NOUMENOpen app
NOUMEN

Z.ai · Open weights

GLM 5.3 Flash

Added Aug 26, 2026Open weights

Compare models

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

Loading models…

Use in the app

ox-alpha out of stealth! GLM-5.3 Flash is Z.ai's first natively multimodal GLM-5 model, with 320B total parameters and just 18B active parameters for efficient coding, agentic work, and precise 1M-token context. Its hybrid sparse-and-linear attention architecture helps it outperform GLM-5.2 at one-tenth the price while approaching Claude Opus 4.8 on coding and agentic benchmarks.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • Video input
Input
Text, Images, Video
Output
Text
Reasoning effort
low · high · max
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.10
Output
$0.30
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K
Average output (7 days)
1.3K tokens
Longer than 80% of 465 models

Side by side

GLM 5.3 Flash 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 5.3 FlashZ.aiThis modelClaude Opus 4.8AnthropicRemove
ProviderZ.aiAnthropic
Discovery tierOpen weightsFrontier
AddedAug 26, 2026May 28, 2026
Limits
Context window1.05MBest1M
Max output131.07KBest128K
Average output1.3K tokens360 tokens
Pricing, USD per 1M tokens
Input$0.10Best$5.00
Output$0.30Best$25.00
Cache read$0.025Best$0.50
Performance
Throughput105.3 tok/sBest72.6 tok/s
Time to first token3.3 s1.4 sBest
Request success (24h)99.6%100.0%Best
Benchmark indexes
Intelligence Index41.841.8
Coding Index71.574.3Best
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputNoYes
Video inputYesNo
Reasoning effortlow, high, maxlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • GLM 5.3 Flash
  • Claude Opus 4.8

Intelligence Index

  • GLM 5.3 Flash41.8
  • Claude Opus 4.841.8

GLM 5.3 Flash: Better than 86% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GLM 5.3 Flash: 71.5
    • Claude Opus 4.8: 74.3Top

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GLM 5.3 Flash: 60.4%Top
    • Claude Opus 4.8: 45.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GLM 5.3 Flash: 25.4%Top
    • Claude Opus 4.8: 17.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • GLM 5.3 Flash: 0.8%
    • Claude Opus 4.8: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GLM 5.3 Flash: 1,452 EloTop
    • Claude Opus 4.8: 1,319 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GLM 5.3 Flash: 1,642 EloTop
    • Claude Opus 4.8: 1,454 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GLM 5.3 Flash: 15.4%
    • Claude Opus 4.8: 22.8%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • GLM 5.3 Flash: 80.0%Top
    • Claude Opus 4.8: 77.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • GLM 5.3 Flash: 11.7%
    • Claude Opus 4.8: 19.4%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GLM 5.3 Flash: 39.9%
    • Claude Opus 4.8: 48.7%Top

  • GPQA Diamond

    Graduate-level science questions

    • GLM 5.3 Flash: 91.2%
    • Claude Opus 4.8: 92.0%Top

  • IFBench

    Following precise output instructions

    • GLM 5.3 Flash: —
    • Claude Opus 4.8: 62.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GLM 5.3 Flash: 32.8%Top
    • Claude Opus 4.8: 21.7%

  • SciCode

    Scientific computing in Python

    • GLM 5.3 Flash: 51.6%
    • Claude Opus 4.8: 54.4%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GLM 5.3 Flash: —
    • Claude Opus 4.8: 58.3%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GLM 5.3 Flash: —
    • Claude Opus 4.8: 94.4%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GLM 5.3 Flash: 80.0%Top
    • Claude Opus 4.8: 77.7%

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
105.3 tok/s
Faster than 62% of 251 models
Time to first token
3.3 s
Quicker than 52% of 251 models
Prompt cache hits
82.1%
About $0.0384 per 1M input tokens with caching
Request success (24h)
99.6%
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 98.2%
  • 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-5.3-flash",
    "reasoning_effort": "low",
    "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-5.3-flash",
    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.