AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#134

GLM 5.3

Z.ai Release: 2026-08-20 Tested on: 2026-08-20 13:55 z-ai/glm-5.3::low
744B total (40B active)MoEClosed
(high) (low)

Summary

GLM 5.3 scores 6.8 on AI BENCHY and ranks #134. It has 10.0 reliability, a 65.2% pass rate, $0.257 total cost, and 13.65s average response time.

What makes GLM 5.3 unique: It stands out most in Instructions following, where it ranks #1, while General Intelligence is its weakest area at #14.

Model facts

Researched on 2026-08-20

Reported
Parameters
744B total (40B active)
Architecture
MoE
Availability
Closed
License
-

Z.ai reports that GLM-5.3 uses the same base model as GLM-5.2. The announced weights were not public at research time.

Parameter source 1 Parameter source 2 Availability source

Score

6.8

Consistency

8.5

Reliability

10.0

Total Cost (Current Price)

$0.257

Total Output Tokens

24,808

Total Input Tokens

104,989

Input Price

$1.400 / 1M

Output Price

$4.400 / 1M

Tests Correct

Wrong Tests: 10

Attempt pass rate: 65.2%

Flaky tests

4

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

13.65s

Response Time (max): 83.60s

Response Time (total): 300.22s

Wrong answer: 8 Did not follow instructions: 1 Invalid tool call: 1

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#134 GLM 5.3

low
Cost
$0.007
Time
28.4s
Tokens
1,599 tok

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

GLM 5.3lowvsDeepSeek V4 PrononeGLM 5.3lowvsMiMo-V2.5-PromediumGLM 5.3lowvsSolar Pro 4mediumGLM 5.3lowvsGemini 3 Flash PreviewnoneGLM 5.3lowvsSolar Pro 4lowGLM 5.3lowvsGemma 4 26B A4BmediumFree AvailableGLM 5.3lowvsSeed-2.0-CodemediumGLM 5.3lowvsGLM 5.2noneGLM 5.3lowvsStep 3.7 FlashhighGLM 5.3lowvsKAT-Coder-Pro V2.5none

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.9 7.9
Coding 6.2 6.9
Combined 3.8 5.8
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 4.1 2.7
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models