Anthropic Claude 3.5 Sonnet v2 vs Google Gemma 3n E4B Instructed
Detailed comparison for LLMs
AnthropicGoogle
Head-to-Head Overview
Gemma 3n E4B Instructed is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Anthropic Claude 3.5 Sonnet v2 and Google Gemma 3n E4B Instructed across the three attack methods.
Overall (ASR)
Claude 3.5 Sonnet v2
4.390
Gemma 3n E4B Instructed
0
TAP Attack Method (ASR)
Claude 3.5 Sonnet v2
8.830
Gemma 3n E4B Instructed
0
Crescendo Attack Method (ASR)
Claude 3.5 Sonnet v2
3.810
Gemma 3n E4B Instructed
0
Zero-Shot (ASR)
Claude 3.5 Sonnet v2
0.540
Gemma 3n E4B Instructed
0
Key Highlights
- Google Gemma 3n E4B Instructed has a lower Overall (ASR).
- Google Gemma 3n E4B Instructed has a lower TAP Attack Method (ASR).
- Google Gemma 3n E4B Instructed has a lower Crescendo Attack Method (ASR).
- Google Gemma 3n E4B Instructed has a lower Zero-Shot (ASR).
Metric Radar Chart
claude-3-5-sonnet-v2
gemma-3n-e4b-instructed