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

STEM Task Evaluation on MMLU Math

51.81Accuracy

Re-TASK (Lite)

18.654827.262435.8744.4776Aug 13, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.08
51.817.61
2024.08
49.422.51
2024.08
48.194.23
2024.08
45.65-0.6
2024.08
43.847.61
2024.08
41.674.23
2024.08
40.58-
2024.08
40.58-2.3
2024.08
36.96-
2024.08
36.522.51
2024.08
34.42-0.6
2024.08
30.43-2.3
2024.08
28.997.61
2024.08
24.644.23
2024.08
24.28-
2024.08
23.91-2.3
2024.08
23.412.51
2024.08
19.93-0.6