Accuracy
How accurate is the CryptoDickbutts 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)
90.1%
Mean accuracy (100−APE)
87.5%
Within ±5%
28%
Within ±10%
50%
Within ±20%
82%
Bias
+1.2%
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 | 460 | 90.6% | 53% | +0.9% |
| middle | 14 | 80.7% | 21% | -10.1% |
| grail | 160 | 89.2% | 47% | +3.0% |
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 |
|---|---|---|---|---|---|---|
| #1531 | floor · high | Oct 31, 2026 | 0.386Ξ | 0.429Ξ | +11.1% | 88.9% |
| #1860 | floor · high | Oct 29, 2026 | 0.520Ξ | 0.447Ξ | -14.0% | 86.0% |
| #1436 | floor · high | Oct 28, 2026 | 0.385Ξ | 0.416Ξ | +8.1% | 91.9% |
| #503 | floor · high | Oct 28, 2026 | 0.399Ξ | 0.462Ξ | +15.9% | 84.1% |
| #3270 | floor · high | Oct 27, 2026 | 0.385Ξ | 0.407Ξ | +5.7% | 94.3% |
| #2467 | floor · high | Oct 26, 2026 | 0.381Ξ | 0.416Ξ | +9.2% | 90.8% |
| #533 | grail · high | Oct 25, 2026 | 0.473Ξ | 0.462Ξ | -2.3% | 97.7% |
| #886 | floor · high | Oct 25, 2026 | 0.386Ξ | 0.476Ξ | +23.3% | 76.7% |
| #1436 | floor · high | Oct 25, 2026 | 0.400Ξ | 0.476Ξ | +19.0% | 81.0% |
| #1498 | floor · high | Oct 24, 2026 | 0.473Ξ | 0.433Ξ | -8.5% | 91.5% |
| #3891 | floor · high | Oct 24, 2026 | 0.473Ξ | 0.447Ξ | -5.5% | 94.5% |
| #2467 | floor · high | Oct 22, 2026 | 0.389Ξ | 0.489Ξ | +25.7% | 74.3% |
| #3613 | grail · high | Oct 22, 2026 | 0.407Ξ | 0.654Ξ | +60.7% | 39.3% |
| #3270 | floor · high | Oct 22, 2026 | 0.406Ξ | 0.497Ξ | +22.4% | 77.6% |
| #4973 | floor · high | Oct 21, 2026 | 0.420Ξ | 0.439Ξ | +4.5% | 95.5% |
| #596 | grail · high | Oct 21, 2026 | 0.549Ξ | 0.570Ξ | +3.8% | 96.2% |
| #2241 | floor · high | Oct 20, 2026 | 0.463Ξ | 0.407Ξ | -12.1% | 87.9% |
| #2241 | floor · high | Oct 20, 2026 | 0.386Ξ | 0.469Ξ | +21.5% | 78.5% |
| #599 | floor · high | Oct 18, 2026 | 0.500Ξ | 0.450Ξ | -10.0% | 90.0% |
| #249 | floor · high | Oct 18, 2026 | 0.500Ξ | 0.479Ξ | -4.2% | 95.8% |
| #3000 | floor · high | Oct 18, 2026 | 0.398Ξ | 0.455Ξ | +14.3% | 85.7% |
| #4800 | middle · high | Oct 17, 2026 | 1.000Ξ | 0.788Ξ | -21.2% | 78.8% |
| #172 | floor · high | Oct 17, 2026 | 0.394Ξ | 0.486Ξ | +23.4% | 76.7% |
| #3000 | floor · high | Oct 15, 2026 | 0.410Ξ | 0.371Ξ | -9.5% | 90.5% |
| #4297 | floor · high | Oct 13, 2026 | 0.472Ξ | 0.472Ξ | -0.1% | 99.9% |
| #3270 | floor · high | Oct 12, 2026 | 0.473Ξ | 0.421Ξ | -11.0% | 89.0% |
| #1612 | floor · high | Oct 12, 2026 | 0.411Ξ | 0.428Ξ | +4.1% | 95.9% |
| #3270 | floor · high | Oct 12, 2026 | 0.421Ξ | 0.415Ξ | -1.4% | 98.6% |
| #3419 | floor · high | Oct 11, 2026 | 0.515Ξ | 0.406Ξ | -21.2% | 78.8% |
| #5177 | grail · high | Oct 10, 2026 | 0.470Ξ | 0.435Ξ | -7.5% | 92.6% |
| #1616 | grail · high | Oct 9, 2026 | 0.473Ξ | 0.424Ξ | -10.4% | 89.6% |
| #1252 | floor · high | Oct 9, 2026 | 0.499Ξ | 0.468Ξ | -6.2% | 93.8% |
| #1616 | grail · high | Oct 9, 2026 | 0.410Ξ | 0.411Ξ | +0.2% | 99.8% |
| #596 | grail · high | Oct 9, 2026 | 0.551Ξ | 0.499Ξ | -9.4% | 90.6% |
| #3613 | grail · high | Oct 8, 2026 | 0.660Ξ | 0.412Ξ | -37.6% | 62.4% |
| #2467 | floor · high | Oct 8, 2026 | 0.450Ξ | 0.419Ξ | -6.9% | 93.1% |
| #1252 | floor · high | Oct 6, 2026 | 0.460Ξ | 0.411Ξ | -10.7% | 89.4% |
| #4364 | floor · high | Oct 4, 2026 | 0.558Ξ | 0.378Ξ | -32.3% | 67.7% |
| #3780 | floor · high | Oct 3, 2026 | 0.800Ξ | 0.376Ξ | -53.0% | 47.0% |
| #893 | floor · high | Oct 3, 2026 | 0.489Ξ | 0.415Ξ | -15.1% | 84.9% |
Model cryptodickbutts-1793480279-2026-08-03.2 · evaluated through 10/31/2026. Method details on the methodology page.