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

General Instruction Following on WildBench

92.6Score

GenRM-R-Align-14B

-4.858420.443345.74571.0467Apr 11, 2025May 31, 2025Jul 20, 2025Sep 8, 2025Oct 28, 2025Dec 17, 2025Feb 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
92.6
2026.02
89.2
2026.02
88.1
2026.02
84.3
2026.02
83.7
2026.02
79.4
2026.02
72.8
2026.01
68.5
2026.01
66.8
2026.01
66.3
2026.01
65.1
2026.01
63.2
2026.01
56.8
2026.01
56.8
2026.01
49.1
2026.01
42.2
2025.04
2.68
2025.04
1.44
-1.11