Anthropic Claude 3.5 Sonnet v1 vs OpenAI GPT OSS 120B
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 120B is the more secure of the two: Claude 3.5 Sonnet v1 scores 16.0% and GPT OSS 120B scores 15.0% 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
GPT OSS 120B is the overall winner in this comparison!
Attack Success Rate (lower is safer)
ASR for Anthropic Claude 3.5 Sonnet v1 vs OpenAI GPT OSS 120B. 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
- OpenAI GPT OSS 120B 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).
Security Profile
Outward is better on every axis.
Frequently asked questions
Is Anthropic Claude 3.5 Sonnet v1 or OpenAI GPT OSS 120B more secure?
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 120B is the more secure of the two: Claude 3.5 Sonnet v1 scores 16.0% and GPT OSS 120B scores 15.0% 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 3.5 Sonnet v1 vs GPT OSS 120B?
Claude 3.5 Sonnet v1 has a 16.0% ASR and GPT OSS 120B has a 15.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were Claude 3.5 Sonnet v1 and GPT OSS 120B 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.