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

Accuracy Evaluation on ROCStories (Writing)

76.3Accuracy

ES + TT-MV

16.81232.25647.763.144Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
76.3
2026.03
68.1
2026.03
66
2026.03
65.8
2026.03
65.7
2026.03
65.2
2026.03
64.8
2026.03
64.7
2026.03
64.5
2026.03
64.5
2026.03
64.5
2026.03
64.4
2026.03
64
2026.03
63.5
2026.03
63.2
2026.03
62.2
2026.03
62.2
2026.03
60.2
2026.03
59.1
2026.03
59
2026.03
57.8
2026.03
57.3
2026.03
56.5
2026.03
56.3
2026.03
55
2026.03
55
2026.03
54.7
2026.03
54
2026.03
53.6
2026.03
53.2
2026.03
51.8
2026.03
51.8
2026.03
50
2026.03
49
2026.03
48.5
2026.03
46.7
2026.03
43.5
2026.03
42.2
2026.03
42.2
2026.03
32.2
2026.03
32
2026.03
30.9
2026.03
30.5
2026.03
24.1
2026.03
22
2026.03
20.3
2026.03
19.5
2026.03
19.1