Anthropic Claude 3.7 Sonnet vs Amazon Nova Premier

Detailed comparison for LLMs

AnthropicAmazon

On Guardion's LLM vulnerability Benchmark, Amazon Nova Premier is the more secure of the two: Claude 3.7 Sonnet scores 20.3% and Nova Premier scores 20.0% 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

Nova Premier is the overall winner in this comparison!

Attack Success Rate (lower is safer)

ASR for Anthropic Claude 3.7 Sonnet vs Amazon Nova Premier. Green marks the safer model on each metric. Only the overall score is available for estimated models.

Overall (ASR)

Claude 3.7 Sonnet
20.3%
Nova Premier
20.0%

TAP Attack Method (ASR)

Claude 3.7 Sonnet
31.4%
Nova Premier

Crescendo Attack Method (ASR)

Claude 3.7 Sonnet
25.3%
Nova Premier

Key Highlights

  • Amazon Nova Premier has a lower Overall (ASR).

Security Profile

Outward is better on every axis.

OverallTAPCrescendo
Claude 3.7 Sonnet
Nova Premier
Full security profile
Anthropic Claude 3.7 Sonnet
Full security profile
Amazon Nova Premier

Frequently asked questions

Is Anthropic Claude 3.7 Sonnet or Amazon Nova Premier more secure?

On Guardion's LLM vulnerability Benchmark, Amazon Nova Premier is the more secure of the two: Claude 3.7 Sonnet scores 20.3% and Nova Premier scores 20.0% 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 Nova Premier?

Claude 3.7 Sonnet has a 20.3% ASR and Nova Premier has a 20.0% 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 Nova Premier 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.

Related Comparisons