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

LLM Evaluation on AlpacaEval 2.0

51.32LC Win Rate

SpecEM

4.915216.962629.0141.0574Dec 10, 2024Feb 23, 2025May 10, 2025Jul 24, 2025Oct 8, 2025Dec 22, 2025Mar 8, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2024.12
51.3254.52---
2024.12
49.241.04---
2024.12
49.0650.84---
2024.12
48.4644.27---
2024.12
46.9851.24---
2024.12
43.8243.54---
2024.12
38.1----
2024.12
34.429.39---
2025.09
14.62-14.78-1,909
2025.09
12.89-13.42-2,004
2025.09
11.23-11.3-1,825
2025.09
11.07-11.06-1,864
2025.09
10.95-11.43-1,881
2025.09
10.38-10.56-1,869
2026.03
7.7-2--
2026.03
6.7-1.9--
2026.06
---85.7-
---86.2-
2026.06
---90.8-