benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
head to head
Claude Opus 4.6
vs
GLM-4.7
5 shared benchmarks
4
wins
0
ties
1
wins
100.0%
AIME
95.7%
91.3%
GPQA Diamond
85.7%
53.1%
Humanity's Last Exam
42.8%
76.0%
LiveCodeBench
84.9%
81.42%
SWE-bench Verified
73.8%