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

Multiple-choice Question Answering on MMLU (test)

86.4Accuracy

GPT-4

22.4439.04555.6572.255Mar 15, 2023Jun 23, 2023Oct 1, 2023Jan 10, 2024Apr 19, 2024Jul 28, 2024Nov 6, 2024
Updated 3d ago

Evaluation Results

MethodLinks
2023.03
86.4-----
2023.03
75.2-----
2023.03
70.7-----
2023.03
70-----
2024.11
26.59-----
2024.11
25.62-----
2024.11
25.62-----
2024.11
25.55-----
2024.11
25.51-----
2024.11
25.3-----
2024.11
25.16-----
2024.11
24.9-----
2022.04
-67.563.654.979.373.9
2022.04
-25.325.623.824.127.8
2022.04
-53.759.541.962.755.8
2022.04
-69.37755.68169.6