Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on StrategyQA (Robustness and Latency)
Loading...
64
Accuracy (Clean)
AGLS
33.1432
41.1541
49.165
57.1759
May 26, 2025
Accuracy (Clean)
Accuracy (Attack)
Attack Success Rate (ASR)
Average Latency (s)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Clean)
Accuracy (Attack)
Attack Success Rate (ASR)
Average Latency (s)
AGLS
Models=gemma2-27B
2025.05
64
59.67
6.77
0.21
AGLS
Models=gpt-4
2025.05
57.33
43.7
23.77
0.56
AGLS
Models=qwen2.5-14B
2025.05
55.67
44.43
20.19
0.68
AGLS
Models=gpt-4o-latest
2025.05
55.33
43.45
21.47
0.7
AGLS
Models=qwen2.5-7B
2025.05
55
36.57
33.51
0.46
AGLS
Models=gemma2-9B
2025.05
54
48.36
10.44
0.17
AGLS
Models=llama3.1-70B
2025.05
47.33
35.68
24.61
1.42
AGLS
Models=llama3.1-8B
2025.05
43.33
42.33
2.31
1.07
AGLS
Models=llama3.2-3B
2025.05
34.33
29.33
14.56
0.23
Feedback
Search any
task
Search any
task
