Alibaba
Qwen 3.5 9B
5 benchmarks
AIME
#26 of 39
92.5%
MMLU Pro
#16 of 29
82.5%
GPQA Diamond
#35 of 49
81.7%
MMMU Pro
#11 of 15
70.1%
LiveCodeBench
#21 of 28
65.6%
benchmark.space canonical public ledger of AI capability