Round 3 · 2026 season
Japanese Grand Prix
P1
ANT
Mercedes
57% to win
Finished 1st
P2
RUS
Mercedes
28% to win
Finished 4th
P3
LEC
Ferrari
6% to win
Finished 3rd
ANT won as favourite at 57%2 of 3 podium spots calledBiggest surprise: LAW, 14th to 9th
Polymarket had ANT at 52%, the model 57%
Result vs prediction
Predicted is our order before the race. Actual is where they finished. PodiumPoints
| Predicted | Driver | Actual | vs prediction | |
|---|---|---|---|---|
| P1 | ANTMercedes | P1 | ✓ exact | |
| P2 | RUSMercedes | P4 | 2 places lower | |
| P3 | LECFerrari | P3 | ✓ exact | |
| P4 | PIAMcLaren | P2 | 2 places higher | |
| P5 | NORMcLaren | P5 | ✓ exact | |
| P6 | HAMFerrari | P6 | ✓ exact | |
| P7 | HADRed Bull Racing | P12 | 5 places lower | |
| P8 | VERRed Bull Racing | P8 | ✓ exact | |
| P9 | LINRacing Bulls | P14 | 5 places lower | |
| P10 | GASAlpine | P7 | 3 places higher | |
| P11 | OCOHaas F1 Team | P10 | 1 place higher | |
| P12 | BORAudi | P13 | 1 place lower | |
| P13 | HULAudi | P11 | 2 places higher | |
| P14 | LAWRacing Bulls | P9 | 5 places higher | |
| P15 | ALBWilliams | P20 | 5 places lower | |
| P16 | BEAHaas F1 Team | DNF | ||
| P17 | COLAlpine | P16 | 1 place higher | |
| P18 | SAIWilliams | P15 | 3 places higher | |
| P19 | PERCadillac | P17 | 2 places higher | |
| P20 | BOTCadillac | P19 | 1 place higher | |
| P21 | STRAston Martin | DNF | ||
| P22 | ALOAston Martin | P18 | 4 places higher |
Chances
WinPodium
Full field
| Pred | Driver | Grid | Win | Podium | Points | DNF | |
|---|---|---|---|---|---|---|---|
| 1 | ANT | 1 | 56.6 | 94.0 | 95.6 | 4.5 | |
| 2 | RUS | 2 | 28.4 | 87.1 | 93.8 | 6.3 | |
| 3 | LEC | 4+1 | 5.7 | 43.3 | 94.1 | 6.0 | |
| 4 | PIA | 3-1 | 4.9 | 38.4 | 93.7 | 6.3 | |
| 5 | NOR | 5 | 1.7 | 14.2 | 91.8 | 7.6 | |
| 6 | HAM | 6 | 1.4 | 11.5 | 91.9 | 7.3 | |
| 7 | HAD | 8+1 | 0.2 | 1.8 | 52.6 | 25.7 | |
| 8 | VER | 11+3 | 0.2 | 1.3 | 43.8 | 33.7 | |
| 9 | LIN | 10+1 | 0.2 | 1.5 | 56.3 | 10.9 | |
| 10 | GAS | 7-3 | 0.2 | 1.5 | 52.4 | 7.0 | |
| 11 | OCO | 12+1 | 0.2 | 1.1 | 46.7 | 8.7 | |
| 12 | BOR | 9-3 | 0.1 | 0.9 | 38.4 | 6.1 | |
| 13 | HUL | 13 | 0.1 | 0.9 | 35.3 | 9.8 | |
| 14 | LAW | 14 | 0.1 | 0.7 | 32.2 | 9.2 | |
| 15 | ALB | 17+2 | 0.0 | 0.5 | 20.5 | 9.1 | |
| 16 | BEA | 18+2 | 0.0 | 0.3 | 18.3 | 12.3 | |
| 17 | COL | 15-2 | 0.0 | 0.3 | 18.0 | 10.6 | |
| 18 | SAI | 16-2 | 0.0 | 0.3 | 13.8 | 10.4 | |
| 19 | PER | 19 | 0.0 | 0.1 | 4.6 | 25.7 | |
| 20 | BOT | 20 | 0.0 | 0.1 | 4.1 | 19.6 | |
| 21 | STR | 22+1 | 0.0 | 0.0 | 1.0 | 77.5 | |
| 22 | ALO | 21-1 | 0.0 | 0.0 | 1.0 | 74.2 |
The predicted order sits close to the starting grid, and that is expected. This model has not been shown to beat "everyone finishes where they start". The percentages are what it adds: checked against past races, they come out about right on average.
Grid penalties are only included if they were entered by hand. They are never in the timing data this is built from.