AFL Expert Tips, Graded: Every Public Model Ranked
Most footy tips are never checked. We grade them. This is every public AFL prediction model - 31 of them - ranked by 2026 tipping accuracy against actual results, with our own model slotted in honestly. No spin, just the scoreboard.
2026 AFL model leaderboard
Ranked by tipping accuracy across the 21 rounds played. "Bits" is the information-score metric the AFL analytics community uses to reward confident correct tips and punish confident wrong ones - a sharper measure than raw accuracy. Our model (highlighted) is graded walk-forward: trained only on 2019-2025, predicting 2026 blind.
| # | Model / tipster | Correct | Accuracy | Bits |
|---|---|---|---|---|
| 1 | Drop Kick Data | 131/171 | 76.6% | 42.7 |
| 2 | ZaphBot | 130/171 | 76.0% | 44.6 |
| 3 | Wheelo Ratings | 129/171 | 75.4% | 41.4 |
| 4 | Holy Grail Ratings | 129/171 | 75.4% | 28.9 |
| 5 | AFLalytics | 127/171 | 74.3% | 42.5 |
| 6 | s10 | 127/171 | 74.3% | 43.8 |
| 7 | TippingEdge AI ★ | 86/116 | 74.1% | - |
| 8 | Punters (the betting market) | 126/171 | 73.7% | 43.5 |
| 9 | Aggregate | 126/171 | 73.7% | 41.4 |
| 10 | Glicko Ratings | 126/171 | 73.7% | 38.6 |
| 11 | Don't Blame the Data | 125/171 | 73.1% | 44.8 |
| 12 | What Snoo Thinks | 125/171 | 73.1% | 38.5 |
| 13 | Informed Stats | 125/171 | 73.1% | 41.4 |
| 14 | Massey Ratings | 106/146 | 72.6% | 37.6 |
| 15 | AFL Lab | 124/171 | 72.5% | 39.4 |
| 16 | The Wooden Finger | 124/171 | 72.5% | 41.9 |
| 17 | Hyperion | 117/162 | 72.2% | 35.0 |
| 18 | Matter of Stats | 123/171 | 71.9% | 42.2 |
| 19 | Winnable | 123/171 | 71.9% | 41.1 |
| 20 | Cheap Stats | 122/170 | 71.8% | 31.8 |
| 21 | The Cruncher | 121/169 | 71.6% | 38.0 |
| 22 | PlusSixOne | 122/171 | 71.3% | 37.4 |
| 23 | Stattraction | 122/171 | 71.3% | 40.1 |
| 24 | footycharts | 122/171 | 71.3% | 40.6 |
| 25 | The Footycast | 121/171 | 70.8% | 32.9 |
| 26 | HBin | 121/171 | 70.8% | 37.7 |
| 27 | Live Ladders | 119/171 | 69.6% | 38.1 |
| 28 | Graft | 118/171 | 69.0% | 37.6 |
| 29 | In The Game | 118/171 | 69.0% | 39.3 |
| 30 | Squiggle | 117/171 | 68.4% | 35.9 |
| 31 | Elo Predicts! | 117/171 | 68.4% | 35.4 |
| 32 | AFL Scorigami | 117/171 | 68.4% | 32.1 |
Model tip data via the Squiggle API (credit to Squiggle for aggregating the public AFL model community). Refreshed automatically each round. "Punters" is Squiggle's tag for the betting-market favourite.
Why beating the market is the real test
Any tipster can look good in a season where favourites win. The honest benchmark is the betting market itself - the "Punters" line above, which tips whichever team is favourite. Beating it consistently is hard, because the market already prices in everything public. Our model (74.1%) is beating the betting market (73.7%) over 116 games this season.
The other thing accuracy alone hides: price. A model that tips winners at $1.20 makes you nothing; one that finds winners at $2.00 prints. That is why our weekly tips publish a probability for every game, so you can compare it to the odds and bet only when there is value - use the value checker to do exactly that.
What about media expert tips?
Newspaper and TV panels - The Age, ESPN, Fox Footy, SEN and the rest - publish weekly tips for the office competition, but they rarely publish a graded season record, and they tip winners rather than prices. The model leaderboard above is the data-backed version of the same question: who actually tips well? When a media expert diverges from both the market and the models, that is the interesting tip - everything else is noise around the favourite.
More from TippingEdge
FAQ
Who is the most accurate AFL tipster in 2026?
Of the 32 graded models above, the top of the table leads on raw accuracy through Round 20. Our model sits at #7 on 74.1%. Rankings shift every week - the table refreshes automatically as results come in.
Are AI models better than expert tips?
The leaderboard is dominated by statistical models, and the best of them beat the betting market - which most human tipsters do not. But accuracy is only half the story: a model that tips short-priced favourites adds no betting value. Look for tips that come with a probability you can compare to the odds.
How is your model graded?
Walk-forward and out-of-sample: trained only on 2019-2025 data, then used to predict every 2026 game blind. That is the same standard the public models are held to, and it is detailed on our accuracy page.
Where does the data come from?
Public model tips and their grading come from the Squiggle API, which aggregates the AFL prediction-model community. Our model's record is computed in-house. The market line ("Punters") is Squiggle's favourite-based benchmark.