Anomaly Detection on MVTec-AD multi-class benchmark leaderboard · SOTA2 Research

Anomaly Detection on MVTec-AD multi-class

99.5Image-level AUROCDPDiff-AD

Evaluation Results

Method	Links
DPDiff-AD2026.05		99.5	99.9	99.1	98.7	65.6	64.8	95.9	89.1
MiniMaxAD-fr2024.05		98.8	99.6	97.7	96.1	58.5	59.5	92.2	86.1
MambaAD2024.05		98.6	99.6	97.8	97.7	56.3	59.2	93.1	86
MambaAD2026.05		98.6	99.6	97.8	97.7	56.3	59.2	93.1	86
ReContrast2026.05		98.3	99.4	97.6	97.1	60.2	61.5	93.2	86.8
ViTAD2026.05		98.3	99.4	97.3	97.7	55.3	58.7	91.4	85.4
HVQ-Trans2026.05		98	99.5	97.5	97.3	48.2	53.3	91.4	83.6
DiAD2024.05		97.2	99	96.5	96.8	52.6	55.5	90.7	84
DiAD2026.05		97.2	99	96.5	96.8	52.6	55.5	90.7	84
UniAD2024.05		96.5	98.8	96.2	96.8	43.4	49.5	90.7	81.7
UniAD2026.05		96.5	98.8	96.2	96.8	43.4	49.5	90.7	81.7
SimpleNet2024.05		95.3	98.4	95.8	96.9	45.9	49.7	86.5	81.2
SimpleNet2026.05		95.3	98.4	95.8	96.9	45.9	49.7	86.5	81.2
RD2024.05		94.6	96.5	95.2	96.1	48.6	53.8	91.1	82.3
RD4AD2026.05		94.6	96.5	95.2	96.1	48.6	53.8	91.1	82.3
DeSTSeg2026.05		89.2	95.5	91.6	93.1	54.3	50.9	64.8	77.1