Thunderpick World Championship 2026 Europe Series 2 · BO3
result vs prediction
STATE#137 in the world · win 2:0series probability
77%23%
probability at match start · final 2:0
Fortress#236 in the world · loss 0:2The 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.
Infernopossible decider
63%40%
STATE · 4 mapsedge STATE +23%Fortress · 6 maps
AncientSTATE ban
50%57%
STATE · 6 mapsedge Fortress +7%Fortress · 3 maps
MirageFortress ban
67%29%
STATE · 5 mapsedge STATE +38%Fortress · 3 maps
NukeSTATE pick
70%50%
STATE · 6 mapsedge STATE +20%Fortress · 2 maps
OverpassFortress pick
38%67%
STATE · 4 mapsedge Fortress +29%Fortress · 2 maps
AnubisSTATE ban
50%40%
STATE · 2 mapsedge STATE +10%Fortress · 1 map
CacheFortress ban
50%33%
STATE · 0 mapsedge STATE +17%Fortress · 2 maps
Most likely veto scenario
1. BanSTATE remove Anubis
2. BanFortress remove Mirage
3. PickSTATE take Nuke
4. PickFortress take Overpass
5. BanFortress remove Cache
6. BanSTATE remove Ancient
DeciderInferno (63% / 40%)
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.
Cacheprediction correct13:7
STATE 64%Fortress 36%
The model gave 64% on STATE — the map was taken by STATE.
Nukeprediction correct13:5
STATE 72%Fortress 28%
The model gave 72% on STATE — the map was taken by STATE.
Model check result
Model favoriteSTATE · 77%
Series resultSTATE 2:0
Series predictioncorrect
Accuracy by map2 of 2