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

Mathematical Reasoning on MMLU STEM

77.1Accuracy

GPT-4

44.54852.99961.4569.901May 23, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.05
77.1
2024.05
71.8
2024.05
71.5
2024.05
68.8
2024.05
66.9
2024.05
65.7
2024.05
64
2024.05
63.5
2024.05
62.3
2024.05
62.3
2024.05
60.4
2024.05
57.9
2024.05
57.7
2024.05
56.1
2024.05
54.9
2024.05
54.4
2024.05
54.3
2024.05
53.6
2024.05
49.5
2024.05
45.8