NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 4.6V

Added Dec 11, 2025Open weights

Compare models

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

Loading models…

Use in the app

GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Quantized at FP8.

  • Vision
  • Video input
Input
Text, Images, Video
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.30
Output
$0.90

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
24K
Average output (7 days)
139 tokens
Longer than 14% of 468 models

Side by side

GLM 4.6V 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 4.6VZ.aiThis modelQwen 3 235b A22BQwenRemove
ProviderZ.aiQwen
Discovery tierOpen weightsOpen weights
AddedDec 11, 2025Apr 29, 2025
Limits
Context window128K262.14KBest
Max output24KBest16.38K
Average output139 tokens616 tokens
Pricing, USD per 1M tokens
Input$0.30$0.0875Best
Output$0.90$0.35Best
Cache read—$0.0175
Performance
Request success (24h)99.7%Best91.4%
Benchmark indexes
Intelligence Index8.4Best8.3
Math Index26.3Best23.7
Capabilities
ToolsNoYes
VisionYesNo
Structured outputNoYes
PDF inputNoYes
Video inputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 4.6V
  • Qwen 3 235b A22B

Intelligence Index

  • GLM 4.6V8.4
  • Qwen 3 235b A22B8.3

GLM 4.6V: Better than 13% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • GLM 4.6V: 26.3Top
    • Qwen 3 235b A22B: 23.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 4.6V: 17.0%Top
    • Qwen 3 235b A22B: 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 4.6V: 3.7%
    • Qwen 3 235b A22B: 4.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 4.6V: 56.6%
    • Qwen 3 235b A22B: 61.3%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GLM 4.6V: 75.2%
    • Qwen 3 235b A22B: 76.2%Top

  • IFBench

    Following precise output instructions

    • GLM 4.6V: 27.9%
    • Qwen 3 235b A22B: 36.6%Top

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GLM 4.6V: 41.1%Top
    • Qwen 3 235b A22B: 34.3%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GLM 4.6V: 26.3%Top
    • Qwen 3 235b A22B: 23.7%

  • AIME

    Competition mathematics

    • GLM 4.6V: —
    • Qwen 3 235b A22B: 32.7%

  • MATH-500

    Competition math problems

    • GLM 4.6V: —
    • Qwen 3 235b A22B: 90.2%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 4.6V: 3.0%
    • Qwen 3 235b A22B: 6.1%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 4.6V: 30.7%Top
    • Qwen 3 235b A22B: 27.2%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 4.6V: 17.0%Top
    • Qwen 3 235b A22B: 0.0%

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
28.4%
Request success (24h)
99.7%
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 96.4%
  • 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-4.6v",
    "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-4.6v",
    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.