Thunderpick World Championship 2026 South America Series 1 · BO3
result vs prediction
LP#107 in the world · win 2:1series probability
69%31%
probability at match start · final 2:1
MIBR Academy#134 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.
Dust2MIBR Academy ban
60%38%
LP · 11 mapsedge LP +22%MIBR Academy · 4 maps
Ancientpossible decider
54%57%
LP · 9 mapsnearly even -3%MIBR Academy · 3 maps
MirageLP ban
58%50%
LP · 8 mapsedge LP +8%MIBR Academy · 4 maps
NukeLP pick
64%67%
LP · 7 mapsnearly even -3%MIBR Academy · 5 maps
InfernoMIBR Academy ban
77%50%
LP · 9 mapsedge LP +27%MIBR Academy · 0 maps
OverpassLP ban
44%43%
LP · 5 mapsnearly even +1%MIBR Academy · 3 maps
DefaultMIBR Academy pick
67%67%
LP · 2 mapsnearly even +0%MIBR Academy · 2 maps
Most likely veto scenario
1. BanLP remove Overpass
2. BanMIBR Academy remove Inferno
3. PickLP take Nuke
4. PickMIBR Academy take Default
5. BanMIBR Academy remove Dust2
6. BanLP remove Mirage
DeciderAncient (54% / 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.
Mirageprediction missed11:13
LP 55%MIBR Academy 45%
The model gave 55% on LP — the map was taken by MIBR Academy.
Ancientprediction missed13:9
LP 50%MIBR Academy 50%
The model gave 50% on MIBR Academy — the map was taken by LP.
Nukeprediction missed13:3
LP 47%MIBR Academy 53%
The model gave 53% on MIBR Academy — the map was taken by LP.
Model check result
Model favoriteLP · 69%
Series resultLP 2:1
Series predictioncorrect
Accuracy by map0 of 3