benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
articles
Alibaba
Qwen 3.6 Plus
7 benchmarks
AIME
#16 of 39
95.3%
GPQA Diamond
#9 of 49
90.4%
MMLU Pro
#3 of 29
88.5%
LiveCodeBench
#6 of 28
87.1%
SWE-bench Verified
#9 of 40
78.8%
Terminal-Bench 2.0
#7 of 14
61.6%
Humanity's Last Exam
#6 of 24
50.6%