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)
93.1%
Mean accuracy (100−APE)
88.7%
Within ±5%
39%
Within ±10%
63%
Within ±20%
82%
Bias
-3.1%
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 | 1606 | 93.2% | 65% | -3.3% |
| middle | 46 | 81.4% | 35% | +10.9% |
| grail | 87 | 92.8% | 59% | -7.1% |
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 |
|---|---|---|---|---|---|---|
| #3195 | floor · high | Aug 2, 2026 | 0.187Ξ | 0.215Ξ | +15.0% | 85.0% |
| #5530 | floor · high | Aug 2, 2026 | 0.187Ξ | 0.200Ξ | +7.0% | 93.1% |
| #3179 | floor · high | Aug 2, 2026 | 0.187Ξ | 0.211Ξ | +12.8% | 87.2% |
| #9254 | floor · high | Aug 2, 2026 | 0.201Ξ | 0.213Ξ | +6.0% | 94.0% |
| #9884 | floor · high | Aug 1, 2026 | 0.200Ξ | 0.215Ξ | +7.5% | 92.5% |
| #6388 | floor · high | Aug 1, 2026 | 0.208Ξ | 0.201Ξ | -3.4% | 96.6% |
| #2301 | floor · high | Aug 1, 2026 | 0.191Ξ | 0.269Ξ | +40.8% | 59.2% |
| #6388 | middle · high | Aug 1, 2026 | 0.189Ξ | 0.307Ξ | +62.4% | 37.6% |
| #2943 | floor · high | Aug 1, 2026 | 0.201Ξ | 0.255Ξ | +26.9% | 73.1% |
| #3074 | floor · high | Jul 31, 2026 | 0.211Ξ | 0.209Ξ | -1.0% | 99.0% |
| #6633 | floor · high | Jul 31, 2026 | 0.200Ξ | 0.216Ξ | +8.0% | 92.0% |
| #8305 | floor · high | Jul 31, 2026 | 0.193Ξ | 0.217Ξ | +12.4% | 87.6% |
| #3074 | floor · high | Jul 31, 2026 | 0.195Ξ | 0.231Ξ | +18.5% | 81.5% |
| #7679 | floor · high | Jul 31, 2026 | 0.234Ξ | 0.210Ξ | -10.3% | 89.7% |
| #3833 | floor · high | Jul 31, 2026 | 0.209Ξ | 0.207Ξ | -1.2% | 98.8% |
| #9572 | floor · high | Jul 31, 2026 | 0.227Ξ | 0.205Ξ | -9.9% | 90.2% |
| #5591 | middle · medium | Jul 30, 2026 | 0.265Ξ | 0.313Ξ | +18.1% | 81.9% |
| #9814 | floor · high | Jul 30, 2026 | 0.450Ξ | 0.284Ξ | -36.9% | 63.1% |
| #6701 | floor · high | Jul 30, 2026 | 0.204Ξ | 0.221Ξ | +8.3% | 91.7% |
| #9279 | floor · high | Jul 30, 2026 | 0.219Ξ | 0.213Ξ | -2.7% | 97.3% |
| #8530 | floor · high | Jul 30, 2026 | 0.218Ξ | 0.236Ξ | +8.3% | 91.7% |
| #6701 | floor · high | Jul 30, 2026 | 0.218Ξ | 0.216Ξ | -0.9% | 99.1% |
| #5420 | floor · high | Jul 29, 2026 | 0.227Ξ | 0.254Ξ | +11.7% | 88.3% |
| #3833 | floor · high | Jul 29, 2026 | 0.209Ξ | 0.209Ξ | 0.0% | 100.0% |
| #90 | floor · high | Jul 29, 2026 | 0.229Ξ | 0.229Ξ | 0.0% | 100.0% |
| #2910 | floor · high | Jul 29, 2026 | 0.212Ξ | 0.231Ξ | +9.0% | 91.0% |
| #1063 | floor · high | Jul 28, 2026 | 0.213Ξ | 0.243Ξ | +14.1% | 85.9% |
| #1574 | floor · high | Jul 27, 2026 | 0.212Ξ | 0.215Ξ | +1.3% | 98.7% |
| #9332 | floor · high | Jul 27, 2026 | 0.214Ξ | 0.218Ξ | +1.9% | 98.1% |
| #9884 | floor · high | Jul 27, 2026 | 0.214Ξ | 0.231Ξ | +7.9% | 92.1% |
| #1735 | floor · high | Jul 27, 2026 | 0.227Ξ | 0.215Ξ | -5.5% | 94.5% |
| #4129 | floor · high | Jul 27, 2026 | 0.227Ξ | 0.217Ξ | -4.6% | 95.4% |
| #2532 | floor · high | Jul 26, 2026 | 0.339Ξ | 0.251Ξ | -25.9% | 74.1% |
| #7531 | floor · high | Jul 26, 2026 | 0.228Ξ | 0.216Ξ | -5.3% | 94.7% |
| #8139 | grail · high | Jul 26, 2026 | 0.228Ξ | 0.225Ξ | -1.3% | 98.8% |
| #1735 | floor · high | Jul 26, 2026 | 0.212Ξ | 0.202Ξ | -4.7% | 95.3% |
| #1574 | floor · high | Jul 26, 2026 | 0.212Ξ | 0.220Ξ | +3.8% | 96.2% |
| #7218 | floor · high | Jul 25, 2026 | 0.329Ξ | 0.220Ξ | -33.1% | 66.9% |
| #2910 | floor · high | Jul 25, 2026 | 0.231Ξ | 0.212Ξ | -8.2% | 91.8% |
| #1574 | floor · high | Jul 25, 2026 | 0.220Ξ | 0.195Ξ | -11.4% | 88.6% |
Model bored-ape-kennel-club-1785688907-2026-08-03.2 · evaluated through 8/2/2026. Method details on the methodology page.