AppraisrAppraisr
CryptoPunks V1

CryptoPunks V1

5,141 items · Body types

OpenSea ↗
Accuracy

How accurate is the CryptoPunks V1 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)
89.7%
Mean accuracy (100−APE)
86.1%
Within ±5%
28%
Within ±10%
49%
Within ±20%
77%
Bias
-1.4%

Accuracy by market tier

Floor, middle-market, and grail sales are scored separately so aggregate accuracy cannot hide a weak segment

TierSalesMedian accuracyWithin ±10%Bias
floor128990.4%51%-2.2%
middle9875.9%23%+9.9%
grail2785.3%33%-5.3%

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

ItemBodyTier / evidenceDateSaleModelErrorAccuracy
#6927Malefloor · highSep 17, 20262.100Ξ2.011Ξ-4.2%95.8%
#5235Malemiddle · highSep 17, 20263.980Ξ3.649Ξ-8.3%91.7%
#1592Malefloor · highSep 17, 20262.200Ξ2.260Ξ+2.7%97.3%
#6927Malefloor · highSep 17, 20261.860Ξ2.236Ξ+20.2%79.8%
#6996Malefloor · highSep 16, 20262.400Ξ2.250Ξ-6.3%93.8%
#5235Malemiddle · highSep 16, 20263.650Ξ3.496Ξ-4.2%95.8%
#1848Malefloor · highSep 16, 20261.889Ξ2.043Ξ+8.2%91.9%
#3416Malefloor · highSep 16, 20264.000Ξ2.470Ξ-38.3%61.8%
#2259Malefloor · highSep 15, 20263.000Ξ2.396Ξ-20.1%79.9%
#9814Femalefloor · highSep 14, 20261.778Ξ1.968Ξ+10.7%89.3%
#1175Malefloor · highSep 14, 20262.220Ξ2.306Ξ+3.9%96.1%
#3320Malefloor · highSep 14, 20261.960Ξ2.144Ξ+9.4%90.6%
#2398Femalefloor · highSep 14, 20261.940Ξ1.836Ξ-5.4%94.6%
#8516Femalefloor · highSep 14, 20261.800Ξ1.855Ξ+3.1%96.9%
#8007Femalefloor · highSep 14, 20261.850Ξ1.855Ξ+0.3%99.7%
#8259Malefloor · highSep 13, 20262.500Ξ2.461Ξ-1.6%98.4%
#6873Malefloor · highSep 13, 20262.299Ξ2.381Ξ+3.6%96.4%
#8007Femalefloor · highSep 13, 20261.750Ξ1.916Ξ+9.5%90.5%
#4840Malefloor · highSep 12, 20262.690Ξ2.291Ξ-14.8%85.2%
#1610Malefloor · highSep 12, 20261.810Ξ2.221Ξ+22.7%77.3%
#8516Femalefloor · highSep 12, 20261.880Ξ1.969Ξ+4.7%95.3%
#3371Femalefloor · highSep 11, 20261.870Ξ2.012Ξ+7.6%92.4%
#2653Malefloor · highSep 9, 20262.350Ξ2.265Ξ-3.6%96.4%
#2753Malemiddle · highSep 8, 20268.955Ξ4.631Ξ-48.3%51.7%
#9632Femalefloor · highSep 6, 20261.800Ξ1.873Ξ+4.1%95.9%
#7221Malefloor · highSep 6, 20262.050Ξ2.184Ξ+6.5%93.5%
#7221Malefloor · highSep 5, 20262.020Ξ2.593Ξ+28.4%71.6%
#4781Malefloor · highSep 5, 20261.880Ξ2.463Ξ+31.0%69.0%
#6871Malefloor · highSep 4, 20262.700Ξ2.255Ξ-16.5%83.5%
#6871Malefloor · highSep 4, 20262.100Ξ2.468Ξ+17.5%82.5%
#4911Femalefloor · highSep 3, 20261.830Ξ1.907Ξ+4.2%95.8%
#7313Malefloor · highSep 3, 20262.220Ξ2.200Ξ-0.9%99.1%
#7081Femalefloor · highSep 1, 20261.870Ξ1.907Ξ+2.0%98.0%
#8512Femalefloor · highSep 1, 20261.870Ξ1.933Ξ+3.4%96.6%
#2653Malefloor · highSep 1, 20262.230Ξ2.453Ξ+10.0%90.0%
#5949Femalefloor · highSep 1, 202614.00Ξ2.051Ξ-85.4%14.7%
#4521Malefloor · highAug 31, 20261.940Ξ2.266Ξ+16.8%83.2%
#1191Malefloor · highAug 31, 20262.700Ξ2.186Ξ-19.0%81.0%
#7122Femalefloor · highAug 31, 20262.000Ξ2.030Ξ+1.5%98.5%
#2970Malefloor · highAug 31, 20262.211Ξ2.131Ξ-3.6%96.4%

Model v1-punks-1789644575-2026-08-03.2 · evaluated through 9/17/2026. Method details on the methodology page.