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

Language Understanding on MMLU (Accuracy and Improvement Tracking)

81.31Accuracy

Baseline

56.3562.8369.3175.79Nov 28, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.11
81.31-
2025.11
80.1-
2025.11
78.4516.78
2025.11
78.3615.03
2025.11
77.14-
2025.11
76.67-
2025.11
74.2711.96
2025.11
73.0715.76
2025.11
72.51-
2025.11
70.3812.86
2025.11
63.33-
2025.11
62.31-
2025.11
61.67-
2025.11
57.52-
2025.11
57.31-