P3B3 Benchmark
Explore score history ↗P3B3 is an expert-curated benchmark of conversational prompts for evaluating variety bias and controllability in LLMs across European and Brazilian Portuguese.
- Released
- 2026-06-15
- Institutions
- Laboratório para a Ciência da Computação e Informática · Universidade Nova de Lisboa
- Evaluates
- General AI, Safety & Trustworthiness, cs.CL
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
P3B3 paper
No reported scores are on record for this benchmark yet.