HyperX Retake Season 12 · BO3
result vs prediction
WBT#108 in the world · win 2:1series probability
61%39%
probability at match start · final 2:1
NT#88 in the world · loss 1:2The prediction was locked in using data as of the match start: map winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Map veto prediction
For each map — both teams' winrate over 3 months. The model guesses who bans it and who keeps it: teams remove maps where they are weaker and pull toward their strong ones.
AnubisWBT pick
56%50%
WBT · 14 mapsedge WBT +6%NT · 0 maps
Dust2WBT ban
53%60%
WBT · 13 mapsedge NT +7%NT · 1 map
Ancientpossible decider
59%50%
WBT · 13 mapsedge WBT +9%NT · 0 maps
MirageNT pick
47%50%
WBT · 11 mapsnearly even -3%NT · 2 maps
NukeNT ban
64%40%
WBT · 7 mapsedge WBT +24%NT · 1 map
CacheWBT ban
30%60%
WBT · 6 mapsedge NT +30%NT · 1 map
DefaultNT ban
60%50%
WBT · 1 mapedge WBT +10%NT · 0 maps
Most likely veto scenario
1. BanWBT remove Cache
2. BanNT remove Nuke
3. PickWBT take Anubis
4. PickNT take Mirage
5. BanNT remove Default
6. BanWBT remove Dust2
DeciderAncient (59% / 50%)
Prediction by map vs result
Probabilities were locked in using statistics as of the match start (map winrate over the 3 months before it). We compare against the actual result of each map.
Infernoprediction missed5:13
WBT 53%NT 47%
The model gave 53% on WBT — the map was taken by NT.
Cacheprediction missed13:9
WBT 20%NT 80%
The model gave 80% on NT — the map was taken by WBT.
Dust2prediction missed13:2
WBT 43%NT 57%
The model gave 57% on NT — the map was taken by WBT.
Model check result
Model favoriteWBT · 61%
Series resultWBT 2:1
Series predictioncorrect
Accuracy by map0 of 3