Geekbench ML Score

2295
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 09:55 AM
Views 1

System Information

System Information
Operating System iOS 16.3
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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2810
301.1 IPS
 
Image Classification (F16)
100% 4350
466.1 IPS
 
Image Classification (I8)
81% 697
74.7 IPS
 
Image Segmentation (F32)
100% 5906
36.5 IPS
 
Image Segmentation (F16)
100% 8324
51.4 IPS
 
Image Segmentation (I8)
89% 1268
7.83 IPS
 
Pose Estimation (F32)
100% 1914
7.74 IPS
 
Pose Estimation (F16)
100% 4789
19.4 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 3291
115.5 IPS
 
Object Detection (F16)
100% 3388
118.9 IPS
 
Object Detection (I8)
52% 997
35.0 IPS
 
Face Detection (F32)
100% 5108
58.7 IPS
 
Face Detection (F16)
97% 9237
106.1 IPS
 
Face Detection (I8)
75% 964
11.1 IPS
 
Text Classification (F32)
100% 1899
751.0 IPS
 
Text Classification (F16)
100% 1526
603.4 IPS
 
Machine Translation (F32)
100% 2052
316.2 IPS
 
Machine Translation (F16)
100% 2045
315.2 IPS
 

Compare

Set Baseline