Geekbench ML Score

1304
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date February 03 2025 08:17 AM
Views 5

System Information

System Information
Operating System iOS 14.3
Model iPad mini (5th generation)
Model IDiPad11,1
Motherboard J210AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.86 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3073
329.3 IPS
 
Image Classification (F16)
100% 2952
316.3 IPS
 
Image Classification (I8)
81% 400
42.9 IPS
 
Image Segmentation (F32)
100% 1383
8.54 IPS
 
Image Segmentation (F16)
100% 1368
8.45 IPS
 
Image Segmentation (I8)
89% 745
4.60 IPS
 
Pose Estimation (F32)
100% 7445
30.1 IPS
 
Pose Estimation (F16)
100% 7330
29.7 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
94% 3939
138.3 IPS
 
Object Detection (F16)
94% 3769
132.3 IPS
 
Object Detection (I8)
52% 566
19.9 IPS
 
Face Detection (F32)
67% 3466
39.8 IPS
 
Face Detection (F16)
67% 3450
39.6 IPS
 
Face Detection (I8)
75% 550
6.32 IPS
 
Text Classification (F32)
100% 268
105.9 IPS
 
Text Classification (F16)
100% 268
106.0 IPS
 
Machine Translation (F32)
100% 996
153.5 IPS
 
Machine Translation (F16)
100% 998
153.9 IPS
 

Compare

Set Baseline Geekbench 6 now available