Новый проект
xinxuxin/keystone-bench
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.
- Stars
- ★ 82
- Forks
- ⑂ 1
- Язык
- Python
- Статус
- В канале 1 янв. 1 г.
AI-разбор
A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.