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

Conversational Evaluation on AlpacaEval 2.0

26.57LC

CPO

3.10769.198815.2921.3812Feb 16, 2025May 3, 2025Jul 18, 2025Oct 3, 2025Dec 18, 2025Mar 4, 2026May 20, 2026
Updated 13d ago

Evaluation Results

MethodLinks
2026.05
26.5725.151,879
2026.05
25.9123.481,810
2026.05
25.0924.61,896
2026.05
25.0124.251,895
2026.05
20.4121.481,993
2026.05
17.417.721,925
2026.05
17.29171,876
2026.05
16.415.531,830
2026.05
15.9518.942,169
2026.05
15.0616.331,998
2026.05
13.4714.221,972
2025.02
8.734.78-
2025.02
8.264.29-
2025.02
4.013.73-