?
IEM Atlanta 2026 · BO3
result vs prediction
GamerLegion#19 in the world · win 2:0
series probability
62%38%
probability at match start · final 2:0
Liquid#27 in the world · loss 0:2
The 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.
InfernoGamerLegion pick
50%60%
GamerLegion · 4 mapsedge Liquid +10%Liquid · 1 map
MirageLiquid pick
33%50%
GamerLegion · 5 mapsedge Liquid +17%Liquid · 0 maps
AncientGamerLegion ban
50%50%
GamerLegion · 2 mapsnearly even +0%Liquid · 2 maps
Dust2GamerLegion ban
50%33%
GamerLegion · 0 mapsedge GamerLegion +17%Liquid · 2 maps
NukeLiquid ban
67%50%
GamerLegion · 2 mapsedge GamerLegion +17%Liquid · 0 maps
OverpassLiquid ban
50%50%
GamerLegion · 2 mapsnearly even +0%Liquid · 0 maps
Most likely veto scenario
1. BanGamerLegion remove Dust2
2. BanLiquid remove Overpass
3. PickGamerLegion take Inferno
4. PickLiquid take Mirage
5. BanLiquid remove Nuke
6. BanGamerLegion remove Ancient
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 missed13:9
GamerLegion 31%Liquid 69%
The model gave 69% on Liquid — the map was taken by GamerLegion.
Nukeprediction correct13:6
GamerLegion 69%Liquid 31%
The model gave 69% on GamerLegion — the map was taken by GamerLegion.
Model check result
Model favoriteGamerLegion · 62%
Series resultGamerLegion 2:0
Series predictioncorrect
Accuracy by map1 of 2