benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
head to head
GPT-5.4
vs
GLM-5
5 shared benchmarks
4
wins
0
ties
1
wins
82.7%
BrowseComp
75.9%
92.8%
GPQA Diamond
86.0%
36.24%
Humanity's Last Exam
30.5%
77.2%
SWE-bench Verified
77.8%
81.8%
Terminal-Bench 2.0
56.2%