NHL Advanced Stats — GAR, WAR, Expected Goals
Hockey Alchemy is an advanced NHL analytics platform: Goals Above Replacement (GAR), Wins Above Replacement (WAR), expected goals (xG), RAPM, Elo-based power rankings, Stanley Cup odds, and prospect pipeline coverage for the 2025-26 season.
Top Skaters by GAR — 2025-26
| # | Player | Team | Pos | GAR |
|---|---|---|---|---|
| 1 | Connor McDavid | EDM | C | 34.8 |
| 2 | Nathan MacKinnon | COL | C | 29.1 |
| 3 | Nikita Kucherov | TBL | RW | 28.6 |
| 4 | Macklin Celebrini | SJS | C | 27.0 |
| 5 | Cole Caufield | MTL | LW | 25.0 |
| 6 | Jason Robertson | DAL | LW | 24.5 |
| 7 | Tage Thompson | BUF | RW | 21.2 |
| 8 | Quinn Hughes | MIN | LD | 20.1 |
| 9 | Nick Suzuki | MTL | C | 19.9 |
| 10 | Mark Scheifele | WPG | C | 19.8 |
| 11 | Dylan Guenther | UTA | RW | 19.6 |
| 12 | Alex DeBrincat | DET | LW | 19.2 |
| 13 | Clayton Keller | UTA | LW | 18.8 |
| 14 | Brandon Hagel | TBL | LW | 18.6 |
| 15 | Artemi Panarin | LAK | LW | 18.4 |
| 16 | Martin Necas | COL | RW | 18.3 |
| 17 | Evan Bouchard | EDM | RD | 18.3 |
| 18 | Jack Hughes | NJD | C | 18.3 |
| 19 | Jack Eichel | VGK | C | 18.2 |
| 20 | Leon Draisaitl | EDM | C | 18.2 |
Top Goalies by GSAx — 2025-26
| # | Goalie | Team | GSAx |
|---|---|---|---|
| 1 | Jeremy Swayman | BOS | 37.1 |
| 2 | Ilya Sorokin | NYI | 33.7 |
| 3 | Logan Thompson | WSH | 33.7 |
| 4 | Scott Wedgewood | COL | 21.3 |
| 5 | Andrei Vasilevskiy | TBL | 19.6 |
NHL Teams
Eastern Conference
Western Conference
Recent Analysis — The Lab
Talent vs Production: Why the Box Score Misleads
Two wingers score 20 goals; only one of them will do it again. The gap between what a player produced and the process underneath it is the most useful idea in hockey analytics - and it is the split our expected-goals and finishing models are built to make.
How Good Is Our WAR Model? We Ran Four Tests and Lost Two
We tested our WAR model against HockeyStats and Evolving Hockey on the four questions an honest player-value model has to answer, matched to each benchmark's published protocol. Summed to a team it loses both tests - it forecasts next season worse than simply reusing last season's standings. Measured per player it wins both, repeating at 0.77 against 0.62 and 0.46.
The Model That Earns Its Keep
Is our projection actually better than a simple average? We ran the honest test - forecasting one player's WAR next season, walk-forward across thirteen seasons - and beat the baseline that is supposed to be unbeatable. Then we ran it on goalies, where we lose.