • Gemini 3.5 Flash Lite: 985 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 13.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 4.7 Original Thinking: 71.0%
    • Gemini 3.5 Flash Lite: 76.0%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 10.6%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 4.7 Original Thinking: 27.4%Top
    • Gemini 3.5 Flash Lite: 18.8%

  • GPQA Diamond

    Graduate-level science questions

    • GLM 4.7 Original Thinking: 85.9%Top
    • Gemini 3.5 Flash Lite: 83.8%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GLM 4.7 Original Thinking: 85.6%
    • Gemini 3.5 Flash Lite: —

  • IFBench

    Following precise output instructions

    • GLM 4.7 Original Thinking: 67.9%
    • Gemini 3.5 Flash Lite: —

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 1.0%

  • SciCode

    Scientific computing in Python

    • GLM 4.7 Original Thinking: —
    • Gemini 3.5 Flash Lite: 41.3%

  • LiveCodeBench

    Recent competitive programming problems

    • GLM 4.7 Original Thinking: 89.4%
    • Gemini 3.5 Flash Lite: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GLM 4.7 Original Thinking: 95.0%
    • Gemini 3.5 Flash Lite: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 4.7 Original Thinking: 31.8%
    • Gemini 3.5 Flash Lite: —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 4.7 Original Thinking: 95.9%
    • Gemini 3.5 Flash Lite: —

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 4.7 Original Thinking: 71.0%
    • 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
31.8 tok/s
Faster than 22% of 254 models
Time to first token
8.3 s
Quicker than 16% of 254 models
Prompt cache hits
40.5%
About $0.27 per 1M input tokens with caching
Request success (24h)
100.0%
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 94.1%
  • 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-4.7-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-4.7-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.