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

site-success regression on RelBench rel-trial (test)

5.5R2 Score

RDBLearn

-6.876-3.663-0.452.763Oct 7, 2025Oct 28, 2025Nov 19, 2025Dec 11, 2025Jan 1, 2026Jan 23, 2026Feb 14, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.02
5.5
2026.02
5.2
2025.10
5.1
2025.10
4.5
2026.02
2.6
2025.10
2.6
2025.10
1.4
2025.10
-6.4