Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on Math QA
Loading...
64.86
Aclean
AGLS
0.5256
17.2278
33.93
50.6322
May 26, 2025
Aclean
Aattack
ASR
Tavg (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Aclean
Aattack
ASR
Tavg (s)
AGLS
Models=qwen2.5-14B
2025.05
64.86
39.18
39.59
1.16
AGLS
Models=gpt-4
2025.05
48.5
34.5
28.87
1.12
AGLS
Models=gpt-4o-latest
2025.05
32.4
22.33
31.08
0.82
AGLS
Models=llama3.1-70B
2025.05
13.67
11.67
17.12
1.27
AGLS
Models=qwen2.5-7B
2025.05
10.33
2
80.64
0.69
AGLS
Models=gemma2-27B
2025.05
10.33
2
80.64
1.28
AGLS
Models=llama3.1-8B
2025.05
8.67
4.67
46.12
0.23
AGLS
Models=gemma2-9B
2025.05
7.67
3.67
52.15
0.44
AGLS
Models=llama3.2-3B
2025.05
3
1
66.67
0.15
Feedback
Search any
task
Search any
task