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

LLM Alignment on AlpacaEval 2.0

61.52LC Win Rate

GRM + LP

24.672834.238943.80553.3711Apr 30, 2026May 2, 2026May 5, 2026May 8, 2026May 11, 2026May 14, 2026May 17, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.04
61.5250.041,400
2026.04
60.9654.561,611
2026.04
60.651.321,522
2026.04
59.9255.551,659
2026.04
59.1956.621,739
2026.04
58.9861.511,919
2026.04
58.7757.241,779
2026.04
57.7660.521,923
2026.04
55.3258.561,931
2026.05
52.2--
2026.05
51.74--
2026.05
48.79--
2026.04
48.3740.191,507
2026.04
44.4940.181,571
2026.04
44.0346.881,881
2026.04
43.1147.071,929
2026.05
42.9--
2026.04
41.8950.132,201
2026.04
40.6349.612,201
2026.04
39.7747.592,119
2026.04
39.4951.192,345
2026.05
38.38--
2026.04
37.7849.742,368
2026.04
37.5347.472,193
2026.04
26.0932.061,968