benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
arxiv
Qwen 3 30B A3B
9 benchmarks
AIME
#47 of 117
89.2%
AIME
#47 of 117
77.8%
GPQA Diamond
#79 of 118
74.0%
GPQA Diamond
#79 of 118
72.5%
LiveCodeBench
#38 of 53
64.2%
LiveCodeBench
#38 of 53
46.1%
HumanEval
#19 of 19
18.0%
Humanity's Last Exam
#71 of 72
14.0%
AIME
#47 of 117
10.0%