Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Instruction Following on AlpacaEval Helpsteer2 (test)

29.64LC Win Rate

OTPO

17.503220.654123.80526.9559May 24, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.05
29.6429.541,991
2025.05
28.5528.541,956
2025.05
27.9127.451,945
2025.05
26.9527.161,991
2025.05
26.7727.251,984
2025.05
22.9222.571,899
2025.05
20.521.252,000
2025.05
20.2920.21,939
2025.05
19.9920.541,970
2025.05
19.0319.721,996
2025.05
18.5819.652,018
2025.05
17.9719.342,041