benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
head to head
GPT-5.5
vs
Kimi K2.5
8 shared benchmarks
8
wins
0
ties
0
wins
84.4%
BrowseComp
60.6%
93.5%
GPQA Diamond
87.6%
41.4%
Humanity's Last Exam
24.37%
81.2%
MMMU Pro
78.5%
78.7%
OSWorld
63.3%
89.4%
OmniDocBench
89.33%
58.6%
SWE-bench Pro
50.7%
82.7%
Terminal-Bench 2.0
50.8%