Drake Bell: raw computed results
The raw ranking from the production similarity calculation (face-embedding centroid cosine → gender-cohort z-normalization). The web-opinion crown, curation, and fusion re-rank are removed.
- 1
88.4%z 4.70 - 2
88.1%z 4.68 - 3
85%z 4.43 - 4
83.6%z 4.31 - 5
82.6%z 4.23 - 6
82.5%z 4.22 - 7
80.8%z 4.08 - 8
75.6%z 3.97 - 9
71.8%z 3.93 - 10
69.6%z 3.90 - 11
62.3%z 3.82 - 12
57.8%z 3.77 - 13
51.8%z 3.71 - 14
51.3%z 3.70 - 15
46.3%z 3.55 - 16
46.1%z 3.55 - 17
46%z 3.53 - 18
45.9%z 3.53 - 19
45.7%z 3.52 - 20
44%z 3.41 - 21
44%z 3.41 - 22
43.9%z 3.40 - 23
43.8%z 3.40 - 24
43.6%z 3.38 - 25
43.4%z 3.37 - 26
43.4%z 3.37 - 27
43.4%z 3.37 - 28
43.3%z 3.36 - 29
42.7%z 3.32 - 30
42.6%z 3.32 - 31
42.5%z 3.31 - 32
42.4%z 3.31 - 33
41.8%z 3.26 - 34
41.6%z 3.25 - 35
41.6%z 3.25 - 36
41.5%z 3.24 - 37
41.4%z 3.24 - 38
41.1%z 3.22 - 39
41%z 3.22 - 40
40.9%z 3.20 - 41
40.8%z 3.20 - 42
40.8%z 3.20 - 43
40.6%z 3.19 - 44
40.4%z 3.18 - 45
40.4%z 3.17 - 46
40.3%z 3.17 - 47
40.2%z 3.16 - 48
39.8%z 3.13 - 49
39.4%z 3.11 - 50
39.4%z 3.11