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

Factuality Evaluation on MMLU

82.4EM

GPT-4

29.46443.20756.9570.693Jun 7, 2023
Updated 4d ago

Evaluation Results

MethodLinks
2023.06
82.4
2023.06
67.9
2023.06
61.3
2023.06
60.4
2023.06
59.2
2023.06
58.7
2023.06
57.7
2023.06
54.6
2023.06
52.3
2023.06
52
2023.06
49.3
2023.06
49.2
2023.06
44.8
2023.06
42.3
2023.06
41.8
2023.06
31.5