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

Knowledge-Orthogonal Reasoning on KOR-Bench

56.56Overall Score (%)

Base Model

18.038428.039238.0448.0408May 5, 2026
Updated 28d ago

Evaluation Results

MethodLinks
2026.05
56.561,1731,1631,163
2026.05
52.641,1861,1821,182
2026.05
32.961,4381,4911,321
2026.05
32.081,4681,4291,429
2026.05
31.761,3521,3821,304
2026.05
27.761,2251,3241,193
2026.05
23.441,1781,2931,169
2026.05
22.561,5801,5331,533
2026.05
22.169421,151960
2026.05
21.681,5981,5561,556
2026.05
19.69101,117885
2026.05
19.521,7151,6811,681