Accuracy
How accurate is the Bored Ape Kennel Club model?
Every score comes from the newest chronological hold-out; the target sale is excluded from training, comparables, and its causal floor proxy.
Median accuracy (100−APE)
92.9%
Mean accuracy (100−APE)
88.5%
Within ±5%
40%
Within ±10%
62%
Within ±20%
82%
Bias
-3.5%
Accuracy by market tier
Floor, middle-market, and grail sales are scored separately so aggregate accuracy cannot hide a weak segment
| Tier | Sales | Median accuracy | Within ±10% | Bias |
|---|---|---|---|---|
| floor | 1646 | 93.1% | 63% | -4.0% |
| middle | 46 | 85.1% | 39% | +17.7% |
| grail | 103 | 92.5% | 61% | -5.2% |
Weekly median accuracy
Chronological hold-out accuracy by sale week
Error distribution
Signed hold-out error; positive means over-predicted
Scored hold-out sales
60 out-of-sample predictions frozen at evaluation time
| Item | Tier / evidence | Date | Sale | Model | Error | Accuracy |
|---|---|---|---|---|---|---|
| #2943 | floor · high | Sep 13, 2026 | 0.182Ξ | 0.185Ξ | +1.7% | 98.4% |
| #6398 | floor · high | Sep 13, 2026 | 0.161Ξ | 0.154Ξ | -4.2% | 95.8% |
| #2667 | floor · high | Sep 13, 2026 | 0.161Ξ | 0.149Ξ | -7.3% | 92.7% |
| #7923 | floor · high | Sep 13, 2026 | 0.152Ξ | 0.158Ξ | +4.0% | 96.1% |
| #6082 | floor · high | Sep 12, 2026 | 0.154Ξ | 0.150Ξ | -2.6% | 97.4% |
| #7923 | floor · high | Sep 11, 2026 | 0.159Ξ | 0.155Ξ | -2.5% | 97.5% |
| #6929 | floor · high | Sep 11, 2026 | 0.156Ξ | 0.148Ξ | -4.9% | 95.1% |
| #8854 | floor · high | Sep 10, 2026 | 0.184Ξ | 0.165Ξ | -10.3% | 89.7% |
| #8627 | floor · high | Sep 10, 2026 | 0.213Ξ | 0.148Ξ | -30.5% | 69.5% |
| #7923 | floor · high | Sep 10, 2026 | 0.157Ξ | 0.155Ξ | -1.3% | 98.7% |
| #810 | floor · high | Sep 9, 2026 | 0.162Ξ | 0.167Ξ | +2.9% | 97.1% |
| #810 | middle · high | Sep 9, 2026 | 0.147Ξ | 0.325Ξ | +121.1% | 0.0% |
| #6929 | floor · high | Sep 9, 2026 | 0.145Ξ | 0.204Ξ | +40.7% | 59.3% |
| #2876 | middle · high | Sep 9, 2026 | 0.148Ξ | 0.289Ξ | +95.3% | 4.7% |
| #5762 | middle · high | Sep 9, 2026 | 0.146Ξ | 0.264Ξ | +80.8% | 19.2% |
| #8854 | floor · high | Sep 9, 2026 | 0.163Ξ | 0.171Ξ | +4.9% | 95.1% |
| #7923 | floor · high | Sep 9, 2026 | 0.156Ξ | 0.149Ξ | -4.5% | 95.5% |
| #2557 | floor · high | Sep 8, 2026 | 0.155Ξ | 0.152Ξ | -2.0% | 98.0% |
| #8136 | grail · high | Sep 8, 2026 | 0.157Ξ | 0.156Ξ | -0.5% | 99.5% |
| #7445 | floor · high | Sep 8, 2026 | 0.180Ξ | 0.163Ξ | -9.4% | 90.6% |
| #2557 | floor · high | Sep 8, 2026 | 0.146Ξ | 0.156Ξ | +6.9% | 93.2% |
| #8136 | grail · high | Sep 7, 2026 | 0.145Ξ | 0.170Ξ | +17.2% | 82.8% |
| #9424 | floor · high | Sep 7, 2026 | 0.151Ξ | 0.165Ξ | +9.3% | 90.7% |
| #7923 | floor · high | Sep 7, 2026 | 0.153Ξ | 0.166Ξ | +8.5% | 91.5% |
| #2523 | floor · high | Sep 7, 2026 | 0.154Ξ | 0.169Ξ | +10.0% | 90.0% |
| #8332 | floor · high | Sep 7, 2026 | 0.147Ξ | 0.169Ξ | +15.0% | 85.0% |
| #7585 | floor · high | Sep 7, 2026 | 0.150Ξ | 0.173Ξ | +15.3% | 84.7% |
| #6945 | floor · high | Sep 6, 2026 | 0.155Ξ | 0.168Ξ | +8.4% | 91.6% |
| #3906 | floor · high | Sep 6, 2026 | 0.165Ξ | 0.172Ξ | +4.3% | 95.7% |
| #9542 | floor · medium | Sep 5, 2026 | 0.186Ξ | 0.210Ξ | +12.9% | 87.1% |
| #2557 | floor · high | Sep 5, 2026 | 0.162Ξ | 0.159Ξ | -2.1% | 97.9% |
| #6388 | floor · high | Sep 5, 2026 | 0.209Ξ | 0.169Ξ | -19.1% | 80.9% |
| #7353 | floor · high | Sep 5, 2026 | 0.160Ξ | 0.166Ξ | +3.8% | 96.3% |
| #2557 | floor · high | Sep 4, 2026 | 0.155Ξ | 0.164Ξ | +5.8% | 94.2% |
| #2665 | floor · high | Sep 4, 2026 | 0.158Ξ | 0.185Ξ | +17.1% | 82.9% |
| #6082 | floor · high | Sep 4, 2026 | 0.158Ξ | 0.184Ξ | +16.5% | 83.5% |
| #7353 | floor · high | Sep 4, 2026 | 0.167Ξ | 0.183Ξ | +9.6% | 90.4% |
| #1485 | grail · high | Sep 4, 2026 | 0.160Ξ | 0.180Ξ | +12.5% | 87.5% |
| #5552 | floor · high | Sep 4, 2026 | 0.162Ξ | 0.187Ξ | +15.4% | 84.6% |
| #6645 | floor · high | Sep 4, 2026 | 0.159Ξ | 0.179Ξ | +12.6% | 87.4% |
Model bored-ape-kennel-club-1789265027-2026-08-03.2 · evaluated through 9/13/2026. Method details on the methodology page.