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

LMSYS Search Arena

Benchmarks

Task NameDataset NameSOTA ResultTrend
Human Alignment CorrelationLMSYS Search Arena (test)
Pearson Correlation0.74
7
Search-based Question AnsweringLMSYS Search Arena
Elo Rating1,201
6
Showing 2 of 2 rows