ModelBeat
Models/GLM-5.3-Flash
All models
Z

Z.ai (Zhipu AI): GLM-5.3-Flash

z-ai/glm-5.3-flash

GLM-5.3-Flash is Z.ai (Zhipu AI)’s open-weights AI model, released Aug 20, 2026. It costs $0.15/M input and $0.50/M output tokens, and handles a 1.3M-token context window. Its strongest use case is coding, where it ranks in the 83rd percentile of the models Model Beat tracks.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.

Context
1.3M
Input
$0.15 / 1M
Output
$0.50 / 1M
Cheapest via Wafer
$0.10 / $0.35 / 1M
Released
Aug 20, 2026
Modalities
textimagevideotext
Strongest atCoding top 17%Math top 34%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where GLM-5.3-Flash lands among all models tracked on Model Beat.

68.0
Intelligence Index
Epoch AI
68th percentile of tracked models
83.0
Coding Index
Epoch AI
83rd percentile of tracked models

Reasoning

3 evals
GPQA Diamond90.2%

Graduate-level scientific reasoning

Humanity's Last Exam39.9%

Frontier of human expert knowledge

SimpleQA Verified32.0%

Factual accuracy & hallucination

Coding

2 evals
SciCode51.6%

Scientific research coding

WebDev Arena1604

Human-rated web development

Math

1 evals
AIME 2024/202593.9%

Olympiad-qualifier math

In the news

5

Changelog

9
  • GLM-5.3-Flash: cheapest credible provider via Wafer now $0.35 per 1M output tokens (was $0.47, -26%)cheapest provider · Sep 9, 2026
  • GLM-5.3-Flash: cheapest credible provider via Wafer now $0.1 per 1M input tokens (was $0.14, -29%)cheapest provider · Sep 9, 2026
  • GLM-5.3-Flash: reported SciCode score rose from 46.1% to 51.6% (+12%)benchmark · Sep 5, 2026
  • GLM-5.3-Flash: cheapest credible provider via Makora now $0.14 per 1M input tokens (was $0.15, -7%)cheapest provider · Sep 2, 2026
  • GLM-5.3-Flash: cheapest credible provider via Makora now $0.47 per 1M output tokens (was $0.5, -6%)cheapest provider · Sep 2, 2026
  • GLM-5.3-Flash: cheapest credible provider via Parasail now $0.5 per 1M output tokens (was $0.25, +100%)cheapest provider · Aug 29, 2026
  • GLM-5.3-Flash: cheapest credible provider via Parasail now $0.15 per 1M input tokens (was $0.075, +100%)cheapest provider · Aug 29, 2026
  • GLM 5.3 Flash: context window changed from 1,048,576 to 1,310,720 tokenscontext · Aug 26, 2026
  • GLM 5.3 Flash (Z.ai) added to the tracker: $0.075/$0.25 per 1M, 1M context.tracked · Aug 26, 2026

Compare GLM-5.3-Flash with

Frequently asked questions

What is GLM-5.3-Flash?

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks.

Who created GLM-5.3-Flash?

GLM-5.3-Flash is an AI model developed by Z.ai (Zhipu AI), released Aug 20, 2026.

How much does GLM-5.3-Flash cost?

GLM-5.3-Flash's list price from Z.ai (Zhipu AI) is $0.15 per million input tokens and $0.50 per million output tokens. The cheapest credible third-party provider on OpenRouter (Wafer) serves it at $0.10/$0.35 per 1M.

What is GLM-5.3-Flash's context window?

GLM-5.3-Flash supports a context window of up to 1.3M tokens.

How does GLM-5.3-Flash perform on benchmarks?

On standardized evaluations tracked by Epoch AI, GLM-5.3-Flash scores 1604 on WebDev Arena, 39.9% on Humanity's Last Exam, 51.6% on SciCode.

Is GLM-5.3-Flash open source?

GLM-5.3-Flash is released with open weights (Open weights (unrestricted)), so the model can be downloaded and self-hosted.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Sep 10, 2026.