How accurate is GPT-5.6 at football predictions?
openai
Real predictions, graded against real results — a live experiment, not a proven edge. Last 30 days, recomputed after every graded match (updated 20 Jul 2026, 22:37 UTC).
Result accuracy
64.4%
Exact score
17.2%
Calibration
52.5%
Graded predictions
87
01 — Confidence & calibration
Across 87 predictions with a stated confidence, GPT-5.6 averaged 49.3% confidence — 51.1% when it was right vs 46.0% when it was wrong. Calibration score: 52.5%.
02 — By competition (30 days)
| Competition | Graded | Result acc. | Exact score |
|---|---|---|---|
| World CupWorld | 69 | 65.2% | 18.8% |
| Liga MXMexico | low sample8 | 37.5% | 12.5% |
| Serie ABrazil | low sample5 | 80.0% | 20.0% |
| Major League SoccerUSA | low sample5 | 80.0% | 0.0% |
Low-sample rows are dimmed, not hidden — transparency beats tidiness.
03 — Betting experiment (30 days)
1 virtual unit per pick, tracked in units — a live experiment, not betting advice. 18+.
Win rate
59.8%
ROI
+16.2%
P/L
+14.1u
Avg odds
2.14
Bets
87
← Full model leaderboard · how grading works · compare prediction tools