benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
head to head
Claude Sonnet 4.6
vs
GLM-5.1
5 shared benchmarks
3
wins
0
ties
2
wins
94.0%
AIME
95.3%
74.0%
BrowseComp
68.0%
89.9%
GPQA Diamond
86.2%
79.6%
SWE-bench Verified
77.8%
59.1%
Terminal-Bench 2.0
69.0%