Running
6
Responsible AI Benchmark
🏆
Evaluating safety, robustness & fairness for real use-cases
AI for Public Good
Evaluating safety, robustness & fairness for real use-cases
Detect off‑topic content in a conversation
Detect system prompt leakage in LLM output
Localised Multilingual Moderation Classifier for Singapore
Multimodal search & retrieval-based biodiversity recognition