Anthropic Claude 3.5 Sonnet v1 vs Moonshot AI Kimi K2-Thinking-0905
Detailed comparison for LLMs
AnthropicMoonshot AI
Head-to-Head Overview
Claude 3.5 Sonnet v1 is the overall winner in this comparison!
LLM Metric
Comparison of Attack Success Rate (ASR) metrics for Anthropic Claude 3.5 Sonnet v1 and Moonshot AI Kimi K2-Thinking-0905 across the three attack methods.
Overall (ASR)
Claude 3.5 Sonnet v1
16.010
Kimi K2-Thinking-0905
100.000
TAP Attack Method (ASR)
Claude 3.5 Sonnet v1
28.390
Kimi K2-Thinking-0905
100.000
Crescendo Attack Method (ASR)
Claude 3.5 Sonnet v1
19.310
Kimi K2-Thinking-0905
100.000
Zero-Shot (ASR)
Claude 3.5 Sonnet v1
0.350
Kimi K2-Thinking-0905
100.000
Key Highlights
Anthropic Claude 3.5 Sonnet v1 has a lower Overall (ASR).
Anthropic Claude 3.5 Sonnet v1 has a lower TAP Attack Method (ASR).
Anthropic Claude 3.5 Sonnet v1 has a lower Crescendo Attack Method (ASR).
Anthropic Claude 3.5 Sonnet v1 has a lower Zero-Shot (ASR).