Accuracy
How accurate is the CrypToadz 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)
88.8%
Mean accuracy (100−APE)
83.5%
Within ±5%
28%
Within ±10%
46%
Within ±20%
70%
Bias
+8.3%
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 | 1387 | 90.0% | 50% | +5.6% |
| middle | 103 | 54.0% | 10% | +37.7% |
| grail | 179 | 86.9% | 39% | +12.7% |
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 |
|---|---|---|---|---|---|---|
| #5574 | floor · high | Nov 1, 2026 | 0.245Ξ | 0.277Ξ | +13.1% | 86.9% |
| #2008 | floor · high | Nov 1, 2026 | 0.254Ξ | 0.238Ξ | -6.3% | 93.7% |
| #1919 | floor · high | Nov 1, 2026 | 0.247Ξ | 0.239Ξ | -3.4% | 96.6% |
| #5237 | floor · high | Oct 31, 2026 | 0.242Ξ | 0.241Ξ | -0.6% | 99.4% |
| #4193 | floor · high | Oct 31, 2026 | 0.239Ξ | 0.243Ξ | +1.6% | 98.4% |
| #6359 | grail · high | Oct 31, 2026 | 0.233Ξ | 0.225Ξ | -3.4% | 96.6% |
| #1210 | grail · high | Oct 30, 2026 | 0.259Ξ | 0.318Ξ | +22.9% | 77.1% |
| #1900 | floor · medium | Oct 29, 2026 | 0.225Ξ | 0.314Ξ | +39.6% | 60.4% |
| #1332 | floor · high | Oct 29, 2026 | 0.233Ξ | 0.228Ξ | -2.1% | 97.9% |
| #229 | floor · high | Oct 28, 2026 | 0.228Ξ | 0.245Ξ | +7.4% | 92.6% |
| #5574 | floor · medium | Oct 28, 2026 | 0.280Ξ | 0.288Ξ | +2.9% | 97.1% |
| #6359 | grail · high | Oct 28, 2026 | 0.212Ξ | 0.280Ξ | +32.1% | 67.9% |
| #2241 | floor · high | Oct 27, 2026 | 0.240Ξ | 0.248Ξ | +3.3% | 96.7% |
| #3991 | floor · high | Oct 25, 2026 | 0.228Ξ | 0.236Ξ | +3.4% | 96.6% |
| #3600 | floor · high | Oct 25, 2026 | 0.224Ξ | 0.281Ξ | +25.5% | 74.6% |
| #6547 | floor · high | Oct 25, 2026 | 0.220Ξ | 0.304Ξ | +38.2% | 61.8% |
| #1981 | middle · high | Oct 24, 2026 | 0.302Ξ | 0.451Ξ | +49.3% | 50.7% |
| #3252 | floor · high | Oct 24, 2026 | 0.227Ξ | 0.299Ξ | +31.7% | 68.3% |
| #3139 | middle · medium | Oct 24, 2026 | 0.600Ξ | 0.360Ξ | -40.0% | 60.0% |
| #4097 | floor · high | Oct 23, 2026 | 0.227Ξ | 0.286Ξ | +26.0% | 74.0% |
| #6871 | floor · high | Oct 21, 2026 | 0.257Ξ | 0.251Ξ | -2.4% | 97.6% |
| #3088 | floor · high | Oct 20, 2026 | 0.228Ξ | 0.338Ξ | +48.3% | 51.8% |
| #793 | floor · medium | Oct 20, 2026 | 0.229Ξ | 0.334Ξ | +45.9% | 54.2% |
| #2497 | floor · high | Oct 18, 2026 | 0.231Ξ | 0.264Ξ | +14.3% | 85.7% |
| #2497 | floor · high | Oct 18, 2026 | 0.264Ξ | 0.247Ξ | -6.5% | 93.5% |
| #1332 | floor · high | Oct 18, 2026 | 0.231Ξ | 0.255Ξ | +10.4% | 89.6% |
| #1332 | floor · high | Oct 17, 2026 | 0.255Ξ | 0.271Ξ | +6.3% | 93.7% |
| #6560 | floor · high | Oct 17, 2026 | 0.244Ξ | 0.237Ξ | -2.9% | 97.1% |
| #4675 | floor · high | Oct 17, 2026 | 0.231Ξ | 0.290Ξ | +25.5% | 74.5% |
| #4675 | floor · high | Oct 17, 2026 | 0.290Ξ | 0.305Ξ | +5.2% | 94.8% |
| #6077 | floor · high | Oct 15, 2026 | 0.232Ξ | 0.303Ξ | +30.6% | 69.4% |
| #5993 | floor · high | Oct 13, 2026 | 0.237Ξ | 0.314Ξ | +32.5% | 67.5% |
| #5541 | floor · high | Oct 13, 2026 | 0.238Ξ | 0.247Ξ | +3.8% | 96.2% |
| #6560 | floor · high | Oct 13, 2026 | 0.239Ξ | 0.313Ξ | +31.0% | 69.0% |
| #3509 | floor · high | Oct 12, 2026 | 0.301Ξ | 0.247Ξ | -17.8% | 82.2% |
| #1056 | floor · high | Oct 11, 2026 | 0.240Ξ | 0.306Ξ | +27.5% | 72.5% |
| #5541 | floor · high | Oct 10, 2026 | 0.252Ξ | 0.260Ξ | +3.2% | 96.8% |
| #3253 | floor · high | Oct 10, 2026 | 0.236Ξ | 0.327Ξ | +38.6% | 61.4% |
| #2172 | grail · medium | Oct 9, 2026 | 0.258Ξ | 0.336Ξ | +30.4% | 69.6% |
| #292 | floor · high | Oct 9, 2026 | 0.245Ξ | 0.317Ξ | +29.4% | 70.6% |
Model cryptoadz-1793503631-2026-08-03.2 · evaluated through 11/1/2026. Method details on the methodology page.