Geekbench ML Score

662
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 20 2025 07:13 PM
Views 4

System Information

System Information
Operating System iOS 15.8.3
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 569
61.0 IPS
 
Image Classification (F16)
100% 607
65.1 IPS
 
Image Classification (I8)
81% 288
30.8 IPS
 
Image Segmentation (F32)
100% 1461
9.03 IPS
 
Image Segmentation (F16)
100% 2474
15.3 IPS
 
Image Segmentation (I8)
89% 468
2.89 IPS
 
Pose Estimation (F32)
100% 626
2.53 IPS
 
Pose Estimation (F16)
100% 1182
4.78 IPS
 
Pose Estimation (I8)
80% 100
0.41 IPS
 
Object Detection (F32)
100% 905
31.7 IPS
 
Object Detection (F16)
100% 1188
41.7 IPS
 
Object Detection (I8)
52% 380
13.3 IPS
 
Face Detection (F32)
100% 1431
16.4 IPS
 
Face Detection (F16)
97% 2615
30.0 IPS
 
Face Detection (I8)
75% 335
3.85 IPS
 
Text Classification (F32)
100% 408
161.4 IPS
 
Text Classification (F16)
98% 567
224.4 IPS
 
Machine Translation (F32)
100% 536
82.6 IPS
 
Machine Translation (F16)
100% 505
77.8 IPS
 

Compare

Set Baseline Geekbench 6 now available