benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
head to head
GLM-5.1
vs
GPT-5.4
5 shared benchmarks
2
wins
0
ties
3
wins
68.0%
BrowseComp
82.7%
86.2%
GPQA Diamond
92.8%
58.4%
SWE-bench Pro
57.7%
77.8%
SWE-bench Verified
77.2%
69.0%
Terminal-Bench 2.0
81.8%