benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
Alibaba
Qwen 3.6 35B-A3B
14 benchmarks
AIME
#28 of 105
92.7%
OmniDocBench
#17 of 26
89.9%
GPQA Diamond
#26 of 95
86.0%
RealWorldQA
#3 of 8
85.3%
MMLU Pro
#13 of 50
85.2%
MMMU
#6 of 26
81.7%
LiveCodeBench
#19 of 49
80.4%
CharXiv
#8 of 10
78.0%
MMMU Pro
#10 of 19
75.3%
SWE-bench Verified
#31 of 77
73.4%
SWE-bench Multilingual
#8 of 12
67.2%
Terminal-Bench 2.0
#19 of 24
51.5%
SWE-bench Pro
#16 of 22
49.5%
Humanity's Last Exam
#30 of 39
21.4%