The same production stack priced under 4 course readings, against the bookmaker's pre-stage line. Each scenario is one opinion about what kind of day this is; the results section settles the argument.
The fork
Course profile is an input the model can't see from a map — it's set from reference races (or overridden by hand). Different readings redistribute the same probability mass across rider types.
The board
Blend win probability per scenario (cascade × LambdaRank, DNF-adjusted at the pricing layer), next to the devigged Kambi (Unibet) win line captured the morning before the stage. "Max edge" compares the most favourable scenario against the book — treat it as scenario-conditional, not a free bet.
Read "Max edge" as directional, not as a price. The blend is a set of per-rider marginals and does not sum to one book — across this field each reading totals GC summit 130%, Climbers' wall 127%, Hindsight (post-hoc) 134% — while the devigged book column sums to exactly 100%. Putting the two side by side flatters the model, and Max edge is inflated by about that factor: divide a rider's probability by his reading's total before calling anything an edge. Of our heads only the LambdaRank one is natively book-preserving.
| Rider | Team | GC summit | Climbers' wall | Break survives | Hindsight (post-hoc) | Book odds | Book devig | Max edge |
|---|---|---|---|---|---|---|---|---|
| Pogacar Tadej | UAE Team Emirates-XRG | 44.6% | 45.7% | – | 45.6% | 1.60 | 38.8% | +7.0pp |
| Vingegaard Jonas | Team Visma | Lease a Bike | 14.0% | 10.3% | – | 14.3% | 17.00 | 3.6% | +10.7pp |
| Evenepoel Remco | Red Bull-BORA-hansgrohe | 13.7% | 12.0% | – | 10.2% | 101.00 | 0.6% | +13.1pp |
| Lipowitz Florian | Red Bull-BORA-hansgrohe | 9.2% | 7.5% | – | 12.0% | 81.00 | 0.8% | +11.3pp |
| Seixas Paul | Decathlon CMA CGM Team | 8.3% | 7.9% | – | 10.0% | 34.00 | 1.8% | +8.2pp |
| del Toro Isaac | UAE Team Emirates-XRG | 6.3% | 6.6% | – | 6.1% | 13.00 | 4.8% | +1.8pp |
| Ayuso Juan | Lidl-Trek | 2.9% | 1.9% | – | 3.4% | 101.00 | 0.6% | +2.8pp |
| Martinez Lenny | Bahrain Victorious | 2.4% | 2.6% | – | 1.9% | 41.00 | 1.5% | +1.1pp |
| Hindley Jai | Red Bull-BORA-hansgrohe | 1.8% | 2.0% | 7.0% | 1.8% | 126.00 | 0.5% | +1.5pp |
| Carapaz Richard | EF Education-EasyPost | 1.9% | 2.0% | 6.4% | 1.8% | 5.50 | 11.3% | -9.3pp |
| Arensman Thymen | Netcompany INEOS | 1.5% | 1.6% | 5.2% | 1.7% | 13.00 | 4.8% | -3.0pp |
| Pidcock Tom | Pinarello-Q36.5 Pro Cycling Team | 1.0% | 1.7% | – | 1.1% | 81.00 | 0.8% | +0.9pp |
| Gee Derek | Lidl-Trek | 1.6% | 1.6% | 6.4% | 1.6% | 51.00 | 1.2% | +0.4pp |
| Johannessen Tobias Halland | Uno-X Mobility | 1.4% | 1.4% | 5.3% | 1.6% | 17.00 | 3.6% | -2.0pp |
| Skjelmose Mattias | Lidl-Trek | 1.2% | 1.1% | – | 1.4% | 151.00 | 0.4% | +1.0pp |
| Riccitello Matthew | Decathlon CMA CGM Team | 1.4% | 1.4% | 4.7% | 1.1% | 151.00 | 0.4% | +1.0pp |
| Jorgenson Matteo | Team Visma | Lease a Bike | 1.2% | 1.2% | 3.8% | 1.3% | 101.00 | 0.6% | +0.7pp |
| Yates Adam | UAE Team Emirates-XRG | 1.0% | 1.0% | 3.2% | 0.6% | 41.00 | 1.5% | -0.5pp |
| Bernal Egan | Netcompany INEOS | 1.0% | 1.0% | 3.2% | 0.8% | 67.00 | 0.9% | +0.1pp |
| # | Rider | Blend | Cascade | LambdaRank | Podium | Top 15 | Book odds |
|---|---|---|---|---|---|---|---|
| 1 | Pogacar Tadej | 44.6% | 49.5% | 33.0% | 77.5% | 91.6% | 1.60 |
| 2 | Vingegaard Jonas | 14.0% | 10.7% | 11.6% | 48.9% | 88.8% | 17.00 |
| 3 | Evenepoel Remco | 13.7% | 10.3% | 11.3% | 36.9% | 78.9% | 101.00 |
| 4 | Lipowitz Florian | 9.2% | 5.2% | 8.0% | 20.1% | 82.9% | 81.00 |
| 5 | Seixas Paul | 8.3% | 10.5% | 5.8% | 21.0% | 72.3% | 34.00 |
| 6 | del Toro Isaac | 6.3% | 3.7% | 5.5% | 13.3% | 67.3% | 13.00 |
| 7 | Ayuso Juan | 2.9% | 2.2% | 2.4% | 9.5% | 63.7% | 101.00 |
| 8 | Martinez Lenny | 2.4% | 2.7% | 1.7% | 6.9% | 51.0% | 41.00 |
| 9 | Carapaz Richard | 1.9% | 1.6% | 1.5% | 7.0% | 51.0% | 5.50 |
| 10 | Hindley Jai | 1.8% | 1.5% | 1.5% | 6.2% | 44.9% | 126.00 |
| 11 | Gee Derek | 1.6% | 1.4% | 1.2% | 4.9% | 29.4% | 51.00 |
| 12 | Arensman Thymen | 1.5% | 1.4% | 1.1% | 6.9% | 30.2% | 13.00 |
| 13 | Johannessen Tobias Halland | 1.4% | 0.8% | 1.2% | 3.5% | 40.1% | 17.00 |
| 14 | Riccitello Matthew | 1.4% | 1.5% | 1.0% | 5.1% | 33.3% | 151.00 |
| 15 | Jorgenson Matteo | 1.2% | 1.8% | 0.8% | 6.7% | 20.0% | 101.00 |
| 16 | Skjelmose Mattias | 1.2% | 1.8% | 0.8% | 8.5% | 61.9% | 151.00 |
| 17 | Bernal Egan | 1.0% | 0.9% | 0.8% | 4.4% | 43.5% | 67.00 |
| 18 | Yates Adam | 1.0% | 1.1% | 0.7% | 2.1% | 26.5% | 41.00 |
| 19 | Pidcock Tom | 1.0% | 0.7% | 0.8% | 10.6% | 67.5% | 81.00 |
| 20 | Kuss Sepp | 0.9% | 0.8% | 0.7% | 4.7% | 34.0% | 41.00 |
| 21 | Van Wilder Ilan | 0.8% | 1.5% | 0.4% | 4.2% | 36.9% | 151.00 |
| 22 | Piganzoli Davide | 0.8% | 0.5% | 0.6% | 4.1% | 49.0% | 81.00 |
| 23 | Grégoire Romain | 0.6% | 0.7% | 0.5% | 5.8% | 25.2% | 601.00 |
| 24 | Vauquelin Kévin | 0.6% | 0.6% | 0.5% | 4.7% | 20.4% | 151.00 |
| 25 | Higuita Sergio | 0.5% | 0.4% | 0.4% | 2.9% | 16.4% | 301.00 |
| 26 | O'Connor Ben | 0.5% | 0.5% | 0.4% | 3.1% | 24.0% | 81.00 |
| 27 | Jegat Jordan | 0.5% | 0.5% | 0.3% | 6.9% | 45.1% | 251.00 |
| 28 | McNulty Brandon | 0.5% | 0.6% | 0.3% | 2.4% | 19.4% | 101.00 |
| 29 | Castrillo Pablo | 0.4% | 0.7% | 0.3% | 3.1% | 18.0% | 101.00 |
| 30 | Healy Ben | 0.4% | 1.1% | 0.2% | 2.1% | 8.0% | 81.00 |
| # | Rider | Blend | Cascade | LambdaRank | Podium | Top 15 | Book odds |
|---|---|---|---|---|---|---|---|
| 1 | Pogacar Tadej | 45.7% | 45.0% | 36.1% | 73.7% | 88.3% | 1.60 |
| 2 | Evenepoel Remco | 12.0% | 11.3% | 9.6% | 30.0% | 73.2% | 101.00 |
| 3 | Vingegaard Jonas | 10.3% | 7.9% | 8.7% | 42.2% | 85.2% | 17.00 |
| 4 | Seixas Paul | 7.9% | 10.6% | 5.6% | 19.0% | 69.5% | 34.00 |
| 5 | Lipowitz Florian | 7.5% | 5.0% | 6.6% | 17.8% | 78.2% | 81.00 |
| 6 | del Toro Isaac | 6.6% | 4.3% | 5.8% | 13.2% | 66.2% | 13.00 |
| 7 | Martinez Lenny | 2.6% | 3.8% | 1.7% | 8.5% | 55.9% | 41.00 |
| 8 | Hindley Jai | 2.0% | 1.9% | 1.6% | 7.7% | 47.1% | 126.00 |
| 9 | Carapaz Richard | 2.0% | 1.9% | 1.6% | 7.6% | 53.1% | 5.50 |
| 10 | Ayuso Juan | 1.9% | 1.7% | 1.6% | 8.3% | 59.0% | 101.00 |
| 11 | Pidcock Tom | 1.7% | 1.4% | 1.4% | 5.4% | 51.4% | 81.00 |
| 12 | Gee Derek | 1.6% | 1.9% | 1.2% | 19.1% | 49.0% | 51.00 |
| 13 | Arensman Thymen | 1.6% | 1.2% | 1.3% | 5.2% | 28.5% | 13.00 |
| 14 | Riccitello Matthew | 1.4% | 1.5% | 1.1% | 5.4% | 33.6% | 151.00 |
| 15 | Johannessen Tobias Halland | 1.4% | 0.8% | 1.2% | 9.0% | 56.4% | 17.00 |
| 16 | Jorgenson Matteo | 1.2% | 1.7% | 0.8% | 7.0% | 22.9% | 101.00 |
| 17 | Skjelmose Mattias | 1.1% | 1.4% | 0.8% | 5.8% | 55.5% | 151.00 |
| 18 | Yates Adam | 1.0% | 1.2% | 0.8% | 3.2% | 35.3% | 41.00 |
| 19 | Kuss Sepp | 1.0% | 1.0% | 0.8% | 4.9% | 35.8% | 41.00 |
| 20 | Van Wilder Ilan | 1.0% | 1.8% | 0.6% | 4.4% | 39.0% | 151.00 |
| 21 | Bernal Egan | 1.0% | 0.7% | 0.8% | 5.4% | 45.1% | 67.00 |
| 22 | Piganzoli Davide | 0.8% | 0.5% | 0.7% | 3.3% | 50.6% | 81.00 |
| 23 | Vauquelin Kévin | 0.8% | 0.7% | 0.6% | 3.5% | 21.2% | 151.00 |
| 24 | Grégoire Romain | 0.7% | 0.6% | 0.6% | 5.0% | 23.8% | 601.00 |
| 25 | Higuita Sergio | 0.6% | 0.3% | 0.5% | 2.6% | 17.0% | 301.00 |
| 26 | McNulty Brandon | 0.6% | 0.8% | 0.4% | 2.9% | 25.3% | 101.00 |
| 27 | O'Connor Ben | 0.5% | 0.3% | 0.4% | 3.4% | 28.0% | 81.00 |
| 28 | Jegat Jordan | 0.5% | 0.4% | 0.4% | 7.8% | 49.6% | 251.00 |
| 29 | Paret-Peintre Valentin | 0.4% | 0.5% | 0.3% | 2.0% | 16.9% | 67.00 |
| 30 | Castrillo Pablo | 0.4% | 0.5% | 0.3% | 3.9% | 16.4% | 101.00 |
| # | Rider | Blend | Cascade | LambdaRank | Podium | Top 15 | Book odds |
|---|---|---|---|---|---|---|---|
| 1 | Hindley Jai | 2.0% | 2.5% | 1.6% | 8.1% | 43.5% | 126.00 |
| 2 | Gee Derek | 1.8% | 2.1% | 1.5% | 16.1% | 41.4% | 51.00 |
| 3 | Carapaz Richard | 1.8% | 1.6% | 1.6% | 6.7% | 47.7% | 5.50 |
| 4 | Johannessen Tobias Halland | 1.5% | 0.8% | 1.5% | 9.9% | 53.6% | 17.00 |
| 5 | Arensman Thymen | 1.5% | 1.4% | 1.3% | 6.3% | 27.8% | 13.00 |
| 6 | Riccitello Matthew | 1.3% | 1.3% | 1.2% | 5.3% | 30.7% | 151.00 |
| 7 | Jorgenson Matteo | 1.1% | 1.8% | 0.8% | 6.3% | 18.7% | 101.00 |
| 8 | Bernal Egan | 0.9% | 0.7% | 0.9% | 3.9% | 41.5% | 67.00 |
| 9 | Yates Adam | 0.9% | 1.2% | 0.7% | 2.2% | 27.1% | 41.00 |
| 10 | Van Wilder Ilan | 0.9% | 1.8% | 0.5% | 4.5% | 36.2% | 151.00 |
| 11 | Kuss Sepp | 0.8% | 0.8% | 0.7% | 4.4% | 33.3% | 41.00 |
| 12 | Piganzoli Davide | 0.8% | 0.5% | 0.8% | 3.3% | 46.7% | 81.00 |
| 13 | Grégoire Romain | 0.7% | 0.7% | 0.6% | 5.6% | 27.4% | 601.00 |
| 14 | Vauquelin Kévin | 0.7% | 0.7% | 0.6% | 4.4% | 20.1% | 151.00 |
| 15 | Healy Ben | 0.6% | 1.6% | 0.2% | 2.8% | 8.2% | 81.00 |
| 16 | Higuita Sergio | 0.5% | 0.4% | 0.5% | 3.5% | 18.6% | 301.00 |
| 17 | McNulty Brandon | 0.5% | 0.8% | 0.4% | 2.8% | 20.3% | 101.00 |
| 18 | Castrillo Pablo | 0.5% | 1.0% | 0.3% | 3.7% | 19.9% | 101.00 |
| 19 | Jegat Jordan | 0.4% | 0.5% | 0.4% | 6.6% | 48.2% | 251.00 |
| 20 | O'Connor Ben | 0.4% | 0.4% | 0.4% | 3.2% | 23.5% | 81.00 |
| 21 | Baudin Alex | 0.4% | 0.6% | 0.2% | 2.0% | 15.4% | 151.00 |
| 22 | Van Eetvelt Lennert | 0.3% | 0.2% | 0.3% | 3.3% | 16.6% | 101.00 |
| 23 | Wellens Tim | 0.3% | 1.0% | 0.1% | 1.7% | 6.1% | 401.00 |
| 24 | van der Poel Mathieu | 0.3% | 0.5% | 0.2% | 3.4% | 8.3% | 801.00 |
| 25 | Foss Tobias | 0.3% | 0.4% | 0.2% | 2.0% | 8.5% | 401.00 |
| 26 | Izagirre Ion | 0.3% | 0.2% | 0.3% | 2.2% | 10.8% | 301.00 |
| 27 | Schmid Mauro | 0.3% | 0.4% | 0.2% | 4.3% | 12.8% | 301.00 |
| 28 | Steinhauser Georg | 0.3% | 0.8% | 0.1% | 1.4% | 7.4% | 201.00 |
| 29 | Storer Michael | 0.3% | 0.2% | 0.3% | 1.5% | 14.7% | 81.00 |
| 30 | Paret-Peintre Valentin | 0.3% | 0.4% | 0.2% | 2.0% | 15.8% | 67.00 |
| # | Rider | Blend | Cascade | LambdaRank | Podium | Top 15 | Book odds |
|---|---|---|---|---|---|---|---|
| 1 | Pogacar Tadej | 45.6% | 53.8% | 32.0% | 77.8% | 90.0% | 1.60 |
| 2 | Vingegaard Jonas | 14.3% | 11.4% | 11.5% | 46.9% | 84.5% | 17.00 |
| 3 | Lipowitz Florian | 12.0% | 6.3% | 10.4% | 25.8% | 81.3% | 81.00 |
| 4 | Evenepoel Remco | 10.2% | 7.9% | 8.2% | 27.0% | 69.7% | 101.00 |
| 5 | Seixas Paul | 10.0% | 10.4% | 7.4% | 22.8% | 67.7% | 34.00 |
| 6 | del Toro Isaac | 6.1% | 3.3% | 5.3% | 10.8% | 62.0% | 13.00 |
| 7 | Ayuso Juan | 3.4% | 1.9% | 3.0% | 9.3% | 57.8% | 101.00 |
| 8 | Martinez Lenny | 1.9% | 1.7% | 1.4% | 5.3% | 47.4% | 41.00 |
| 9 | Carapaz Richard | 1.8% | 1.5% | 1.4% | 6.4% | 45.1% | 5.50 |
| 10 | Hindley Jai | 1.8% | 1.2% | 1.5% | 6.0% | 36.7% | 126.00 |
| 11 | Arensman Thymen | 1.7% | 1.5% | 1.4% | 7.9% | 31.2% | 13.00 |
| 12 | Gee Derek | 1.6% | 2.2% | 1.1% | 12.1% | 36.1% | 51.00 |
| 13 | Johannessen Tobias Halland | 1.6% | 0.7% | 1.4% | 2.8% | 32.3% | 17.00 |
| 14 | Skjelmose Mattias | 1.4% | 1.2% | 1.1% | 4.3% | 45.1% | 151.00 |
| 15 | Jorgenson Matteo | 1.3% | 2.0% | 0.8% | 6.4% | 19.9% | 101.00 |
| 16 | Pidcock Tom | 1.1% | 0.8% | 0.9% | 11.0% | 65.2% | 81.00 |
| 17 | Riccitello Matthew | 1.1% | 0.9% | 0.8% | 4.0% | 30.8% | 151.00 |
| 18 | Kuss Sepp | 0.9% | 1.2% | 0.6% | 7.1% | 31.0% | 41.00 |
| 19 | Bernal Egan | 0.8% | 0.8% | 0.6% | 4.2% | 40.1% | 67.00 |
| 20 | Piganzoli Davide | 0.8% | 0.5% | 0.7% | 6.1% | 47.8% | 81.00 |
| 21 | Grégoire Romain | 0.8% | 1.0% | 0.5% | 5.7% | 30.8% | 601.00 |
| 22 | Vauquelin Kévin | 0.8% | 0.8% | 0.5% | 4.7% | 24.1% | 151.00 |
| 23 | Van Wilder Ilan | 0.7% | 0.5% | 0.6% | 2.6% | 28.6% | 151.00 |
| 24 | Yates Adam | 0.6% | 0.5% | 0.5% | 1.3% | 19.6% | 41.00 |
| 25 | Aranburu Alex | 0.6% | 1.6% | 0.1% | 2.5% | 8.6% | 1001.00 |
| 26 | Castrillo Pablo | 0.5% | 1.3% | 0.2% | 3.3% | 19.1% | 101.00 |
| 27 | McNulty Brandon | 0.5% | 0.5% | 0.4% | 2.3% | 21.4% | 101.00 |
| 28 | O'Connor Ben | 0.5% | 0.6% | 0.3% | 2.2% | 20.8% | 81.00 |
| 29 | van der Poel Mathieu | 0.5% | 1.1% | 0.2% | 4.6% | 10.2% | 801.00 |
| 30 | Higuita Sergio | 0.5% | 0.4% | 0.4% | 3.3% | 23.8% | 301.00 |
Angle
The top 10 on GC after stage 14 removed — everyone below that is far enough back to be given freedom. Remaining riders under the 'Break survives' read; the conditional column renormalizes their win probability over this pool (P(win | a non-GC rider wins), pool holds 28% of the unconditional book). The model can't see who actually makes the break — read this as a fitness-for-the-day ranking, not break-formation odds.
| Rider | Team | Break survives win p | P(win | break wins) | Book odds | Book devig |
|---|---|---|---|---|---|
| Hindley Jai | Red Bull-BORA-hansgrohe | 2.0% | 7.0% | 126 | 0.5% |
| Gee Derek | Lidl-Trek | 1.8% | 6.4% | 51 | 1.2% |
| Carapaz Richard | EF Education-EasyPost | 1.8% | 6.4% | 6 | 11.3% |
| Johannessen Tobias Halland | Uno-X Mobility | 1.5% | 5.3% | 17 | 3.6% |
| Arensman Thymen | Netcompany INEOS | 1.5% | 5.2% | 13 | 4.8% |
| Riccitello Matthew | Decathlon CMA CGM Team | 1.3% | 4.7% | 151 | 0.4% |
| Jorgenson Matteo | Team Visma | Lease a Bike | 1.1% | 3.8% | 101 | 0.6% |
| Bernal Egan | Netcompany INEOS | 0.9% | 3.2% | 67 | 0.9% |
| Yates Adam | UAE Team Emirates-XRG | 0.9% | 3.2% | 41 | 1.5% |
| Van Wilder Ilan | Soudal Quick-Step | 0.9% | 3.0% | 151 | 0.4% |
| Kuss Sepp | Team Visma | Lease a Bike | 0.8% | 2.9% | 41 | 1.5% |
| Piganzoli Davide | Team Visma | Lease a Bike | 0.8% | 2.8% | 81 | 0.8% |
| Grégoire Romain | Groupama-FDJ United | 0.7% | 2.5% | 601 | 0.1% |
| Vauquelin Kévin | Netcompany INEOS | 0.7% | 2.3% | 151 | 0.4% |
Angle
Shortest book prices for the stage, with our blend win probability (and rank) under each scenario. 'free' = outside the excluded GC pool (top 10 on GC after stage 14), i.e. the type the peloton might let up the road.
| Rider | Book odds | Devig | GC summit | Climbers' wall | Break survives | GC status |
|---|---|---|---|---|---|---|
| Pogacar Tadej | 1.60 | 38.8% | 44.6% (#1) | 45.7% (#1) | 38.4% (#1) | GC #1 |
| Carapaz Richard | 5.50 | 11.3% | 1.9% (#9) | 2.0% (#9) | 1.8% (#11) | free |
| del Toro Isaac | 13.00 | 4.8% | 6.3% (#6) | 6.6% (#6) | 5.4% (#6) | GC #7 |
| Arensman Thymen | 13.00 | 4.8% | 1.5% (#12) | 1.6% (#13) | 1.5% (#13) | free |
| Vingegaard Jonas | 17.00 | 3.6% | 14.0% (#2) | 10.3% (#3) | 11.0% (#3) | GC #2 |
| Johannessen Tobias Halland | 17.00 | 3.6% | 1.4% (#13) | 1.4% (#15) | 1.5% (#12) | free |
| Seixas Paul | 34.00 | 1.8% | 8.3% (#5) | 7.9% (#4) | 7.7% (#4) | GC #4 |
| Martinez Lenny | 41.00 | 1.5% | 2.4% (#8) | 2.6% (#7) | 2.4% (#8) | GC #10 |
| Kuss Sepp | 41.00 | 1.5% | 0.9% (#20) | 1.0% (#19) | 0.8% (#21) | free |
| Yates Adam | 41.00 | 1.5% | 1.0% (#18) | 1.0% (#18) | 0.9% (#19) | free |
Angle
Model column is the GC-summit read RENORMALIZED over the field (blend / 130.4%), so it is directly comparable to the devigged book; the raw board would flatter us by a third. Two clean patterns. Above the line, the model backs proven GC quality on any hard day: it gives Evenepoel 10.5% and Lipowitz 7.0% where the book has them at 101 and 81 (0.6% and 0.8%). The book is pricing a specific fact the model cannot represent — 11.3 km at 9.1% is not terrain on which a time-trial-shaped rider wins a stage, whatever his GC position. Our own Climbers' wall read was built to test exactly that and barely moved him (13.7% to 12.0% raw), which says the model's mountain axis concentrates mass on the best climber rather than re-sorting riders by gradient tolerance. Below the line the mirror image: the book has Carapaz at 5.5 (11.3%) and Arensman at 13 (4.8%) because it is pricing break formation on a day with 160 km of gentle drag before the wall, and the model prices only rider-course fit. Treat the top of this table as the model's known blind spot, not as edge.
| Rider | Team | Model (renormalized) | Book devig | Book odds | Difference |
|---|---|---|---|---|---|
| Evenepoel Remco | Red Bull-BORA-hansgrohe | 10.5% | 0.6% | 101.0 | +9.9pp |
| Vingegaard Jonas | Team Visma | Lease a Bike | 10.8% | 3.6% | 17.0 | +7.1pp |
| Lipowitz Florian | Red Bull-BORA-hansgrohe | 7.0% | 0.8% | 81.0 | +6.3pp |
| Seixas Paul | Decathlon CMA CGM Team | 6.3% | 1.8% | 34.0 | +4.5pp |
| Ayuso Juan | Lidl-Trek | 2.3% | 0.6% | 101.0 | +1.6pp |
| Hindley Jai | Red Bull-BORA-hansgrohe | 1.4% | 0.5% | 126.0 | +0.9pp |
| Yates Adam | UAE Team Emirates-XRG | 0.8% | 1.5% | 41.0 | -0.8pp |
| Kuss Sepp | Team Visma | Lease a Bike | 0.7% | 1.5% | 41.0 | -0.8pp |
| Johannessen Tobias Halland | Uno-X Mobility | 1.1% | 3.6% | 17.0 | -2.6pp |
| Arensman Thymen | Netcompany INEOS | 1.1% | 4.8% | 13.0 | -3.6pp |
| Pogacar Tadej | UAE Team Emirates-XRG | 34.2% | 38.8% | 1.6 | -4.6pp |
| Carapaz Richard | EF Education-EasyPost | 1.5% | 11.3% | 5.5 | -9.8pp |
After the stage
| Pos | Rider | Team | GC summit win p | Climbers' wall win p | Break survives win p | Hindsight (post-hoc) win p |
|---|---|---|---|---|---|---|
| 1 | Evenepoel Remco | Red Bull-BORA-hansgrohe | 13.7% | 12.0% | 11.1% | 10.2% |
| 2 | Pogacar Tadej | UAE Team Emirates-XRG | 44.6% | 45.7% | 38.4% | 45.6% |
| 3 | del Toro Isaac | UAE Team Emirates-XRG | 6.3% | 6.6% | 5.4% | 6.1% |
| 4 | Seixas Paul | Decathlon CMA CGM Team | 8.3% | 7.9% | 7.7% | 10.0% |
| 5 | Lipowitz Florian | Red Bull-BORA-hansgrohe | 9.2% | 7.5% | 6.5% | 12.0% |
| 6 | Martinez Lenny | Bahrain Victorious | 2.4% | 2.6% | 2.4% | 1.9% |
| 7 | Skjelmose Mattias | Lidl-Trek | 1.2% | 1.1% | 1.0% | 1.4% |
| 8 | Ayuso Juan | Lidl-Trek | 2.9% | 1.9% | 2.4% | 3.4% |
| 9 | Yates Adam | UAE Team Emirates-XRG | 1.0% | 1.0% | 0.9% | 0.6% |
| 10 | Simmons Quinn | Lidl-Trek | 0.1% | 0.1% | 0.1% | 0.1% |
| Scenario | Blend win p | Book devig |
|---|---|---|
| GC summit | 13.67% | 0.61% |
| Climbers' wall | 11.97% | 0.61% |
| Break survives | 11.10% | 0.61% |
| Hindsight (post-hoc) | 10.21% | 0.61% |
Reflection
The road picked the GC-summit branch, and then some: no break survived the wall, and the two strongest stage-racers in the race arrived together. But the name on the stage was the one nobody was supposed to say. Remco Evenepoel won on an 11.3 km wall at 9.1%, taking Pogacar to the line at level time with del Toro six seconds back — and the book had priced him at 101.0, six-tenths of a percent devigged, the longest price on any top-four GC rider all Tour. Every one of our reads had him second or third at 9.4–10.5% renormalized. Last night's disagreement table led with Evenepoel at +9.9pp and told readers to 'treat the top of this table as the model's known blind spot, not as edge.' That editorial call was wrong, and it deserves to be owned plainly: the model's number was the good one, the book's archetype logic — time-trial-shaped riders don't win on 9% walls — was the thing that failed. A 16x disagreement settled for the model is the strongest single result the system has produced this Tour.
The supporting cast makes it systematic rather than lucky. The same table backed Lipowitz (+6.3pp, book 81.0) and Seixas (+4.5pp, book 34.0): they finished fifth and fourth at +58s, ahead of every featherweight climber the gradient story favoured. And the book's other lean — Carapaz at 5.5 as break-survives second favourite — evaporated with the break itself; he came twelfth from the GC group at +2:51. On this stage the model's 'proven GC quality wins any hard day' prior beat both of the book's stories at once: the gradient-archetype story above the line and the break-formation story below it.
The hindsight run says course knowledge was not just unnecessary — it would have made the winner call slightly worse. Matched to the actual finish curve (2 within 5s, 5 within 60s, 24 within 10min), the five closest DB stages are all GC-captain summit wins (Vingegaard TdF'24 s11, Almeida twice, Roglic, Onley), and that read prices Evenepoel at 7.6% renormalized — below the 10.5% the pre-race GC-summit read gave him — while promoting Lipowitz to 9.0%. Same pattern as stage 14: hindsight tunes the supporting cast, not the winner. Worth logging for the mountain-axis file: the reference stages that finish like Solaison carry a DB fingerprint of mountain ~0.45 / rolling ~0.55, nowhere near the 0.75 synthetic of our Climbers' wall read — and the featherweight promotion that read was built to test is exactly what the road refused to deliver. The axis still can't re-sort by gradient tolerance, but this result argues the book's gradient-tolerance story is itself overrated on summit finishes: what transfers is quality and form.
The asterisk is Vingegaard. Our #2 on every read at 8–11%, he crashed out of the race along with Merlier and Van Asbroeck — the model's second-biggest number never reached the climb. That is what the DNF head and the dnf-adjusted columns exist to absorb, and it is also the day's real GC story: Evenepoel inherits second at +5:00, the Visma captaincy question is gone from the race, and the standings cliff behind Pidcock (9th, +11:19, then +19:26) has become an eight-minute chasm that will define who gets breakaway freedom in the Alps. Carry-forward watch item: our stage-16 time-trial preview inherits a board where the two riders who just dropped everyone are also the two best men against the clock.