Too close to call: 36.5% / 27.9% / 35.6%, top outcome 36.5%.
From the 1500 baseline they currently stand at -26 and +36. The top two outcomes are within 0.9 points of each other, which is inside the range where the model is not really choosing. Santos is ahead on each half — 1.16 to 1.02 in attack, 0.99 to 1.08 in defence. Raw profiles are 1.02 and 1.08 against 1.16 and 0.99. Santos's expected share on the Elo curve comes to 49.6%. The model gives 72.1% to someone winning. A 8.6-point range covers every outcome here. 36.5% goes to Vasco da Gama, the model's lean. 2 of the listed scorelines reach 8% or better. The record shows a single previous meeting, 2026, 1-2 in comp-fd-BSA; not enough to lean on. Outcomes are scattered: top of the list is 1-1 at 10.4%. The two ratings differ by 62 points. Result on the day: 0-3. The forecast we stored before the match was 41.1% / 26.9% / 32.0%. The result went the other way. Goal expectation splits 1.50 to 1.69. Its rounded call is 1-1. The higher rating belongs to the away side.
Source: our elo-poisson-v1 model, run across the complete result record. Not betting guidance.