?
IEM Beijing 2026 Closed Qualifier · BO3
result vs prediction
HEROIC#25 in the world · win 2:0
series probability
68%32%
probability at match start · final 2:0
Color#54 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.
Dust2Color pick
64%69%
HEROIC · 7 mapsedge Color +5%Color · 12 maps
AncientHEROIC ban
58%58%
HEROIC · 8 mapsnearly even +0%Color · 8 maps
Miragepossible decider
70%69%
HEROIC · 6 mapsnearly even +1%Color · 9 maps
InfernoHEROIC pick
64%50%
HEROIC · 10 mapsedge HEROIC +14%Color · 4 maps
CacheColor ban
33%40%
HEROIC · 5 mapsedge Color +7%Color · 6 maps
NukeColor ban
50%50%
HEROIC · 8 mapsnearly even +0%Color · 0 maps
AnubisHEROIC ban
50%60%
HEROIC · 0 mapsedge Color +10%Color · 6 maps
Most likely veto scenario
1. BanHEROIC remove Anubis
2. BanColor remove Nuke
3. PickHEROIC take Inferno
4. PickColor take Dust2
5. BanColor remove Cache
6. BanHEROIC remove Ancient
DeciderMirage (70% / 69%)
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.
Dust2prediction missed13:6
HEROIC 41%Color 59%
The model gave 59% on Color — the map was taken by HEROIC.
Infernoprediction correct13:5
HEROIC 67%Color 33%
The model gave 67% on HEROIC — the map was taken by HEROIC.
Model check result
Model favoriteHEROIC · 68%
Series resultHEROIC 2:0
Series predictioncorrect
Accuracy by map1 of 2