Geekbench ML Score

222
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 30 2025 08:44 PM
Views 2

System Information

System Information
Operating System iOS 15.8.4
Model iPad Air 2
Model IDiPad5,3
Motherboard J81AP
CPU Information
Name Apple A8X
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 1.50 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 167
17.9 IPS
 
Image Classification (F16)
100% 167
17.9 IPS
 
Image Classification (I8)
81% 373
40.0 IPS
 
Image Segmentation (F32)
100% 299
1.85 IPS
 
Image Segmentation (F16)
100% 294
1.81 IPS
 
Image Segmentation (I8)
89% 633
3.91 IPS
 
Pose Estimation (F32)
100% 107
0.43 IPS
 
Pose Estimation (F16)
100% 101
0.41 IPS
 
Pose Estimation (I8)
80% 118
0.48 IPS
 
Object Detection (F32)
100% 229
8.04 IPS
 
Object Detection (F16)
100% 226
7.93 IPS
 
Object Detection (I8)
52% 395
13.9 IPS
 
Face Detection (F32)
100% 288
3.31 IPS
 
Face Detection (F16)
100% 283
3.25 IPS
 
Face Detection (I8)
75% 378
4.34 IPS
 
Text Classification (F32)
100% 158
62.5 IPS
 
Text Classification (F16)
100% 158
62.6 IPS
 
Machine Translation (F32)
100% 181
27.9 IPS
 
Machine Translation (F16)
100% 183
28.3 IPS
 

Compare

Set Baseline Geekbench 6 now available