Geekbench ML Score

285
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 28 2021 11:23 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone 6s Plus
Model IDiPhone8,2
Motherboard N66AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 201
21.5 IPS
 
Image Classification (F16)
100% 212
22.7 IPS
 
Image Classification (I8)
81% 193
20.7 IPS
 
Image Segmentation (F32)
100% 482
2.98 IPS
 
Image Segmentation (F16)
100% 485
2.99 IPS
 
Image Segmentation (I8)
89% 365
2.25 IPS
 
Pose Estimation (F32)
100% 311
1.26 IPS
 
Pose Estimation (F16)
100% 313
1.27 IPS
 
Pose Estimation (I8)
80% 67
0.27 IPS
 
Object Detection (F32)
100% 518
18.2 IPS
 
Object Detection (F16)
100% 540
19.0 IPS
 
Object Detection (I8)
52% 277
9.72 IPS
 
Face Detection (F32)
100% 700
8.04 IPS
 
Face Detection (F16)
100% 701
8.05 IPS
 
Face Detection (I8)
75% 272
3.13 IPS
 
Text Classification (F32)
98% 67
26.4 IPS
 
Text Classification (F16)
98% 66
26.1 IPS
 
Machine Translation (F32)
100% 461
71.1 IPS
 
Machine Translation (F16)
100% 455
70.2 IPS
 

Compare

Set Baseline Geekbench 6 now available