benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
arxiv
Qwen 3 30B A3B
9 benchmarks
AIME
#39 of 105
89.2%
AIME
#39 of 105
77.8%
GPQA Diamond
#56 of 95
74.0%
GPQA Diamond
#56 of 95
72.5%
LiveCodeBench
#34 of 49
64.2%
LiveCodeBench
#34 of 49
46.1%
HumanEval
#18 of 18
18.0%
Humanity's Last Exam
#39 of 39
14.0%
AIME
#39 of 105
10.0%