Geekbench ML Score

7409
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 09:42 AM
Views 8

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 7.33 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3380
632.5 IPS
 
Image Classification (F16)
100% 6473
1.21 KIPS
 
Image Classification (I8)
99% 6781
1.27 KIPS
 
Image Segmentation (F32)
100% 1456
24.3 IPS
 
Image Segmentation (F16)
100% 1582
26.4 IPS
 
Image Segmentation (I8)
100% 1626
27.2 IPS
 
Pose Estimation (F32)
100% 23509
28.5 IPS
 
Pose Estimation (F16)
100% 79932
96.8 IPS
 
Pose Estimation (I8)
100% 84411
102.2 IPS
 
Object Detection (F32)
100% 2840
212.0 IPS
 
Object Detection (F16)
100% 3722
277.9 IPS
 
Object Detection (I8)
97% 2611
194.9 IPS
 
Face Detection (F32)
100% 9338
111.0 IPS
 
Face Detection (F16)
97% 10638
126.5 IPS
 
Face Detection (I8)
96% 10654
126.7 IPS
 
Depth Estimation (F32)
100% 16449
127.6 IPS
 
Depth Estimation (F16)
100% 39833
308.9 IPS
 
Depth Estimation (I8)
37% 35995
279.1 IPS
 
Style Transfer (F32)
100% 40382
53.1 IPS
 
Style Transfer (F16)
100% 131098
172.4 IPS
 
Style Transfer (I8)
100% 129460
170.3 IPS
 
Image Super-Resolution (F32)
100% 9522
340.1 IPS
 
Image Super-Resolution (F16)
100% 18002
642.9 IPS
 
Image Super-Resolution (I8)
100% 18486
660.2 IPS
 
Text Classification (F32)
100% 1119
1.61 KIPS
 
Text Classification (F16)
100% 741
1.06 KIPS
 
Text Classification (I8)
96% 740
1.06 KIPS
 
Machine Translation (F32)
100% 788
14.5 IPS
 
Machine Translation (F16)
100% 2600
47.8 IPS
 
Machine Translation (I8)
99% 749
13.8 IPS
 

Compare

Set Baseline Geekbench 6 now available