BLAST Open Porto 2026 · BO3
result vs prediction
G2#7 in the world · win 2:1series probability
54%46%
probability at match start · final 2:1
Aurora#6 in the world · loss 1:2The 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.
AnubisAurora pick
40%62%
G2 · 6 mapsedge Aurora +22%Aurora · 9 maps
Miragepossible decider
69%60%
G2 · 9 mapsedge G2 +9%Aurora · 6 maps
Dust2G2 ban
36%55%
G2 · 7 mapsedge Aurora +19%Aurora · 7 maps
InfernoG2 pick
82%63%
G2 · 7 mapsedge G2 +19%Aurora · 4 maps
AncientAurora ban
33%40%
G2 · 8 mapsedge Aurora +7%Aurora · 1 map
NukeG2 ban
50%69%
G2 · 0 mapsedge Aurora +19%Aurora · 9 maps
CacheAurora ban
50%50%
G2 · 2 mapsnearly even +0%Aurora · 4 maps
Most likely veto scenario
1. BanG2 remove Nuke
2. BanAurora remove Ancient
3. PickG2 take Inferno
4. PickAurora take Anubis
5. BanAurora remove Cache
6. BanG2 remove Dust2
DeciderMirage (69% / 60%)
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.
Anubisprediction correct7:13
G2 27%Aurora 73%
The model gave 73% on Aurora — the map was taken by Aurora.
Infernoprediction correct19:16
G2 75%Aurora 25%
The model gave 75% on G2 — the map was taken by G2.
Mirageprediction correct13:1
G2 60%Aurora 40%
The model gave 60% on G2 — the map was taken by G2.
Model check result
Model favoriteG2 · 54%
Series resultG2 2:1
Series predictioncorrect
Accuracy by map3 of 3