IEM Atlanta 2026 · BO3
result vs prediction
SINNERS#45 in the world · loss 1:2series probability
33%67%
probability at match start · final 1:2
GamerLegion#19 in the world · win 2:1The 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.
MirageSINNERS pick
60%43%
SINNERS · 1 mapedge SINNERS +17%GamerLegion · 3 maps
InfernoGamerLegion pick
40%50%
SINNERS · 1 mapedge GamerLegion +10%GamerLegion · 2 maps
OverpassGamerLegion ban
60%50%
SINNERS · 1 mapedge SINNERS +10%GamerLegion · 2 maps
NukeSINNERS ban
60%60%
SINNERS · 1 mapnearly even +0%GamerLegion · 1 map
AncientSINNERS ban
50%40%
SINNERS · 0 mapsedge SINNERS +10%GamerLegion · 1 map
Dust2GamerLegion ban
60%50%
SINNERS · 1 mapedge SINNERS +10%GamerLegion · 0 maps
Most likely veto scenario
1. BanSINNERS remove Ancient
2. BanGamerLegion remove Dust2
3. PickSINNERS take Mirage
4. PickGamerLegion take Inferno
5. BanGamerLegion remove Overpass
6. BanSINNERS remove Nuke
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 correct13:10
SINNERS 69%GamerLegion 31%
The model gave 69% on SINNERS — the map was taken by SINNERS.
Infernoprediction correct9:13
SINNERS 37%GamerLegion 63%
The model gave 63% on GamerLegion — the map was taken by GamerLegion.
Nukeprediction missed8:13
SINNERS 50%GamerLegion 50%
The model gave 50% on SINNERS — the map was taken by GamerLegion.
Model check result
Model favoriteGamerLegion · 67%
Series resultGamerLegion 1:2
Series predictioncorrect
Accuracy by map2 of 3