Llama internal safety benchmarks (Meta)
Only in system cards
Models face Meta's adversarial and borderline prompts per capability and language. Scored as violation rate and false refusal rate.
In-house Meta evaluation with over 4,000 prompts per capability or language. Llama 3 shows results only in charts.
Made by Meta Released Jul 2024 Refusing harmful requests Tasks kept private Last in a system card Nov 2024
Last model added Nov 2024
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
2
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Llama internal safety benchmarks (Meta) yet.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
2 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 23 Nov 2024 |  Llama 3.1-70B technical report | Internal violation rate and false refusal rate, Llama 3 70B with and without Llama Guard, chart only with no printed values (Figure 21) | Safety | |
| 23 Nov 2024 | Llama 3.1-405B technical report | Internal violation and false refusal rates by language, tool use and long context, with and without Llama Guard, charts only with no printed values (Figures 19 to 21) | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy. Muse Spark Open 98.1%
- Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%