AI NFL Predictions · Week 10 Daggy vs. the Market
We’re testing our AI forecast agents against the hardest possible benchmark: a real-time, liquid market. Before each game, we post our predictions along with those from Kalshi’s prediction market and score them as they settle. Why we’re doing this.
Through 137 graded games this season, Daggy's combined AI forecast has picked the winner 89 times and missed 48 (65.0%), with a Brier score of 0.222. Kalshi's prediction market, the benchmark to beat, scores 0.219, so the market is slightly ahead. Lower Brier is better: 0 is a perfect forecast and 0.25 is calling every game 50-50. Week 10 predictions for every game → · Week 9 recap →
Week by Week
| Week | Method | Daggy W-L | Kalshi W-L | Daggy Brier | Kalshi Brier |
|---|---|---|---|---|---|
| · so far |  Supervisor | 0-1 | 0-1 | 0.406 | 0.314 |
| Supervisor | 14-1 | 14-1 | 0.125 | 0.117 | |
| Supervisor | 9-5 | 10-4 | 0.188 | 0.177 | |
| Supervisor | 8-6 | 9-5 | 0.249 | 0.242 | |
| Supervisor | 7-7 | 9-5 | 0.267 | 0.267 | |
| Supervisor | 8-7 | 9-6 | 0.240 | 0.239 | |
| Supervisor | 11-5 | 9-7 | 0.214 | 0.223 | |
| Supervisor | 9-7 | 8-8 | 0.243 | 0.258 | |
 Extremized | 11-5 | 11-5 | 0.248 | 0.231 | |
 Mean | 12-4 | 12-4 | 0.216 | 0.211 | |
| Season | Our call | 89-48 | 91-46 | 0.222 | 0.219 |
Week 10
1 of 14 final
Agent Breakdown
Over 137 graded games, Moonshot's Kimi with Daggy's statistical engine has the best (lowest) Brier score, 0.216, ahead of Kalshi's 0.219. Then Google's Gemini at 0.218, OpenAI's GPT at 0.219, and Anthropic's Claude at 0.221. Without the engine, the same models score 0.222 to 0.230. Averaged into one forecast, the agents with Daggy's engine scored 0.218 and the same models without it 0.224 (Kalshi 0.219); all four providers did better with it.
Models against Kalshi, over time
Click a provider to compare its engine-on line (solid) with its engine-off line (dashed). You can also click a line or its name.
Each line is a running total: game by game, it adds how much lower (up) or higher (down) that agent’s Brier was than Kalshi’s on the same game, so a rising line is beating the market. For example, Moonshot · engine on ends at +.50 over 137 games: +.004 per game, the gap between its season Brier and Kalshi’s in the table below. Click any Brier there to see the game-by-game sum. Totals run all season per provider; the week-3 rule marks the model upgrade.
Season and week by week
Engine on means the agent ran with the Daggy stats engine; engine off is the same model without it. Each cell shows Brier (lower is better) over W–L; a forecast of exactly 50% counts as picking the home team. Kalshi’s row is the market to beat, and the best Brier in each column is bold. Click a column to sort, a provider to highlight it on the chart, or a Brier to see its games.
| Market-redacted | Market-aware | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| market-redacted | market-redacted | market-redacted | market-redacted | market-redacted | market-redacted | market-redacted | market-redacted | market-aware | market-aware | ||
| Kalshi | 91–46 | 0–1 | 14–1 | 10–4 | 9–5 | 9–5 | 9–6 | 9–7 | 8–8 | 11–5 | 12–4 |
| Average of 4 | |||||||||||
| Engine on | 91–46 | 0–1 | 14–1 | 10–4 | 9–5 | 7–7 | 8–7 | 11–5 | 9–7 | 11–5 | 12–4 |
| Engine off | 90–47 | 0–1 | 14–1 | 10–4 | 7–7 | 7–7 | 9–6 | 11–5 | 9–7 | 11–5 | 12–4 |
| Moonshot | |||||||||||
| Engine on | 89–48 | 0–1 | 14–1 | 11–3 | 7–7 | 6–8 | 8–7 | 11–5 | 10–6 | 10–6 | 12–4 |
| Engine off | 89–48 | 0–1 | 14–1 | 10–4 | 7–7 | 8–6 | 8–7 | 11–5 | 9–7 | 10–6 | 12–4 |
| Engine on | 91–46 | 0–1 | 14–1 | 10–4 | 8–6 | 7–7 | 8–7 | 11–5 | 10–6 | 11–5 | 12–4 |
| Engine off | 88–49 | 0–1 | 14–1 | 10–4 | 7–7 | 7–7 | 9–6 | 9–7 | 9–7 | 11–5 | 12–4 |
| OpenAI | |||||||||||
| Engine on | 90–47 | 0–1 | 14–1 | 10–4 | 9–5 | 8–6 | 8–7 | 9–7 | 10–6 | 11–5 | 11–5 |
| Engine off | 88–49 | 0–1 | 14–1 | 8–6 | 7–7 | 7–7 | 9–6 | 11–5 | 9–7 | 11–5 | 12–4 |
| Anthropic | |||||||||||
| Engine on | 89–48 | 0–1 | 14–1 | 11–3 | 7–7 | 7–7 | 8–7 | 10–6 | 9–7 | 11–5 | 12–4 |
| Engine off | 86–51 | 0–1 | 14–1 | 9–5 | 8–6 | 6–8 | 9–6 | 9–7 | 8–8 | 11–5 | 12–4 |
Questions About AI NFL Predictions
How accurate are AI NFL predictions?
Through 137 graded games this season, Daggy's combined AI forecast has picked the winner 89 times and missed 48 (65.0%), with a Brier score of 0.222. Kalshi's prediction market, the benchmark to beat, scores 0.219, so the market is slightly ahead. Lower Brier is better: 0 is a perfect forecast and 0.25 is calling every game 50-50.
Which AI model predicts NFL games best?
Over 137 graded games, Moonshot's Kimi with Daggy's statistical engine has the best (lowest) Brier score, 0.216, ahead of Kalshi's 0.219. Then Google's Gemini at 0.218, OpenAI's GPT at 0.219, and Anthropic's Claude at 0.221. Without the engine, the same models score 0.222 to 0.230.
Does a statistics engine make AI forecasters better?
Averaged into one forecast, the agents with Daggy's engine scored 0.218 and the same models without it 0.224 (Kalshi 0.219); all four providers did better with it.
Can AI beat a prediction market like Kalshi?
Two of the four agents with Daggy's engine score better than Kalshi's 0.219 this season: Kimi 0.216 and Gemini 0.218. Daggy's combined forecast, at 0.222, is slightly behind.
How This Whole Racket Works
Why We're Running This Game
Superforecasters typically turn qualitative signals into probabilities via judgment. In a football game, these signals could be player-coach friction. But probabilistic modeling and machine learning generally beat qualitative judgment, especially when we have a well-defined quantitative target. This page documents our journey to build an AI forecasting system that mixes the judgment of frontier LLMs with Daggy’s statistical capabilities.
Every forecast is posted before kickoff and scored in public, so if the approach doesn’t work, it shows here first.
The Two Players
Daggy is not one model. It's 8 agents forecasting every game — 4 of them wired to the Daggy statistical engine, the rest working from what they can reason out — combined into a single pick per game, before kickoff.
Kalshi isn't a rival forecaster. It's the live price real money is trading at, on a market where anyone can bet on the outcome. When we say “Daggy vs. Kalshi,” we mean model vs. market — not two people guessing.
The Score
In addition to win-loss, we use the Brier score, which judges based on confidence:
Aggregation Methods
We have 8 agents predict each game, but what's left is to aggregate all 8 predictions to one forecast. We use the following methods, but commit to one before each week.
- Mean: A simple average of each agent's prediction
- Extremized: Agents often overly hedge their bets toward 50/50. Extremizing pushes the predictions toward zero-one by using Platt scaling
- Supervisor: An AI agent looks at all 8 predictions, thinks them through and then comes up with a final forecast.
For information and entertainment only. Not betting, trading, or investment advice.