Which AI predicts sports best?
GLM 5.2, Claude Opus 4.8, Grok 4.5, DeepSeek V4 Pro, Claude Sonnet 5, GPT-5.6 Luna Pro, Gemini 3.6 Flash, Gemini 3.7 Flash, and Kimi K3 — head to head on real games. Each gets the identical line-blind data packet (no betting line, no web search), locks its call ~3 hours before first pitch, and is graded in public. No edits, no do-overs.
The honest finding so far: nobody beats the closing line consistently — not even the frontier models. The race worth watching is who gets closest.
New: the July 2026 benchmark report, the month's numbers frozen and citable.
MLB standings · ranked by Brier (lower = better)
95 graded games · last 7 days| # | Model | Record | AccAccuracy | Brier | ROI |
|---|---|---|---|---|---|
| 1 | DeepSeek V4 Pro | 55–28 | 66% | 0.221 | +14.1% |
| 2 | Kimi K3 | 59–32 | 65% | 0.227 | +11.8% |
| 3 | GLM 5.2 | 62–33 | 65% | 0.228 | +13.1% |
| 4 | Claude Opus 4.8 | 62–33 | 65% | 0.229 | +13.0% |
| 5 | Gemini 3.6 Flash | 62–33 | 65% | 0.230 | +12.5% |
| 6 | Claude Sonnet 5 | 62–33 | 65% | 0.230 | +13.5% |
| 7 | Grok 4.5 | 59–36 | 62% | 0.230 | +6.8% |
| 8 | Gemini 3.7 Flash | 61–33 | 65% | 0.230 | +11.7% |
| 9 | GPT-5.6 Luna Pro | 60–35 | 63% | 0.231 | +8.6% |
| 10 | Pick the favoritebaseline | 65–30 | 68% | 0.316 | +18.7% |
| 11 | Pick the home teambaseline | 56–39 | 59% | 0.411 | +3.9% |
Brier = mean squared error of the win probability (0 = perfect, 0.25 = a coin flip). Accuracy = how often the model's side won. ROI = return on a 1-unit bet on each pick at the closing market price (so beating the vig means clearing ~0%). CLV = closing-line value: how far the market moved toward the model's side between the moment it picked and first pitch, in percentage points. Positive means it was on the right side of the move, which shows up long before win/loss does. A typical MLB line moves about 1.9 points, so these are fractions of the available move. The baselines are the bar: an AI that can't out-forecast "pick the home team" isn't forecasting. Early samples are small — read with care.
The raw rows behind this board are an open dataset (CC BY 4.0): every graded prediction with results, closing prices and CLV, refreshed weekly. Each month's numbers freeze into the monthly benchmark report.
Embed this board on your site
Copy-paste, free, updates itself. Add ?theme=dark or ?rows=5 to the iframe URL to taste.
predictedsports.com
Get our sports prediction daily newsletter
Featuring our models and analysis — the AI board, our own picks, and where they disagree. Free, in your inbox every morning.
Run totals · over/under, ranked by accuracy
| # | Model | O/U acc | Avg miss | ROI |
|---|---|---|---|---|
| 1 | Claude Opus 4.8 | 54% | ±3.6 | +8.2% |
| 2 | Kimi K3 | 52% | ±3.5 | +4.4% |
| 3 | GPT-5.6 Luna Pro | 51% | ±3.5 | +1.7% |
| 4 | DeepSeek V4 Pro | 50% | ±3.6 | -0.4% |
| 5 | GLM 5.2 | 50% | ±3.6 | -0.1% |
| 6 | Gemini 3.6 Flash | 50% | ±3.6 | -0.1% |
| 7 | Claude Sonnet 5 | 49% | ±3.6 | -2.1% |
| 8 | Grok 4.5 | 47% | ±3.6 | -7.1% |
| 9 | Gemini 3.7 Flash | 40% | ±3.6 | -20.8% |
| Market (closing line)baseline | 47% | — | -8.9% |
Each model projects the game's total runs (line-blind); we grade its over/under call against the closing market line (a no-vig multi-book consensus via The Odds API where captured; Kalshi before that). O/U acc = how often that call was right. Avg miss = mean runs off the actual total. ROI = return on a 1-unit bet at the closing price — so break-even is the market's price (here the favored side runs ~59¢), not 50%: a model can top 50% and still lose to the vig. The Market (closing line) row is the bar to clear. Early samples are small — read with care.
predictedsports.com
🔒 See each model's projected total on every game — not just the scoreboard.
Start 7-day free trialUFC — best fight forecasters
Same idea, in the cage: every model gets the identical line-blind fight packet — no odds, no search — calls the winner and the method, and is graded on both. Follow the picks on every card.
No graded fights yet. Each model's locked picks grade as fights resolve — the board fills from the next card on.
Premier League — best soccer forecasters
Line-blind soccer forecasting: models call 1X2 match winner (home, draw, away), total goals, and BTTS with live injury reports. Follow every fixture on the Premier League AI Pick Board.
Matchweek 1 predictions are locked and live on the board. Standings will grade automatically as matches conclude.
How it works
Line-blind. No model ever sees the betting line. Each produces its own win probabilities and run projections from the data alone, so the board reads forecasting skill — not an echo of the market.
One packet, no search. Every model gets the same point-in-time data (ratings, Statcast, bullpens, park/umpire, situational splits) ~3h before first pitch. No web search, so it's the models we're measuring.
Graded in public, no do-overs. Each model makes one call per game and we live with it — against the outcome (accuracy, Brier) and against the closing price (ROI). Our own house models get the same treatment on the accuracy page.
Where the Index goes next
The standings change every night. Get the update.
Who's hot, who's slipping, where the AIs disagree — free in your inbox every morning.