Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Selection on Open LLM Leaderboard Scientific Discovery scenario K = 42 models

64Main Objective

PrefUCB

52.66455.60758.5561.493Jun 20, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
6443.672.2
59.346.364.6
2026.06
56.753.958.7
2026.06
53.151.155.5