Geekbench ML Score

7414
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 06:11 PM
Views 2

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (11-inch, 4th generation)
Model IDiPad14,3
Motherboard J617AP
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.49 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.33 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3546
663.6 IPS
 
Image Classification (F16)
100% 6554
1.23 KIPS
 
Image Classification (I8)
99% 6776
1.27 KIPS
 
Image Segmentation (F32)
100% 1430
23.9 IPS
 
Image Segmentation (F16)
100% 1578
26.3 IPS
 
Image Segmentation (I8)
100% 1589
26.5 IPS
 
Pose Estimation (F32)
100% 22778
27.6 IPS
 
Pose Estimation (F16)
100% 81405
98.6 IPS
 
Pose Estimation (I8)
100% 84324
102.1 IPS
 
Object Detection (F32)
100% 2813
210.0 IPS
 
Object Detection (F16)
100% 3869
288.8 IPS
 
Object Detection (I8)
97% 2613
195.1 IPS
 
Face Detection (F32)
100% 9294
110.5 IPS
 
Face Detection (F16)
97% 10695
127.2 IPS
 
Face Detection (I8)
96% 10630
126.4 IPS
 
Depth Estimation (F32)
100% 16070
124.6 IPS
 
Depth Estimation (F16)
100% 39411
305.6 IPS
 
Depth Estimation (I8)
37% 34095
264.4 IPS
 
Style Transfer (F32)
100% 39657
52.2 IPS
 
Style Transfer (F16)
100% 131966
173.6 IPS
 
Style Transfer (I8)
100% 132867
174.8 IPS
 
Image Super-Resolution (F32)
100% 9413
336.2 IPS
 
Image Super-Resolution (F16)
100% 17733
633.3 IPS
 
Image Super-Resolution (I8)
100% 19181
685.0 IPS
 
Text Classification (F32)
100% 1102
1.58 KIPS
 
Text Classification (F16)
100% 734
1.05 KIPS
 
Text Classification (I8)
96% 746
1.07 KIPS
 
Machine Translation (F32)
100% 818
15.1 IPS
 
Machine Translation (F16)
100% 2621
48.2 IPS
 
Machine Translation (I8)
99% 768
14.1 IPS
 

Compare

Set Baseline Geekbench 6 now available