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

General Evaluation on AGIEval

70.22Accuracy

DeepSeek-R1 (BF16)

27.652838.703949.75560.8061Nov 28, 2025Nov 29, 2025Nov 30, 2025Dec 1, 2025Dec 2, 2025Dec 3, 2025Dec 5, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
70.22
2025.12
69.58
2025.11
44.08
2025.11
38.64
2025.11
36.52
2025.11
33.58
2025.11
30.01
2025.11
29.29