IEM Atlanta 2026 · BO3
result vs prediction
GamerLegion#14 in the world · win 2:0series probability
41%59%
probability at match start · final 2:0
Astralis#9 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.
MirageAstralis ban
43%60%
GamerLegion · 3 mapsedge Astralis +17%Astralis · 1 map
InfernoAstralis pick
50%60%
GamerLegion · 2 mapsedge Astralis +10%Astralis · 1 map
NukeGamerLegion pick
67%40%
GamerLegion · 2 mapsedge GamerLegion +27%Astralis · 1 map
AncientAstralis ban
60%60%
GamerLegion · 1 mapnearly even +0%Astralis · 1 map
Dust2GamerLegion ban
50%50%
GamerLegion · 0 mapsnearly even +0%Astralis · 2 maps
Most likely veto scenario
1. BanGamerLegion remove Dust2
2. BanAstralis remove Mirage
3. PickGamerLegion take Nuke
4. PickAstralis take Inferno
5. BanAstralis 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 missed13:3
GamerLegion 36%Astralis 64%
The model gave 64% on Astralis — the map was taken by GamerLegion.
Ancientprediction missed13:8
GamerLegion 47%Astralis 53%
The model gave 53% on Astralis — the map was taken by GamerLegion.
Model check result
Model favoriteAstralis · 59%
Series resultGamerLegion 2:0
Series predictionmissed
Accuracy by map0 of 2