?
IEM Cologne Major 2026 Stage 1 · BO1
result vs prediction
MIBR#12 in the world · win 16:14
series probability
59%41%
probability at match start · final 16:14
TYLOO#33 in the world · loss 14:16
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.
AncientTYLOO ban
50%31%
MIBR · 2 mapsedge MIBR +19%TYLOO · 9 maps
MirageTYLOO ban
50%69%
MIBR · 2 mapsedge TYLOO +19%TYLOO · 9 maps
Infernopossible decider
33%67%
MIBR · 2 mapsedge TYLOO +34%TYLOO · 8 maps
OverpassMIBR ban
40%60%
MIBR · 1 mapedge TYLOO +20%TYLOO · 6 maps
NukeMIBR ban
50%67%
MIBR · 0 mapsedge TYLOO +17%TYLOO · 5 maps
AnubisTYLOO ban
60%60%
MIBR · 1 mapnearly even +0%TYLOO · 1 map
DefaultMIBR ban
50%60%
MIBR · 0 mapsedge TYLOO +10%TYLOO · 1 map
Most likely veto scenario
1. BanMIBR remove Nuke
2. BanTYLOO remove Ancient
3. BanMIBR remove Overpass
4. BanTYLOO remove Anubis
5. BanMIBR remove Default
6. BanTYLOO remove Mirage
DeciderInferno (33% / 67%)
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.
Nukeprediction missed16:14
MIBR 33%TYLOO 67%
The model gave 67% on TYLOO — the map was taken by MIBR.
Model check result
Model favoriteMIBR · 59%
Series resultMIBR 16:14
Series predictioncorrect
Accuracy by map0 of 1