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

Chat Evaluation on AlpacaEval LC 2

74.11Score

DictaLM 3.0 24B-Think

5.043622.974340.90558.8357Dec 15, 2025Dec 23, 2025Dec 31, 2025Jan 8, 2026Jan 16, 2026Jan 24, 2026Feb 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
74.11
73.5
2025.12
73.5
2026.02
65.5
2025.12
60.5
58
2025.12
52.1
2025.12
50.6
2026.02
50.57
2025.12
49.8
2025.12
43.9
2025.12
43.3
41.22
2025.12
40.9
2025.12
28.6
24
2025.12
23
2025.12
21.8
2025.12
18.3
2026.02
17.45
8.6
2025.12
8.1
7.7