benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
head to head
Claude Sonnet 4.6
vs
DeepSeek V4 Pro
6 shared benchmarks
0
wins
0
ties
6
wins
94.0%
AIME
95.2%
74.0%
BrowseComp
83.4%
89.9%
GPQA Diamond
90.1%
79.2%
MMLU Pro
87.5%
79.6%
SWE-bench Verified
80.6%
59.1%
Terminal-Bench 2.0
67.9%