Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Natural Language Processing on T0 MTest11 P3 (test)

61.4Accuracy

Full FT

40.70446.07751.4556.823Jun 18, 2024
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
61.41
2024.06
60.3-
2024.06
601.9
2024.06
58.90.88
2024.06
58.80.88
2024.06
58.21.9
2024.06
57.713.2
2024.06
57.61
2024.06
56.81
2024.06
56.61
2024.06
56.2-
2024.06
55.21.9
2024.06
54.70.88
2024.06
54.513.2
2024.06
53.80.88
2024.06
53.713.2
2024.06
53.41.9
2024.06
53.24.1
2024.06
53.11
2024.06
52.613.2
2024.06
52.41
2024.06
52.41
2024.06
52.41
2024.06
51.91
2024.06
511.9
2024.06
50.80.88
2024.06
50.11
2024.06
49.913.2
2024.06
49.11
2024.06
48.64.1
2024.06
47.64.1
2024.06
47.21
2024.06
471.9
2024.06
45.60.88
2024.06
45.51
2024.06
44.61
2024.06
44.613.2
2024.06
44.24.1
2024.06
44.11
2024.06
43.91
2024.06
42.61
2024.06
41.51