No spin here — this is every captain and transfer call I’ve made, scored against reality.
2026-27 · GW2–4: early-season model · GW5–8: model v6-phase9
Our captain landed in the top 5 on 4 of 7 gameweeks
We've captured 73.0% of the perfect-captain points pool this season.
coachme captain
73.0%
Share of optimal captain points we captured.
Always-Haaland baseline
52.5%
What a “captain Haaland every week” strategy would have captured.
We're beating the naive baseline by 20.5%.
Transfer net
+0.14
Average points the player we moved IN beat the player we moved OUT by.
Hit take rate
14.3%
How often a recommended -4 hit produced net-positive points.
Bench order
0.57 / 3
Bench positions ordered correctly, averaged across GWs.
Which model made these calls
The first gameweeks of a season run on an early-season model, before our main model has enough matches to learn from. Each gameweek is scored against the model you were shown that week.
GW2–4: early-season model
Captain points captured 61.8% · top 5 hit rate 33.3%
GW5–8: model v6-phase9
Captain points captured 82.1% · top 5 hit rate 75.0%
Per gameweek
Our captain points vs the optimal captain points each GW.
Calibration
When we predict a bucket of expected points, what do players in that bucket actually score on average? The line should hug the diagonal. This and the section below cover GW5–8: model v6-phase9, the model serving now.
Are our predictions trustworthy?
Per-player xP is structurally flat — the ensemble shrinks toward the mean. We publish the three metrics below so you can see exactly how spread out our predictions are, how often actuals stay under our ceiling, and whether each predicted-xP bucket pays off.
Not enough post-v6-phase9 predictions with actuals yet to measure calibration. Come back after the next scored gameweek.
What we got wrong
The three gameweeks where our captain call missed the top scorer by the most. No spin — here they are.
GW 3
We captained B.Fernandes. They scored 2.
Top score: 15
missed by 13 pts
GW 7
We captained De Cuyper. They scored 6.
Top score: 15
missed by 9 pts
GW 4
We captained Haaland. They scored 9.
Top score: 17
missed by 8 pts
Like what you see? Sign up and I’ll bring these calls straight to you every gameweek.
Want these picks delivered every gameweek?
Sign up free — captain pick, transfer ideas, push notifications before the deadline.
Sign Up FreeLast updated 26 Oct 2026, 16:15