?
arrow_backBack to match
Winline Insight · BO3
result vs prediction
HFwin 2:1
series probability
35%65%
probability at match start · final 2:1
No Sorryloss 1:2
The prediction was locked in using data as of the match start: hero winrates, form and head-to-head were computed only from games before it began. This is how the model's honest accuracy is verified.
Teams' go-to heroes · 6 months
Who plays what and how often they win. "Signature" — from 6 games with a 60%+ winrate: such a pick statistically raises the win chance.

HF

Sand King
Sand Kingsignature
Cloud · 14 games
71%
Mirana
Miranasignature
ArrOw · 13 games
77%
Dragon Knight
Dragon Knightoften banned
Cloud · 12 games
58%
Kunkka
Kunkkaoften banned
TA2000 · 11 games
45%
Bane
Bane
Malady · 8 games
50%
Shadow Shaman
Shadow Shamansignature
Kaori · 8 games
75%
Mars
Marsoften banned
Cloud · 7 games
57%
Hoodwink
Hoodwinksignature
ArrOw · 6 games
67%

No Sorry

Bane
Bane
BLACKARXANGEL · 38 games
58%
Skywrath Mage
Skywrath Mage
y0nd · 34 games
53%
Mars
Marsoften banned
LastHero- · 29 games
45%
Tiny
Tiny
Worick · 28 games
57%
Hoodwink
Hoodwink
y0nd · 27 games
44%
Storm Spirit
Storm Spiritoften banned
Worick · 26 games
58%
Ember Spirit
Ember Spiritoften banned
Worick · 23 games
52%
Keeper of the Light
Keeper of the Lightoften banned
BLACKARXANGEL · 18 games
50%
Patch meta · 3 months
The most picked heroes of the pro scene and their winrate. Picking a meta hero adds points to the team in the model.
Mars
Mars
463 picks · 636 bans
48%
Tiny
Tiny
449 picks · 434 bans
49%
Bane
Bane
446 picks · 268 bans
56%
Sand King
Sand King
409 picks · 560 bans
54%
Storm Spirit
Storm Spirit
397 picks · 637 bans
56%
Dragon Knight
Dragon Knight
394 picks · 475 bans
52%
Pangolier
Pangolier
357 picks · 554 bans
53%
Keeper of the Light
Keeper of the Light
331 picks · 656 bans
49%
Prediction components
Form (series winrate)60% vs 61%
Hero pool strength56% HF
Head-to-head0 – 0
Model total65% No Sorry
Prediction by game vs result
Probabilities were locked in using statistics as of the match start: the draft was assessed by hero comfort, counter-picks and late-game potential. We compare against the actual result.
Game 1prediction correct
HF 35%No Sorry 65%
The model gave 65% on No Sorry — the game was taken by No Sorry.
Game 2prediction missed
HF 35%No Sorry 65%
The model gave 65% on No Sorry — the game was taken by HF.
Game 3prediction missed
HF 35%No Sorry 65%
The model gave 65% on No Sorry — the game was taken by HF.
Model check result
Model favoriteNo Sorry · 65%
Series resultHF 2:1
Series predictionmissed
Accuracy by game1 of 3