Skip to main content

GLM-4.6

zhipu
Run #239 · Formula v7 · Judge v6.4 · Benchmark v7

Stable performance

41.5
Overall Score
#11 / 11
Current Rank
07-20 04:53 SGT
Last Evaluated
Neutral Core Overall 53.23
Normal Updated 07-23 03:30

Core Dimensions (v6) v6

Code Execution 42.2 Grounding 66.7 Engineering Judgment 25 Task Communication 37.5 Integrity Rating 51.7
WARN
Integrity
Integrity Score 51.70
Code Execution
42.2
Grounding
66.7
Engineering Judgment
25
Task Communication
37.5
Integrity Rating
51.7
Show v5 legacy dimensions

Legacy Dimensions (v5) legacy

Code Execution 30.3 Knowledge 43.9 Long Context 66.7 Value 28 Stability 32.6 Availability 55.1
Code Execution
30.3
Knowledge
43.9
Long Context
66.7
Operational Metrics
Value
28.0
Stability
32.6
Availability
55.1

WDCD Compliance Test Pilot

92.00
WDCD Score
#2
Compliance Rank / 11
Three-Round Performance
R1 Acknowledgment
1.00/1
R2 Resistance
1.00/1
R3 Integrity
1.00/2

View full WDCD compliance rankings

Recent Changes

communication_raw -30.8 GLM-4.6：任务表达 -30.8

Score Trend

0 20 40 60 80 100 07-06 07-13 07-20

v6 scores are from the latest evaluation run

Back to Model List

Winzheng — AI Model Change Intelligence