Project AURIONAI Use-Cases Research & Innovation
LLM

GLM-5.2

Z.ai open-weight coder-strong MoE model.

Z.ai (Zhipu)Z.ai (Zhipu)ChinaGLMFamily
Z.ai (Zhipu)
Levelmodel
ClassLLM
Parameters753B
Context1,000,000
Released13 Jun 2026
Opennessopen weights permissive
Runs onhyperscale cluster, multi-GPU node
Statusactive

Benchmark Results

vendor-reportedindependent
Arena Text leaderboardhuman preference arena
glm-5.2-maxindependent
1,475 ±4
1,2001,4001,600

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

Arena Text overall8 Oct 2026 arena.ai
SWE-bench Procoding
max effortvendor-reported
62.1
050100

Score in %. Higher is better.

rits.shanghai.nyu.edu
SWE-bench Verifiedcoding
third-party via Thinking Machinesindependent
80
050100

Score in %. Higher is better.

leaderboard.steel.dev
tau2-benchagents and tool use
Artificial Analysis telecom runindependent
99.1
050100

Score in %. Higher is better.

rank 1, BenchLM aggregator, top score10 Oct 2026 benchlm.ai
Terminal-Bench 2.1agents and tool use
vendor-reported
81
050100

Score in %. Higher is better.

rits.shanghai.nyu.edu
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 to GLM-5.1: successor, medium confidenceGLM-5GLM-5Z.ai (Zhipu)GLM-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-5.1 is the parent (successor)medium confidencenotes
Z.ai (Zhipu)GLM-5.3 is a child (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, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Code language modelsproduced byEfficiency architectures (MoE, sparse attention, long context)produced byOpen-weight frontier releases as research substrateused by

Identity

Developer
Z.ai (Zhipu)
Family
GLM
Released
13 Jun 2026 sourcessecondary report
Weights published
–
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
Total parameters
753B sources
Active parameters
40B
Checkpoint parameters
–
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 permissive
Licence
MIT License sources
Access routes
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). About 40B active.
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. GLM-5.2: Z.ai’s Open-Weights Coder Beats GPT-5.5 at 1/6 the Cost rits.shanghai.nyu.edu https://rits.shanghai.nyu.edu/ai/glm-5-2-z-ais-open-weights-coder-beats-gpt-5-5-at-1-6-the-cost/
  2. leaderboard.steel.dev/leaderboards/swe-bench-verified.md https://leaderboard.steel.dev/leaderboards/swe-bench-verified.md
  3. huggingface.co/zai-org/GLM-5.3 https://huggingface.co/zai-org/GLM-5.3
  4. Text Arena: LLM Rankings & AI Model Benchmarks arena.ai https://arena.ai/leaderboard/chat/text
  5. τ²-bench results Leaderboard & Scores , October 2026 benchlm.ai https://www.benchlm.ai/benchmarks/tau2-bench

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GLM-5.2", https://aurion.semai.id/models/zhipu-zai-glm-5-2/, records of October 2026.