BoolQ
Question AnsweringEnglishBenchmark
Created by Clark et al. at 2019, the BoolQ is a question answering benchmark dataset in English containing 15,942 records in JSON format.
📊 This dataset is used as an LLM benchmark. See model leaderboards →
Details
- Task
- Question Answering
- Language
- English
- Format
- JSON
- Rows / instances
- 15,942
- Creator
- Clark et al.
- Year
- 2019