Thunderpick World Championship 2026 South America Series 2 · BO3
result vs prediction
LP#107 in the world · loss 0:2series probability
64%36%
probability at match start · final 0:2
Imperial#51 in the world · win 2:0The 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.
InfernoLP pick
67%69%
LP · 17 mapsnearly even -2%Imperial · 9 maps
Dust2LP ban
61%62%
LP · 14 mapsnearly even -1%Imperial · 9 maps
MirageImperial pick
50%50%
LP · 10 mapsnearly even +0%Imperial · 10 maps
Nukepossible decider
67%67%
LP · 11 mapsnearly even +0%Imperial · 5 maps
AncientImperial ban
59%50%
LP · 13 mapsedge LP +9%Imperial · 0 maps
OverpassImperial ban
44%50%
LP · 5 mapsedge Imperial +6%Imperial · 2 maps
AnubisLP ban
50%60%
LP · 0 mapsedge Imperial +10%Imperial · 6 maps
Most likely veto scenario
1. BanLP remove Anubis
2. BanImperial remove Ancient
3. PickLP take Inferno
4. PickImperial take Mirage
5. BanImperial remove Overpass
6. BanLP remove Dust2
DeciderNuke (67% / 67%)
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.
Mirageprediction correct11:13
LP 47%Imperial 53%
The model gave 53% on Imperial — the map was taken by Imperial.
Infernoprediction missed4:13
LP 50%Imperial 50%
The model gave 50% on LP — the map was taken by Imperial.
Model check result
Model favoriteLP · 64%
Series resultImperial 0:2
Series predictionmissed
Accuracy by map1 of 2