Thunderpick World Championship 2026 Europe Series 2 · BO3
result vs prediction
Fortress#236 in the world · loss 0:2series probability
22%78%
probability at match start · final 0:2
STATE#137 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.
Infernopossible decider
40%57%
Fortress · 6 mapsedge STATE +17%STATE · 3 maps
AncientSTATE ban
63%50%
Fortress · 4 mapsedge Fortress +13%STATE · 4 maps
NukeSTATE pick
43%67%
Fortress · 3 mapsedge STATE +24%STATE · 5 maps
MirageFortress ban
29%63%
Fortress · 3 mapsedge STATE +34%STATE · 4 maps
CacheFortress ban
25%60%
Fortress · 4 mapsedge STATE +35%STATE · 1 map
OverpassFortress pick
67%33%
Fortress · 2 mapsedge Fortress +34%STATE · 2 maps
AnubisSTATE ban
50%40%
Fortress · 2 mapsedge Fortress +10%STATE · 1 map
Most likely veto scenario
1. BanFortress remove Mirage
2. BanSTATE remove Anubis
3. PickFortress take Overpass
4. PickSTATE take Nuke
5. BanSTATE remove Ancient
6. BanFortress remove Cache
DeciderInferno (40% / 57%)
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.
Nukeprediction correct10:13
Fortress 25%STATE 75%
The model gave 75% on STATE — the map was taken by STATE.
Ancientprediction missed2:13
Fortress 65%STATE 35%
The model gave 65% on Fortress — the map was taken by STATE.
Model check result
Model favoriteSTATE · 78%
Series resultSTATE 0:2
Series predictioncorrect
Accuracy by map1 of 2