Geekbench ML Score

1387
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:18 PM
Views 4

System Information

System Information
Operating System iOS 15.2.1
Model iPhone 11 Pro
Model IDiPhone12,3
Motherboard D421AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1229
131.7 IPS
 
Image Classification (F16)
100% 1578
169.1 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 3431
21.2 IPS
 
Image Segmentation (F16)
100% 5410
33.4 IPS
 
Image Segmentation (I8)
89% 835
5.15 IPS
 
Pose Estimation (F32)
100% 1424
5.76 IPS
 
Pose Estimation (F16)
100% 4410
17.8 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
100% 1563
54.9 IPS
 
Object Detection (F16)
99% 1864
65.4 IPS
 
Object Detection (I8)
52% 640
22.5 IPS
 
Face Detection (F32)
100% 3623
41.6 IPS
 
Face Detection (F16)
97% 5382
61.8 IPS
 
Face Detection (I8)
75% 632
7.27 IPS
 
Text Classification (F32)
100% 959
379.2 IPS
 
Text Classification (F16)
98% 1209
478.1 IPS
 
Machine Translation (F32)
100% 1198
184.6 IPS
 
Machine Translation (F16)
100% 1207
186.1 IPS
 

Compare

Set Baseline Geekbench 6 now available