benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
head to head
Claude Sonnet 4.6
vs
GPT-5 mini
4 shared benchmarks
2
wins
0
ties
2
wins
94.0%
AIME
94.2%
89.9%
GPQA Diamond
85.0%
79.2%
MMLU Pro
83.3%
79.6%
SWE-bench Verified
60.4%