OpenAI GPT OSS 120B vs Anthropic Claude 3.5 Sonnet v1
Detailed comparison for LLMs
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 120B is the more secure of the two: GPT OSS 120B scores 15.0% and Claude 3.5 Sonnet v1 scores 16.0% 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 OpenAI GPT OSS 120B vs Anthropic Claude 3.5 Sonnet v1. 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 OpenAI GPT OSS 120B or Anthropic Claude 3.5 Sonnet v1 more secure?
On Guardion's LLM vulnerability Benchmark, OpenAI GPT OSS 120B is the more secure of the two: GPT OSS 120B scores 15.0% and Claude 3.5 Sonnet v1 scores 16.0% 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 GPT OSS 120B vs Claude 3.5 Sonnet v1?
GPT OSS 120B has a 15.0% ASR and Claude 3.5 Sonnet v1 has a 16.0% ASR — the share of adversarial prompts that succeed across zero-shot, TAP, and Crescendo attacks. Lower is safer.
How were GPT OSS 120B and Claude 3.5 Sonnet v1 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.