Geekbench ML Score

937
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:36 PM
Views 1

System Information

System Information
Operating System iOS 15.1.1
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.53 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 760
81.4 IPS
 
Image Classification (F16)
100% 743
79.6 IPS
 
Image Classification (I8)
81% 445
47.7 IPS
 
Image Segmentation (F32)
100% 1119
6.91 IPS
 
Image Segmentation (F16)
100% 1085
6.70 IPS
 
Image Segmentation (I8)
89% 1458
9.00 IPS
 
Pose Estimation (F32)
100% 420
1.70 IPS
 
Pose Estimation (F16)
100% 412
1.67 IPS
 
Pose Estimation (I8)
80% 486
1.97 IPS
 
Object Detection (F32)
100% 1100
38.6 IPS
 
Object Detection (F16)
100% 1098
38.5 IPS
 
Object Detection (I8)
52% 753
26.4 IPS
 
Face Detection (F32)
100% 1329
15.3 IPS
 
Face Detection (F16)
100% 1308
15.0 IPS
 
Face Detection (I8)
75% 850
9.76 IPS
 
Text Classification (F32)
100% 1098
434.3 IPS
 
Text Classification (F16)
100% 1361
538.2 IPS
 
Machine Translation (F32)
100% 1971
303.8 IPS
 
Machine Translation (F16)
100% 1970
303.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download