safety benchmark
AttaQ
AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.
Updated Aug 11, 2026
Models3
Model coverage3
MetricScore
EvidenceB
AttaQ Ranking
Higher score ranks better on this benchmark.
| 1 | IB | 88.5% | 100.0% | 3 | C | |
| 2 | IB | 88.5% | 50.0% | 3 | C | |
| 3 | IB | 86.1% | 0.0% | 3 | C |
AttaQ Score Distribution
A closer view of the leading scores on this benchmark.
AttaQ Highlights
The leading models and scores on this benchmark.
What is AttaQ?
What AttaQ measures and how its scores work.
AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AttaQ
- Modality
- text
- Primary category
- safety
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- attaq|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AttaQ.
Which model scores highest on AttaQ?
Granite 3.3 8B Base is currently ranked first with 88.5%.
What does AttaQ measure?
AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language models. The benchmark evaluates safety vulnerabilities by using specialized clustering techniques that analyze both the semantic similarity of input attacks and the harmfulness of model responses, facilitating targeted improvements to model safety mechanisms.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.