Geekbench ML Score

384
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 28 2025 01:12 AM
Views 1

System Information

System Information
Operating System iOS 15.8.4
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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 484
51.9 IPS
 
Image Classification (F16)
100% 656
70.3 IPS
 
Image Classification (I8)
81% 97
10.4 IPS
 
Image Segmentation (F32)
100% 1158
7.15 IPS
 
Image Segmentation (F16)
100% 1874
11.6 IPS
 
Image Segmentation (I8)
89% 179
1.10 IPS
 
Pose Estimation (F32)
100% 451
1.83 IPS
 
Pose Estimation (F16)
100% 856
3.47 IPS
 
Pose Estimation (I8)
80% 33
0.13 IPS
 
Object Detection (F32)
100% 588
20.6 IPS
 
Object Detection (F16)
100% 745
26.1 IPS
 
Object Detection (I8)
52% 135
4.72 IPS
 
Face Detection (F32)
100% 1105
12.7 IPS
 
Face Detection (F16)
97% 1942
22.3 IPS
 
Face Detection (I8)
75% 123
1.41 IPS
 
Text Classification (F32)
100% 333
131.9 IPS
 
Text Classification (F16)
98% 397
157.0 IPS
 
Machine Translation (F32)
100% 205
31.5 IPS
 
Machine Translation (F16)
100% 204
31.5 IPS
 

Compare

Set Baseline Geekbench 6 now available