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

Language Understanding on MMLU (5-shot, test)

74.2Accuracy

FP16

41.575250.045158.51566.9849May 9, 2023Oct 25, 2023Apr 11, 2024Sep 27, 2024Mar 15, 2025Aug 31, 2025Feb 16, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
74.2------
2025.12
72.5------
2025.12
72.5------
2026.02
72.42------
2026.02
72.23------
2026.02
72.2------
2026.02
72.18------
2026.02
72.17------
2024.12
70.96------
2024.12
70.76------
2024.12
70.66------
2024.12
70.55------
2024.12
70.53------
2024.12
70.52------
2025.12
70.5------
2024.12
70.42------
2025.12
70.3------
2024.12
70.12------
2024.12
69.91------
2024.12
69.8------
2024.12
69.77------
2024.12
69.1------
2024.12
69.1------
2024.12
69.01------
2024.12
68.75------
2024.12
68.75------
2025.12
68.39------
2025.12
67.6------
2025.12
67.5------
2024.12
66.69------
2024.12
66.45------
2025.12
65.6------
2025.12
64------
2025.12
63.2------
2025.12
63------
2025.12
62.9------
2025.12
61.5------
2025.12
61.1------
2025.12
60.72------
2025.12
60.2------
2025.12
59.9------
2025.12
59.5------
2025.12
59.2------
2025.12
58.74------
2025.12
57.42------
2025.12
56.9------
2025.12
56.3------
2025.12
56.1------
2025.12
55.9------
2025.12
55.42------
2025.12
55.13------
2026.02
54.49------
2026.02
54.35------
2026.02
54.13------
2026.02
53.97------
2026.02
53.93------
2024.12
53.11------
2024.12
53.11------
2024.12
53.07------
2024.12
53.07------
2024.12
53.03------
2024.12
52.97------
2024.12
52.96------
2024.12
52.89------
2024.12
52.88------
2024.12
52.84------
2024.12
52.81------
2024.12
52.81------
2024.12
52.79------
2024.12
52.7------
2025.12
52.7------
2024.12
52.65------
2024.12
52.6------
2025.12
52.6------
2024.12
52.59------
2024.12
52.38------
2025.12
49.9------
2024.07
49.5------
2024.07
49.3------
2024.07
49.2------
2024.07
48.4------
2024.07
48.2------
2024.07
48.2------
2024.05
488.48-----
2024.07
48------
2024.05
47.59.91-----
2024.07
47.4------
2024.05
47.39.91-----
2024.07
47.3------
2024.05
47.215.82-----
2023.05
46.9------
2024.07
46.3------
2024.07
46.3------
2024.07
46.1------
2024.12
45.6-43.351.636.352.1-
2025.12
45.16------
2024.07
45------
2024.05
43.8------
2024.05
43.3------
2025.12
42.83------
Showing 100 of 153 rows