Geekbench ML Score

167
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 17 2025 04:37 AM
Views 1

System Information

System Information
Operating System iOS 14.3
Model iPhone SE
Model IDiPhone8,4
Motherboard N69uAP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.80 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.97 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 94
10.1 IPS
 
Image Classification (F16)
100% 95
10.1 IPS
 
Image Classification (I8)
81% 174
18.6 IPS
 
Image Segmentation (F32)
100% 216
1.33 IPS
 
Image Segmentation (F16)
100% 211
1.31 IPS
 
Image Segmentation (I8)
89% 279
1.72 IPS
 
Pose Estimation (F32)
100% 56
0.23 IPS
 
Pose Estimation (F16)
100% 56
0.23 IPS
 
Pose Estimation (I8)
80% 61
0.25 IPS
 
Object Detection (F32)
100% 168
5.89 IPS
 
Object Detection (F16)
100% 166
5.83 IPS
 
Object Detection (I8)
52% 228
8.00 IPS
 
Face Detection (F32)
100% 205
2.35 IPS
 
Face Detection (F16)
100% 205
2.35 IPS
 
Face Detection (I8)
75% 228
2.62 IPS
 
Text Classification (F32)
100% 323
127.6 IPS
 
Text Classification (F16)
100% 330
130.7 IPS
 
Machine Translation (F32)
100% 240
37.0 IPS
 
Machine Translation (F16)
100% 321
49.5 IPS
 

Compare

Set Baseline Geekbench 6 now available