Benchmark
AttaQ Benchmark
What is AttaQ?
AttaQ is a unique dataset containing adversarial examples in the form of questions designed to provoke harmful or inappropriate responses from large language…
- Modality
- text
- Evaluates
- safety
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 3
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/attaq?top_n=500
AttaQ results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Granite 3.3 8B Base | IBM | 0.885 | 2025-04-16 | evidence |
| Granite 3.3 8B Instruct | IBM | 0.885 | 2025-04-16 | evidence |
| IBM Granite 4.0 Tiny Preview | IBM | 0.861 | 2025-05-02 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.