2026 Leaderboard
Ties don't count as a win or a loss. Missed picks don't count either — they show as a gap in the pick total.
The AIs
| # | Contestant | W | L | Win % | vs spread | Agrees | Pending |
|---|---|---|---|---|---|---|---|
| – | Always the betting favoriteBaseline — the one to beat | 67 | 38 | 63.8% | — | 100.0% | |
| – | AI consensusMajority of the AIs (splits skipped) | 63 | 37 | 63.0% | — | — | |
| 3 | GLM-5.2Z.ai (Zhipu) | 66 | 39 | 62.9% | 49–54 | 73.6% | 13 |
| 4 | Nemotron 3 UltraNVIDIA | 66 | 39 | 62.9% | 50–53 | 71.7% | 13 |
| 5 | Mistral LargeMistral AI | 65 | 40 | 61.9% | 48–55 | 72.6% | 13 |
| 6 | GPT-OSS 120BOpenAI (open-weight) | 60 | 45 | 57.1% | 45–58 | 71.7% | 13 |
| – | Always the home teamBaseline | 52 | 53 | 49.5% | — | — |
Grey rows are baselines — simple strategies an AI has to beat to prove it adds anything. Always the betting favorite is the real test: about two NFL favorites in three win outright, so a model near that number has matched the bookmaker rather than beaten it. Agrees is how often a pick was simply the favorite, and vs spread asks the harder question — roughly 52.4% is break-even there.
Players
| # | Player | W | L | Win % | Points | vs spread | Pending |
|---|---|---|---|---|---|---|---|
| 1 | Supreme Ruler@supremeruler | 53 | 38 | 58.2% | — | — | 14 |