NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 4.5V

Added Nov 22, 2025Open weights

Compare models

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

Loading models…

Use in the app

Multimodal GLM 4.5V that handles images alongside text while keeping the balanced reasoning strength of the GLM 4.5 family.

  • Reasoning
  • Vision
Input
Text, Images
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.60
Output
$1.80

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
16.4K
Average output (7 days)
732 tokens
Longer than 63% of 468 models

Side by side

GLM 4.5V 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 4.5VZ.aiThis modelMistral Small 3 24B (2501)MistralRemove
ProviderZ.aiMistral
Discovery tierOpen weightsOpen weights
AddedNov 22, 2025Sep 10, 2026
Limits
Context window65.54KBest32.77K
Max output16.38KBest8.19K
Average output732 tokens403 tokens
Pricing, USD per 1M tokens
Input$0.60$0.12Best
Output$1.80$0.35Best
Benchmark indexes
Intelligence Index6.76.7
Math Index15.3Best4.3
Capabilities
ReasoningYesNo
ToolsNoYes
VisionYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GLM 4.5V
  • Mistral Small 3 24B (2501)

Intelligence Index

  • GLM 4.5V6.7
  • Mistral Small 3 24B (2501)6.7

GLM 4.5V: Better than 6% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    Composite of the math evaluations

    • GLM 4.5V: 15.3Top
    • Mistral Small 3 24B (2501): 4.3

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 4.5V: 0.0%Top
    • Mistral Small 3 24B (2501): 0.0%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 4.5V: 3.5%
    • Mistral Small 3 24B (2501): 3.8%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 4.5V: 57.3%Top
    • Mistral Small 3 24B (2501): 46.2%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GLM 4.5V: 75.1%Top
    • Mistral Small 3 24B (2501): 65.2%

  • IFBench

    Following precise output instructions

    • GLM 4.5V: 28.6%Top
    • Mistral Small 3 24B (2501): 26.4%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GLM 4.5V: 35.2%Top
    • Mistral Small 3 24B (2501): 25.2%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GLM 4.5V: 15.3%Top
    • Mistral Small 3 24B (2501): 4.3%

  • AIME

    Competition mathematics

    • GLM 4.5V: —
    • Mistral Small 3 24B (2501): 8.0%

  • MATH-500

    Competition math problems

    • GLM 4.5V: —
    • Mistral Small 3 24B (2501): 71.5%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 4.5V: 6.8%
    • Mistral Small 3 24B (2501): —

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 4.5V: 19.6%Top
    • Mistral Small 3 24B (2501): 19.6%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 4.5V: 0.0%Top
    • Mistral Small 3 24B (2501): 0.0%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-4.5v",
    "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-4.5v",
    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.