benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
Alibaba
Qwen 3.6 35B-A3B
14 benchmarks
AIME
#35 of 117
92.7%
OmniDocBench
#18 of 31
89.9%
GPQA Diamond
#48 of 118
86.0%
RealWorldQA
#3 of 9
85.3%
MMLU Pro
#16 of 55
85.2%
MMMU
#7 of 27
81.7%
LiveCodeBench
#22 of 53
80.4%
CharXiv
#19 of 23
78.0%
MMMU Pro
#20 of 36
75.3%
SWE-bench Verified
#38 of 86
73.4%
SWE-bench Multilingual
#12 of 16
67.2%
Terminal-Bench 2.0
#23 of 29
51.5%
SWE-bench Pro
#36 of 43
49.5%
Humanity's Last Exam
#62 of 72
21.4%