Geekbench ML Score

420
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 27 2025 03:13 PM
Views 12

System Information

System Information
Operating System iOS 15.8.4
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% 549
58.8 IPS
 
Image Classification (F16)
100% 580
62.2 IPS
 
Image Classification (I8)
81% 121
13.0 IPS
 
Image Segmentation (F32)
100% 1518
9.37 IPS
 
Image Segmentation (F16)
100% 2519
15.6 IPS
 
Image Segmentation (I8)
89% 190
1.17 IPS
 
Pose Estimation (F32)
100% 631
2.55 IPS
 
Pose Estimation (F16)
100% 1153
4.67 IPS
 
Pose Estimation (I8)
80% 34
0.14 IPS
 
Object Detection (F32)
100% 632
22.2 IPS
 
Object Detection (F16)
100% 671
23.5 IPS
 
Object Detection (I8)
52% 121
4.24 IPS
 
Face Detection (F32)
100% 1426
16.4 IPS
 
Face Detection (F16)
97% 2068
23.8 IPS
 
Face Detection (I8)
75% 105
1.21 IPS
 
Text Classification (F32)
100% 383
151.7 IPS
 
Text Classification (F16)
98% 518
204.7 IPS
 
Machine Translation (F32)
100% 178
27.5 IPS
 
Machine Translation (F16)
100% 183
28.1 IPS
 

Compare

Set Baseline Geekbench 6 now available