Model Performance
Transparent accuracy tracking. Every prediction is measured, every miss is counted.
How to read this page
A forecast here is one decision — one match, one race, one stage, one title — not one line of probability. A Cycling Stage Winner forecast means scoring around 30 candidates, most of them easy calls; counting each line as a forecast would let a single race outweigh dozens of matches.
Raw Brier scores cannot be compared across markets, because some questions are harder than others. A forecaster with no knowledge at all scores about 0.250 on Football 1st Half Over/Under 0.5 and about 0.022 on Cycling Stage Winner — a lower Brier on the second says nothing about the model being better. The skill score removes that: it measures how much better the model does than knowing only how often this kind of call comes in. Zero means it adds nothing, one is perfect, and a negative number means it is worse than guessing. 4 forecasts sit in segments too small to set a reliable baseline, so they show a raw score only.
Some markets are worked out from the same forecast as others. In football, double chance, draw no bet, other goal lines, team goals and correct score come from the same scoreline forecast as the match result and over/under 2.5. In Formula 1, the top 10 and the team-mate battles come from the same simulated races as the winner, podium and top 6. They are scored and listed below, but left out of the overall figures, the sport summary, the monthly trend and the model version comparison: counting several restatements of one forecast per event would let them drown out the forecasts that carry the information. A draw no bet forecast is not scored when the match is drawn.
For football match result and goals markets there is a second, much harder benchmark: the betting market's closing odds — the average across bookmakers just before kick-off — with the margin removed. vs market compares the model with those odds on exactly the same matches. A positive number means the model's probabilities were closer to what happened than the market's; a negative one means the market knew more. Beating the closing line consistently is rare, so a value slightly below zero is the normal result for a good public model.
Calibration
When the model says 70%, does it happen 70% of the time? The closer to the diagonal, the better calibrated. Head-to-head markets (match result, goals, match winner) and field markets (races, rallies, stages) are drawn separately: field markets are mostly low-probability lines and would otherwise hide everything else.
Skill over time
Monthly skill score by sport. Higher is better. Months with fewer than 5 scored forecasts are excluded.
By market
Raw Brier sits next to the baseline it is measured against; compare Brier only within a row, and skill across rows. The highlighted row is where the model adds the most over guessing.
| Sport | Market | Field | Forecasts | Brier | Baseline | Skill | Market | vs market |
|---|---|---|---|---|---|---|---|---|
| Cycling | GC Winner | 30 | 5 | 0.9942 | 0.9344 | — | — | — |
| Cycling | Stage Winner | 30 | 48 | 0.0215 | 0.0224 | 0.039 | — | — |
| Cycling | Top 10 Finish | 30 | 48 | 0.1361 | 0.1314 | -0.036 | — | — |
| Football | 1st Half Over/Under 0.5 | 2 | 67 | 0.1886 | 0.2500 | 0.246 | — | — |
| Football | 1st Half Over/Under 1.5 | 2 | 67 | 0.2377 | 0.2500 | 0.049 | — | — |
| Football | 1X2 | 3 | 475 | 0.1978 | 0.2222 | 0.110 | 0.1903 | -0.056 |
| Football | Away Team Over/Under 0.5 | 2 | 67 | 0.2110 | 0.2500 | 0.156 | — | — |
| Football | BTTS | 2 | 475 | 0.2476 | 0.2500 | 0.010 | — | — |
| Football | Correct Score | 5 | 67 | 0.1010 | 0.1006 | -0.004 | — | — |
| Football | Double Chance | 3 | 67 | 0.1653 | 0.2222 | 0.256 | — | — |
| Football | Draw No Bet | 2 | 56 | 0.1552 | 0.2500 | 0.379 | — | — |
| Football | Half-Time Result | 3 | 67 | 0.2047 | 0.2222 | 0.079 | — | — |
| Football | Half-Time/Full-Time | 9 | 67 | 0.0830 | 0.0988 | 0.160 | — | — |
| Football | Home Team Over/Under 0.5 | 2 | 67 | 0.1374 | 0.2500 | 0.450 | — | — |
| Football | Home Team Over/Under 1.5 | 2 | 67 | 0.2031 | 0.2500 | 0.187 | — | — |
| Football | Over/Under 1.5 | 2 | 67 | 0.1611 | 0.2500 | 0.356 | — | — |
| Football | Over/Under 2.5 | 2 | 475 | 0.2522 | 0.2500 | -0.009 | 0.2302 | -0.092 |
| Football | Over/Under 3.5 | 2 | 67 | 0.1922 | 0.2500 | 0.231 | — | — |
| Formula 1 | Fastest Lap | 22 | 7 | 0.0496 | 0.0442 | — | — | — |
| Formula 1 | Podium | 22 | 14 | 0.0901 | 0.1194 | 0.245 | — | — |
| Formula 1 | Qualifying Winner | 22 | 2 | 0.0404 | 0.0443 | — | — | — |
| Formula 1 | Race Winner | 22 | 14 | 0.0416 | 0.0441 | 0.056 | — | — |
| Formula 1 | Team-mate Head-to-Head | 20 | 2 | 0.1924 | — | — | — | — |
| Formula 1 | Top 10 | 21 | 2 | 0.0916 | — | — | — | — |
| Formula 1 | Top 6 best | 22 | 14 | 0.1097 | 0.2004 | 0.453 | — | — |
| Tennis | Match Winner | 2 | 398 | 0.2242 | 0.2500 | 0.103 | 0.2222 | -0.010 |
| Tennis | Set Betting | 4 | 32 | 0.1661 | 0.1875 | 0.114 | — | — |
| Tennis | Tournament Winner | 32 | 2 | 0.6579 | 0.9385 | — | — | — |
| WRC | Drivers Championship | 8 | 1 | 0.1031 | 0.7656 | — | — | — |
| WRC | Rally Podium | 11 | 4 | 0.1989 | — | — | — | — |
| WRC | Rally Winner | 10 | 4 | 0.0862 | 0.0880 | — | — | — |
| WRC | Stage Winner | 10 | 37 | 0.0861 | 0.0881 | 0.022 | — | — |
By sport
Skill only. A sport's markets have different field sizes, so an average Brier across them would mean nothing. The count is the forecasts the skill score covers, which can be fewer than the sport's total.
| Sport | Forecasts | Skill | Log loss |
|---|---|---|---|
| Cycling | 101 | -0.040 | 0.7288 |
| Football | 1425 | 0.034 | 0.6564 |
| Formula 1 | 51 | 0.307 | 0.2465 |
| Tennis | 400 | 0.107 | 0.6485 |
| WRC | 42 | 0.169 | 0.3335 |
Model versions
Each model change is tracked separately so improvements can be verified.
| Version | Sport | Forecasts | Brier | Skill | Log loss | Status |
|---|---|---|---|---|---|---|
| cycling-stage-v2 | Cycling | 15 | 0.1233 | 0.080 | 0.8267 | active |
| cycling-stage-v1 | Cycling | 86 | 0.1243 | -0.064 | 0.7118 | retired |
| dc-v7-comp-mu | Football | 201 | 0.2202 | 0.085 | 0.6281 | active |
| dixon-coles-v1 | Football | 93 | 0.2408 | 0.000 | 0.6747 | retired |
| dixon-coles-v5-intl | Football | 30 | 0.2244 | 0.068 | 0.6383 | retired |
| dixon-coles-v6-reg | Football | 1215 | 0.2324 | 0.035 | 0.6563 | retired |
| f1-pl-v2 | Formula 1 | 8 | 0.0524 | — | 0.1752 | active |
| f1-plackett-luce-v1 | Formula 1 | 46 | 0.0766 | 0.300 | 0.2537 | retired |
| tennis-elo-v2 | Tennis | 57 | 0.2277 | 0.089 | 0.6518 | active |
| tennis-outright-v1 | Tennis | 2 | 0.6579 | — | 2.7122 | active |
| tennis-elo-v1 | Tennis | 343 | 0.2233 | 0.107 | 0.6352 | retired |
| wrc-elo-v1 | WRC | 46 | 0.0963 | 0.169 | 0.3335 | active |