Project AURIONAI Use-Cases Research & Innovation
Z.ai (Zhipu)
LLM

GLM-5.3

Z.ai's open-weight GLM-5 line model; one of the highest-scoring open models on AA. Licence: custom file, not MIT as Arena labels it.

Z.ai (Zhipu)Z.ai (Zhipu)ChinaGLMFamily
Benchmark bar charts for GLM-5.3 against other models.
Levelmodel
ClassLLM
Parameters753B
Context1,000,000
Released25 Aug 2026
Opennessopen weights restricted
Runs onhyperscale cluster, multi-GPU node
Statusactive

Benchmark Results

vendor-reportedindependent
Arena Text leaderboardhuman preference arena
glm-5.3-maxindependent
1,478 ±5
1,2001,4001,600

Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.

rank 27, Arena Text overall8 Oct 2026 arena.ai
Artificial Analysis Intelligence Index v4.3.2composite index
GLM-5.3 (Max)independent
45
03060

Score in index. Higher is better.

rank 2, Artificial Analysis open-weights viewartificialanalysis.ai, artificialanalysis.ai
maxindependent
45
03060

Score in index. Higher is better.

rank 29 of 205, AA leaderboard, 205 current models10 Oct 2026 artificialanalysis.ai
DeepSWE v1.1coding
mini-swe-agentvendor-reported
66.9
050100

Score in %. Higher is better.

huggingface.co
Humanity's Last Exam (HLE)knowledge and reasoning
with toolsvendor-reported
62.5
050100

Score in %. Higher is better.

huggingface.co
Terminal-Bench 2.1agents and tool use
vendor-reported
88.2
050100

Score in %. Higher is better.

huggingface.co
Claude Code 2.1.207vendor-reported
88.2
050100

Score in %. Higher is better.

huggingface.co
Terminal-Bench 3.0agents and tool use
vendor-reported
28.3
01530

Score. Higher is better.

huggingface.co
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

successor
GLM-5.1 to GLM-5.2: successor, medium confidenceGLM-5.2 to GLM-5.3: successor, medium confidenceGLM-5.1GLM-5.1Z.ai (Zhipu), Apr 2026GLM-5.2GLM-5.2Z.ai (Zhipu), Jun 2026GLM-5.3GLM-5.3Z.ai (Zhipu), Aug 2026
Z.ai (Zhipu)GLM-5.2 is the parent (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.

R&D Topics

Open-weight frontier releases as research substrateused by

Identity

Developer
Z.ai (Zhipu)
Family
GLM
Released
25 Aug 2026 sourcessecondary report
Weights published
4 Sep 2026
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
MoE MoE with DSA attention (tag glm_moe_dsa); same base as GLM-5.2
Total parameters
753B sources
Active parameters
–
Checkpoint parameters
–
Note
Active parameters unverified; context: evaluated up to 1M
Context length
1,000,000 tokens
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights restricted
Licence
GLM-5.3 licence sources
Access routes
API, open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
hyperscale cluster, multi-GPU node
Footprint
T2/T3 estimate (unverified). Active parameters not stated. Up to 1M context in evals.
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. huggingface.co/zai-org/GLM-5.3 https://huggingface.co/zai-org/GLM-5.3
  2. huggingface.co/zai-org https://huggingface.co/zai-org
  3. Pricing - Overview - Z.AI DEVELOPER DOCUMENT docs.z.ai https://docs.z.ai/guides/overview/pricing
  4. LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, SpaceXAI & others | Artificial Analysis artificialanalysis.ai/leaderboards/models https://artificialanalysis.ai/leaderboards/models
  5. Text Arena: LLM Rankings & AI Model Benchmarks arena.ai https://arena.ai/leaderboard/chat/text
  6. Comparison of Open Source AI Models across Intelligence, Performance, Price, Context Window, and more | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/models/open-source
  7. huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE https://huggingface.co/zai-org/GLM-5.3/blob/main/LICENSE
  8. Open-Source LLMs 2026: Which Are Actually Open-Licensed codersera.com https://codersera.com/blog/open-source-llms-landscape-2026/
  9. LLM Leaderboard - Comparison of AI models from OpenAI, Anthropic, Google, SpaceXAI & others | Artificial Analysis artificialanalysis.ai/leaderboards/models?open_weights=true https://artificialanalysis.ai/leaderboards/models?open_weights=true

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GLM-5.3", https://aurion.semai.id/models/zhipu-zai-glm-5-3/, records of October 2026.