Brad Leeb: 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
88.6%z 4.72 - 2
86.5%z 4.55 - 3
82%z 4.18 - 4
80.4%z 4.05 - 5
62.9%z 3.83 - 6
62.9%z 3.83 - 7
57.3%z 3.77 - 8
55.4%z 3.75 - 9
53.7%z 3.73 - 10
49.5%z 3.68 - 11
47.9%z 3.66 - 12
47.8%z 3.65 - 13
47.7%z 3.64 - 14
47.6%z 3.64 - 15
47.3%z 3.62 - 16
46.7%z 3.58 - 17
45.1%z 3.48 - 18
44.3%z 3.43 - 19
43.8%z 3.40 - 20
43.5%z 3.38 - 21
43.3%z 3.36 - 22
43.2%z 3.35 - 23
42.9%z 3.33 - 24
42.8%z 3.33 - 25
42.7%z 3.32 - 26
42.6%z 3.32 - 27
42.6%z 3.31 - 28
42.1%z 3.28 - 29
41.9%z 3.27 - 30
41.7%z 3.26 - 31
41.6%z 3.25 - 32
41.5%z 3.25 - 33
41.1%z 3.22 - 34
41%z 3.21 - 35
40.8%z 3.20 - 36
40.4%z 3.17 - 37
40.4%z 3.17 - 38
40.1%z 3.15 - 39
39.9%z 3.14 - 40
39.8%z 3.14 - 41
39.6%z 3.12 - 42
39.3%z 3.10 - 43
39.2%z 3.09 - 44
38.9%z 3.08 - 45
38.9%z 3.08 - 46
38.8%z 3.07 - 47
38.6%z 3.06 - 48
38.6%z 3.06