Anthropic Claude 3.7 Sonnet vs Meta Llama 3.1 405B Instruct
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, Anthropic Claude 3.7 Sonnet is the more secure of the two: Claude 3.7 Sonnet scores 20.3% and Llama 3.1 405B Instruct scores 36.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
Head-to-Head Overview
Claude 3.7 Sonnet is the overall winner in this comparison!
Attack Success Rate (lower is safer)
ASR for Anthropic Claude 3.7 Sonnet vs Meta Llama 3.1 405B Instruct. Green marks the safer model on each metric. Only the overall score is available for estimated models.
Overall (ASR)
TAP Attack Method (ASR)
Crescendo Attack Method (ASR)
Zero-Shot (ASR)
Key Highlights
- Anthropic Claude 3.7 Sonnet has a lower Overall (ASR).
- Anthropic Claude 3.7 Sonnet has a lower TAP Attack Method (ASR).
- Anthropic Claude 3.7 Sonnet has a lower Crescendo Attack Method (ASR).
Security Profile
Outward is better on every axis.
Frequently asked questions
Is Anthropic Claude 3.7 Sonnet or Meta Llama 3.1 405B Instruct more secure?
On Guardion's LLM vulnerability Benchmark, Anthropic Claude 3.7 Sonnet is the more secure of the two: Claude 3.7 Sonnet scores 20.3% and Llama 3.1 405B Instruct scores 36.0% on attack success rate (ASR) (lower is better). One or both scores are estimated from public safety evaluations pending a Guardion benchmark run.
What is the attack success rate (ASR) of Claude 3.7 Sonnet vs Llama 3.1 405B Instruct?
Claude 3.7 Sonnet has a 20.3% ASR and Llama 3.1 405B Instruct has a 36.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were Claude 3.7 Sonnet and Llama 3.1 405B Instruct tested?
Both were red-teamed with the HarmBench framework across zero-shot, TAP (Tree of Attacks with Pruning), and Crescendo multi-turn attacks, scored by Attack Success Rate.