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

Long-context Understanding on RULER 16k (test)

93.5RULER Score

IndexMem

12.27633.36354.4575.537May 25, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
93.5
2026.05
93.4
2026.05
93.4
2026.05
93.4
2026.05
93.4
2026.05
93.4
2026.05
93.4
2026.05
92.9
2026.05
92.9
2026.05
92.9
2026.05
92.9
2026.05
92.9
2026.05
92.9
2026.05
92.8
2026.05
91.6
2026.05
90.9
2026.05
90.1
2026.05
89.4
2026.05
89.2
2026.05
88.9
2026.05
88.7
2026.05
88.3
2026.05
86.8
2026.05
86.1
2026.05
86.1
2026.05
86.1
2026.05
86.1
2026.05
86.1
2026.05
86.1
2026.05
86
2026.05
85.2
2026.05
82.9
2026.05
82
2026.05
81.7
2026.05
81.5
2026.05
81
2026.05
80
2026.05
77.9
2026.05
77.7
2026.05
77.5
2026.05
76.2
2026.05
76.1
2026.05
75.9
2026.05
74.5
2026.05
74.3
2026.05
73.8
2026.05
72.2
2026.05
70.1
2026.05
69.5
2026.05
68.7
2026.05
68.5
2026.05
68.4
2026.05
68
2026.05
66.9
2026.05
66.4
2026.05
66
2026.05
62.8
2026.05
62.5
2026.05
62.3
2026.05
61
2026.05
59.3
2026.05
59.2
2026.05
56
2026.05
56
2026.05
53.4
2026.05
53.1
2026.05
52.9
2026.05
52.4
2026.05
49.5
2026.05
47.8
2026.05
47.7
2026.05
45
2026.05
43.1
2026.05
41.7
2026.05
41
2026.05
39.6
2026.05
36.5
2026.05
33.2
2026.05
32.6
2026.05
27.1
2026.05
26.8
2026.05
26.2
2026.05
25.6
2026.05
25.5
2026.05
24.1
2026.05
22.9
2026.05
22
2026.05
21.3
2026.05
18
2026.05
15.4