Thunderpick World Championship 2026 South America Series 1 · BO3
result vs predictionseries probability
37%63%
probability at match start · final 0:2
LP#107 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.
Dust2Fake do Biru pick
56%60%
Fake do Biru · 12 mapsnearly even -4%LP · 11 maps
MirageFake do Biru ban
38%54%
Fake do Biru · 4 mapsedge LP +16%LP · 9 maps
InfernoLP pick
57%77%
Fake do Biru · 3 mapsedge LP +20%LP · 9 maps
Nukepossible decider
75%67%
Fake do Biru · 4 mapsedge Fake do Biru +8%LP · 8 maps
AncientFake do Biru ban
50%57%
Fake do Biru · 0 mapsedge LP +7%LP · 10 maps
OverpassLP ban
50%44%
Fake do Biru · 2 mapsedge Fake do Biru +6%LP · 5 maps
AnubisLP ban
43%50%
Fake do Biru · 3 mapsedge LP +7%LP · 0 maps
Most likely veto scenario
1. BanFake do Biru remove Ancient
2. BanLP remove Anubis
3. PickFake do Biru take Dust2
4. PickLP take Inferno
5. BanLP remove Overpass
6. BanFake do Biru remove Mirage
DeciderNuke (75% / 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.
Dust2prediction correct6:13
Fake do Biru 49%LP 51%
The model gave 51% on LP — the map was taken by LP.
Infernoprediction correct10:13
Fake do Biru 26%LP 74%
The model gave 74% on LP — the map was taken by LP.
Model check result
Model favoriteLP · 63%
Series resultLP 0:2
Series predictioncorrect
Accuracy by map2 of 2