AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#55

GLM 5.2

Z.ai Release: 2026-06-17 Tested on: 2026-08-14 01:42 z-ai/glm-5.2::high
744B total (40B active)MoEOpen source
(high) (medium) (none)

Summary

GLM 5.2 scores 8.0 on AI BENCHY and ranks #55. It has 10.0 reliability, a 69.7% pass rate, $1.188 total cost, and 69.86s average response time.

What makes GLM 5.2 unique: It stands out most in Combined, where it ranks #1, while Puzzle Solving is its weakest area at #15.

Model facts

Researched on 2026-08-12

Reported
Parameters
744B total (40B active)
Architecture
MoE
Availability
Open source
License
MIT
Parameter source Availability source

Score

8.0

Consistency

8.6

Reliability

10.0

Total Cost (Current Price)

$1.188 ↑ +23.8%

Tested at: $0.959

Total Output Tokens

364,655

Total Input Tokens

83,822

Input Price

$0.966 / 1M

Output Price

$3.036 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 69.7%

Flaky tests

3

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

Response Time (avg)

69.86s

Response Time (max): 599.43s

Response Time (total): 1536.98s

Timed out: 3 No answer: 2 Wrong answer: 2 Did not follow instructions: 1

Hamster playing table tennis

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

#55 GLM 5.2

high
Invalid SVG
Cost
$0.000
Time
300.0s
Tokens
0 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 01:42 Re-test 8.0 10.0 $0.775 ↓ Current run
2026-07-16 21:43 New test added 8.0 10.0 $0.929 ↑ Compare
2026-07-10 11:53 Initial run 8.0 9.3 $0.554 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-10 11:54 $0.770 / 1M $2.420 / 1M
2026-07-14 10:48 $0.929 / 1M $2.918 / 1M
2026-07-16 15:36 $0.934 / 1M $2.935 / 1M
2026-07-16 18:05 $0.920 / 1M $2.891 / 1M
2026-07-16 18:31 $0.919 / 1M $2.887 / 1M
2026-07-18 15:17 $0.293 / 1M $0.920 / 1M
2026-07-20 15:56 $0.960 / 1M $3.014 / 1M
2026-07-21 16:10 $0.808 / 1M $2.539 / 1M
2026-07-22 11:30 $0.787 / 1M $2.473 / 1M
2026-07-24 00:05 $0.791 / 1M $2.486 / 1M
2026-07-25 03:22 $0.793 / 1M $2.491 / 1M
2026-07-28 08:40 $0.769 / 1M $2.416 / 1M
2026-07-31 10:14 $1.232 / 1M $3.873 / 1M
2026-07-31 13:32 $1.120 / 1M $3.520 / 1M
2026-08-01 02:47 $0.908 / 1M $2.854 / 1M
2026-08-01 12:04 $0.761 / 1M $2.389 / 1M
2026-08-02 09:23 $0.285 / 1M $0.894 / 1M
2026-08-04 12:41 $0.760 / 1M $2.420 / 1M
2026-08-07 22:44 $0.475 / 1M $1.492 / 1M
2026-08-07 23:08 $0.461 / 1M $1.448 / 1M
2026-08-11 16:01 $0.489 / 1M $1.536 / 1M
2026-08-12 11:59 $0.500 / 1M $3.150 / 1M
2026-08-12 20:39 $0.490 / 1M $1.540 / 1M
2026-08-14 12:51 $0.630 / 1M $1.981 / 1M
2026-08-20 12:51 $0.966 / 1M $3.036 / 1M

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 5.2highvsDeepSeek V4 Flash 0731highGLM 5.2highvsInklingmediumGLM 5.2highvsDeepSeek V4 Flash 0731lowGLM 5.2highvsGPT-5.6 TerrahighGLM 5.2highvsMuse Spark 1.1highGLM 5.2highvsKimi K3maxGLM 5.2highvsInklinghighGLM 5.2highvsGPT-5.2 ChatnoneGLM 5.2highvsMuse Glimmer 30BxhighGLM 5.2highvsStep 3.7 Flashmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 6.4 8.6
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.1 6.5
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 6.0 4.6
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models