Llama 3
Meta
partial detail 13 method fields published
Evaluation
Proficiency exams (GRE, LSAT, SAT, AP, GMAT)
GRE (Official Practice Test 1-2), LSAT (Preptests 71/73/80/93), SAT (8 exams, 2018 guide), AP (one official practice exam per subject), GMAT (Official Online Exam); MCQ and generation questions, image questions excluded; GRE scored 130-170, others accuracy; few-shot where >1 exam set
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.