benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
OpenAI
gpt-oss-120b
4 benchmarks
AIME
#7 of 39
97.9%
MMLU Pro
#2 of 29
90.0%
GPQA Diamond
#41 of 49
73.5%
SWE-bench Verified
#36 of 40
62.4%