ROUND_15 · BAKU CITY CIRCUIT
Azerbaijan GP 2026did we call it right?
Before the race we ran this GP 400 times through our engine, starting from the real qualifying grid, and published the odds. The race has now been run: here is the contrast, misses included.
Leer en españolVERDICT · RACE RUN
What we saidand what happened
Russell won from pole, the model's favourite, with Verstappen 0.196 seconds behind
The model had George Russell as the favourite on 48.3% of 400 simulations, ahead of the rest of the grid. He won.
3.96
Avg. position error
across 15 finishers
0.67
Order correlation
1 = exact order
7/8
Front of the race
of the predicted top
6/10
Points scorers
called right
| Actual | Driver | Grid | Predicted | Diff |
|---|---|---|---|---|
| 1 | George RussellMercedesStarted from pole and was the simulation favourite at 48.3%. Won by 0.196 seconds and set the fastest lap. | 1 | 2.20 | -1.20 |
| 2 | Max VerstappenRed BullStarted 8th. The model gave him a 6.3% podium chance and he finished two tenths from winning. | 8 | 5.90 | -3.90 |
| 3 | Isack HadjarRed BullStarted 4th. The model gave him a 1.8% podium chance. | 4 | 7.20 | -4.20 |
| 4 | Charles LeclercFerrari | 2 | 3.50 | +0.50 |
| 5 | Kimi AntonelliMercedesStarted 16th after hitting the wall in Q1. The model put his average finish at 8.1 and he climbed to 5th, with two safety cars along the way. | 16 | 8.10 | -3.10 |
| 6 | Lewis HamiltonFerrari | 6 | 4.70 | +1.30 |
| 7 | Arvid LindbladRacing Bulls | 15 | 14.40 | -7.40 |
| 8 | Esteban OconHaas | 13 | 14.30 | -6.30 |
| 9 | Oliver BearmanHaas | 10 | 12.40 | -3.40 |
| 10 | Carlos SainzWilliams | 14 | 13.80 | -3.80 |
| 11 | Nico HulkenbergAudi | 18 | 17.30 | -6.30 |
| 12 | Liam LawsonRacing Bulls | 11 | 11.10 | +0.90 |
| 13 | Oscar PiastriMcLarenWas running 3rd when he locked up into Turn 1 and had to spin round to rejoin. The model gave him a 64.3% podium chance. | 3 | 3.70 | +9.30 |
| 14 | Sergio PerezCadillac | 20 | 19.20 | -5.20 |
| 15 | Gabriel BortoletoAudi | 17 | 17.60 | -2.60 |
| DNF | Valtteri BottasCadillacCrashed in the closing laps and did not reach the flag. The official classification has him 16th after covering 49 of the 51 laps, but here he counts as a retirement: he did not finish the race. | 19 | 19.10 | — |
| DNF | Franco ColapintoAlpineLocked up and hit his team mate Gasly, who in turn collected Norris. All three retired. | 9 | 11.40 | — |
| DNF | Pierre GaslyAlpine | 7 | 10.30 | — |
| DNF | Lando NorrisMcLarenStarted 5th and was taken out in the collision between the two Alpines. | 5 | 4.20 | — |
| DNF | Alexander AlbonWilliamsLocked up and went into the barrier. | 12 | 13.80 | — |
| DNF | Fernando AlonsoAston MartinStarted 21st after his engine penalty and retired with a car problem. | 21 | 17.30 | — |
| DNF | Lance StrollAston MartinStarted last after his engine penalty and retired early with a water pressure problem. | 22 | 20.40 | — |
Where the model got it wrong
- Oscar Piastri predicted around P3.70, finished 13th (9.30 places off).
- Arvid Lindblad predicted around P14.40, finished 7th (7.40 places off).
- Esteban Ocon predicted around P14.30, finished 8th (6.30 places off).
- Nico Hulkenberg predicted around P17.30, finished 11th (6.30 places off).
- Did not see Arvid Lindblad, Esteban Ocon, Oliver Bearman, Carlos Sainz scoring.
The pattern is clear: the model orders the front of the race well and underrates the midfield, because each car's performance is set per season and does not capture a given weekend's form. That is the biggest known limitation, and the next one to attack.
Official result: Formula1.com. The probabilities were published BEFORE the race and have not been touched since.
The preview, exactly as published
Favourite
George Russell 48.3%
Wins 48.3% of the simulations and finishes on the podium in 89%. Starts P1.
Driver by driver
| Grid | Driver | Win | Podium | Avg. finish |
|---|---|---|---|---|
| P1 | George Russell | 48.3% | 89% | P2.2 |
| P2 | Charles Leclerc | 22% | 72.3% | P3.5 |
| P3 | Oscar Piastri | 19% | 64.3% | P3.7 |
| P4 | Isack Hadjar | 0% | 1.8% | P7.2 |
| P5 | Lando Norris | 7% | 40.8% | P4.2 |
| P6 | Lewis Hamilton | 3.5% | 25.8% | P4.7 |
| P7 | Pierre Gasly | 0% | 0% | P10.3 |
| P8 | Max Verstappen | 0.3% | 6.3% | P5.9 |
| P9 | Franco Colapinto | 0% | 0% | P11.4 |
| P10 | Oliver Bearman | 0% | 0% | P12.4 |
| P11 | Liam Lawson | 0% | 0% | P11.1 |
| P12 | Alexander Albon | 0% | 0% | P13.8 |
| P13 | Esteban Ocon | 0% | 0% | P14.3 |
| P14 | Carlos Sainz | 0% | 0% | P13.8 |
| P15 | Arvid Lindblad | 0% | 0% | P14.4 |
| P16 | Kimi Antonelli | 0% | 0% | P8.1 |
| P17 | Gabriel Bortoleto | 0% | 0% | P17.6 |
| P18 | Nico Hulkenberg | 0% | 0% | P17.3 |
| P19 | Valtteri Bottas | 0% | 0% | P19.1 |
| P20 | Sergio Perez | 0% | 0% | P19.2 |
| P21 | Fernando Alonso | 0% | 0% | P17.3 |
| P22 | Lance Stroll | 0% | 0% | P20.4 |
How the model works
The engine accounts for how much starting at the front is worth at each circuit, and nowhere is it worth as much as at Monaco. Since the 2026 Azerbaijan GP that weight is calibrated track by track against the real races from 2014 to 2025; earlier previews ran on a simpler formula that derived it from how easy it is to overtake on each layout. Which is why George Russell comes out favourite at 48.3% without having the fastest car of the season.
A favourite who only wins one race in four is not a broken model: that is what a real Grand Prix looks like. A retirement, a safety car at the wrong moment or a slow stop flips the result, and the engine simulates all of them. That is why 4 drivers have a genuine shot rather than a single name circled in red.
The most interesting column is the average finish: Kimi Antonelli starts P16 and averages P8.1, the biggest gain on the grid: the driver the model thinks is most underrated by where he qualified.
The numbers come from 400 full race simulations (51 laps) with car and driver ratings updated to this point of the season. This is not betting advice and not an official prediction: it is what our model said. The odds were published before the race and have not been touched since: the contrast with the real result is above.