Ninety90Machine's track record
Ninety's own football forecasts, graded against the sharpest odds in football. Over six seasons (10,707 matches in the five big leagues) 90Machine is close to, but slightly behind, Pinnacle's closing line. On the 898 matches of 2025/26 it finished ahead of Pinnacle, Bet365 and the bookmaker average. Combined with the market, Ninety's best estimate is level with Pinnacle's close.
Probability 90Machine gave to the actual result, on average (Pinnacle closing: 38.13%)
Matches over six seasons: 90Machine slightly behind Pinnacle's closing line (log loss 0.004 to 0.005 worse)
Leagues where 90Machine beat Pinnacle in 2025/26: Serie A, LaLiga, Ligue 1
2025/26 against the odds at kick-off
898 matches with Pinnacle's closing line on record, the sharpest price in football. 90Machine 1.7, the forecast shown on match day. One season only: over six seasons 90Machine is slightly behind this line.
| Forecast | Probability given to the result | Log loss | Brier |
|---|---|---|---|
| 90Machine Best | 38.22% | 0.9618 | 0.5720 |
| Bookmaker average, opening | 38.19% | 0.9626 | 0.5724 |
| Pinnacle, opening | 38.18% | 0.9628 | 0.5725 |
| Bookmaker average, closing | 38.17% | 0.9631 | 0.5729 |
| Bet365, closing | 38.16% | 0.9634 | 0.5731 |
| Pinnacle, closing | 38.13% | 0.9641 | 0.5736 |
The margins are small because closing odds are already very good: they carry the whole betting market's information. One good season is not proof: over six seasons the closing line is still slightly ahead.
Every match with bookmaker odds
All 1752 matches in the five leagues, including those without a Pinnacle price: level with the bookmaker average, ahead of Bet365 and of the opening odds.
| Forecast | Probability given to the result | Log loss | Brier |
|---|---|---|---|
| Bookmaker average, closing | 37.63% | 0.9774 | 0.5820 |
| 90Machine | 37.62% | 0.9776 | 0.5819 |
| Bet365, closing | 37.61% | 0.9779 | 0.5823 |
| Bookmaker average, opening | 37.59% | 0.9784 | 0.5825 |
Ninety's best estimate vs Polymarket
In the app, 90Machine is combined with the live prediction-market price into one best estimate. Measured exactly as it runs, 30 minutes before kick-off, on 619 matches: ahead of Polymarket on its own and of Pinnacle's closing line. More on Polymarket.
| Forecast | Probability given to the result | Log loss |
|---|---|---|
| Ninety best estimate (90Machine + market) Best | 38.27% | 0.9605 |
| Polymarket | 38.25% | 0.9611 |
| Pinnacle, closing | 38.15% | 0.9636 |
League by league
| League | Matches | 90Machine | Pinnacle closing |
|---|---|---|---|
| Serie A | 198 | 0.9823 | 0.9907 |
| LaLiga | 188 | 0.9439 | 0.9484 |
| Ligue 1 | 153 | 0.9561 | 0.9592 |
| Bundesliga | 149 | 0.9221 | 0.9205 |
| Premier League | 210 | 0.9906 | 0.9875 |
Log loss, lower is better. Leagues are smaller samples, so expect more swing here.
Does 90Machine mean what it says?
A forecast should be right about its own confidence: things it calls 25% should happen about a quarter of the time. Across every outcome of 2025/26, they do.
This season, live
Every forecast the app shows at kick-off is now saved and graded automatically. 230 matches graded so far; the live table appears here once there are enough for the numbers to mean something.
How it is measured
Each match is graded by how much probability a forecast gave to what actually happened: home win, draw or away win. That is log loss, the standard measure for forecasts, and it punishes confident misses. Brier score, the average squared error, tells the same story. Higher "probability given to the result" is better; lower log loss and Brier are better.
Nothing is graded on matches the model was fitted on. Every forecast here came from a model trained only on earlier seasons, the same way it runs live. Since late October 2026 the 2025/26 season has also been used to decide which versions ship, so it is no longer an untouched test; the six-season figure is the fairer long-run view. The 2025/26 tables were measured with 90Machine 1.7; 1.7.1 changed only its calibration.
90Machine 1.7.1. Updated 4 November 2026. Data: football-data.co.uk (results and bookmaker odds), Polymarket. Forecasts are information, not betting advice.
Questions
How accurate is 90Machine?
Over six seasons (10,707 matches in the five big leagues) 90Machine is close to, but slightly behind, Pinnacle's closing line, the sharpest odds in football. On the 898 matches of 2025/26 with Pinnacle closing odds on record it finished ahead of Pinnacle, Bet365 and the bookmaker average, on both log loss and Brier score. None of those matches were used to fit the model, but since late October 2026 that season has also helped decide which versions ship, so it is no longer an untouched test.
Is 90Machine better than the betting odds?
Not overall. Over six seasons 90Machine is close to, but slightly behind, the sharpest closing odds. On the 2025/26 season it finished ahead by a small margin (it gave the actual result 38.22% on average against 38.13% for Pinnacle's closing line). Combined with the market, Ninety's best estimate is level with Pinnacle's close. Across all 1752 2025/26 matches with bookmaker odds it was level with the bookmaker average and ahead of Bet365.
How does Ninety compare with Polymarket?
Ninety's best estimate (90Machine combined with the market price) beat Polymarket and Pinnacle's closing line on 619 matches in 2025/26, measured exactly as the app shows it, 30 minutes before kick-off.
How is accuracy measured?
With log loss: how much probability a forecast gave to what actually happened, punishing confident misses. It is the standard way to compare forecasts. Brier score (squared error) tells the same story. Each season is forecast by a model trained only on earlier seasons, so nothing is graded on matches it was fitted on.
Is 90Machine free?
Yes. Every forecast in the Ninety app and on the website is free.