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

Natural Language Understanding on AGIEval

71.6Accuracy

Llama 3 405B

11.69627.24842.858.352Nov 7, 2023Mar 15, 2024Jul 23, 2024Nov 30, 2024Apr 9, 2025Aug 17, 2025Dec 25, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2024.07
71.6
2024.07
64.6
2024.07
61.5
2025.12
48.13
2024.07
47.8
2024.07
46
2024.07
42.7
2025.12
42.14
2025.12
33.34
2023.11
32.7
2024.10
29.3
2023.11
28.5
2024.10
28.5
2025.12
28.05
2024.03
27.8
2025.12
26.32
2023.11
23.2
2024.10
23.2
2023.11
21.8
2024.10
21.8
2023.11
21.2
2024.10
21.2
2024.03
19.3
2024.03
14