benchmark
.
space
benchmarks
rankings
compare
voices
transcripts
papers
articles
head to head
Gemma 4 31B
vs
Qwen 3.6 35B-A3B
10 shared benchmarks
1
wins
1
ties
8
wins
89.2%
AIME
92.7%
84.3%
GPQA Diamond
86.0%
19.5%
Humanity's Last Exam
21.4%
80.0%
LiveCodeBench
80.4%
85.2%
MMLU Pro
85.2%
76.9%
MMMU Pro
75.3%
51.7%
SWE-bench Multilingual
67.2%
35.7%
SWE-bench Pro
49.5%
52.0%
SWE-bench Verified
73.4%
42.9%
Terminal-Bench 2.0
51.5%