Geekbench ML Score

2293
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 06:23 PM
Views 2

System Information

System Information
Operating System iOS 16.0
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 5.50 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2817
301.8 IPS
 
Image Classification (F16)
100% 4387
470.0 IPS
 
Image Classification (I8)
81% 696
74.5 IPS
 
Image Segmentation (F32)
100% 5880
36.3 IPS
 
Image Segmentation (F16)
100% 8316
51.4 IPS
 
Image Segmentation (I8)
89% 1273
7.86 IPS
 
Pose Estimation (F32)
100% 1910
7.73 IPS
 
Pose Estimation (F16)
100% 4872
19.7 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 3266
114.6 IPS
 
Object Detection (F16)
100% 4269
149.8 IPS
 
Object Detection (I8)
52% 987
34.6 IPS
 
Face Detection (F32)
100% 5106
58.7 IPS
 
Face Detection (F16)
97% 9218
105.9 IPS
 
Face Detection (I8)
75% 970
11.1 IPS
 
Text Classification (F32)
100% 1524
602.8 IPS
 
Text Classification (F16)
100% 1505
595.4 IPS
 
Machine Translation (F32)
100% 2026
312.3 IPS
 
Machine Translation (F16)
100% 2023
311.8 IPS
 

Compare

Set Baseline