Per-sport closing-line-value audit on the platform's recommended picks. CLV = closing price − the price we took, raw implied on both sides. The model is not in that formula, which is what makes it a test rather than a restatement of our own opinion. Positive mean CLV means our picks consistently beat the close, the standard proxy for sharp skill.
When we like a side, the price tends to move against us before the game starts. That is the earliest sign a pick was wrong, and it shows up long before results do.
| Sport | Bet type | N | Mean CLV | Median CLV | % beating close |
|---|---|---|---|---|---|
| AMERICANFOOTBALL_NFL | moneyline | 32 | +0.13pp | +0.00pp | 37.5% |
| EPL | moneyline | 32 | +4.10pp | +0.04pp | 50.0% |
| LALIGA | moneyline | 40 | +0.28pp | -0.97pp | 40.0% |
| LALIGA | over_under | 31 | -1.97pp | +0.00pp | 48.4% |
| LIGUE1 | moneyline | 31 | -1.05pp | -0.12pp | 45.2% |
| MLB | moneyline | 434 | -1.08pp | -0.51pp | 37.6% |
| MLB | over_under | 176 | -9.61pp | -2.81pp | 16.5% |
| MLB | spread | 316 | -7.74pp | -3.84pp | 19.3% |
| MMA_MIXED_MARTIAL_ARTS | moneyline | 80 | -9.32pp | -0.56pp | 28.7% |
| MMA_MIXED_MARTIAL_ARTS | over_under | 53 | -0.55pp | +0.00pp | 26.4% |
| NCAAF | moneyline | 119 | -0.16pp | +0.00pp | 3.4% |
| NCAAF | over_under | 130 | -0.12pp | +0.00pp | 0.0% |
| NCAAF | spread | 127 | -0.16pp | +0.00pp | 1.6% |
| NFL_PRESEASON | moneyline | 34 | +1.34pp | +2.24pp | 64.7% |
| NFL_PRESEASON | over_under | 33 | -0.04pp | +0.00pp | 0.0% |
| NFL_PRESEASON | spread | 30 | +0.08pp | +0.00pp | 3.3% |
| SERIEA | moneyline | 38 | -0.92pp | -1.31pp | 34.2% |
| SERIEA | over_under | 33 | -2.91pp | -2.83pp | 15.2% |
| TENNIS_ATP | moneyline | 235 | -0.70pp | +0.00pp | 39.1% |
| TENNIS_WTA | moneyline | 272 | -0.72pp | +0.00pp | 38.2% |
A number like the one above is worth little without the response to it, so here is ours, and the figure that will show whether it worked.
The test: mean CLV on the picks we recommend, non-negative at 95% confidence. Until it clears that bar we are not selling picks — and this page will keep saying so.
See /trust for live calibration buckets across sports and /methodology for the signal pipeline behind each pick.