Geekbench ML Score

943
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 10:45 AM
Views 1

System Information

System Information
Operating System iOS 15.4.1
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 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 794
85.1 IPS
 
Image Classification (F16)
100% 761
81.6 IPS
 
Image Classification (I8)
81% 451
48.4 IPS
 
Image Segmentation (F32)
100% 1153
7.12 IPS
 
Image Segmentation (F16)
100% 1128
6.97 IPS
 
Image Segmentation (I8)
89% 1436
8.87 IPS
 
Pose Estimation (F32)
100% 438
1.77 IPS
 
Pose Estimation (F16)
100% 430
1.74 IPS
 
Pose Estimation (I8)
80% 496
2.01 IPS
 
Object Detection (F32)
100% 1110
38.9 IPS
 
Object Detection (F16)
100% 1120
39.3 IPS
 
Object Detection (I8)
52% 732
25.7 IPS
 
Face Detection (F32)
100% 1370
15.7 IPS
 
Face Detection (F16)
100% 1341
15.4 IPS
 
Face Detection (I8)
75% 843
9.69 IPS
 
Text Classification (F32)
100% 1173
464.0 IPS
 
Text Classification (F16)
100% 1100
435.2 IPS
 
Machine Translation (F32)
100% 1962
302.4 IPS
 
Machine Translation (F16)
100% 1962
302.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download