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

Feedback Evaluation Alignment on Feedback Bench

82.4Kendall's Tau

Mistral-7B-Instruct + CE (GPT-4 Score)

10.22428.96247.766.438Mar 6, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.03
82.4
2025.03
82
2025.03
81.8
2025.03
79.8
2025.03
76.5
2025.03
13