Geekbench ML Score

1786
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 29 2025 06:21 AM
Views 5

System Information

System Information
Operating System iOS 15.4.1
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4126
442.1 IPS
 
Image Classification (F16)
100% 4194
449.3 IPS
 
Image Classification (I8)
81% 419
44.9 IPS
 
Image Segmentation (F32)
100% 1426
8.81 IPS
 
Image Segmentation (F16)
100% 1427
8.81 IPS
 
Image Segmentation (I8)
89% 766
4.73 IPS
 
Pose Estimation (F32)
100% 13644
55.2 IPS
 
Pose Estimation (F16)
100% 13475
54.5 IPS
 
Pose Estimation (I8)
80% 147
0.59 IPS
 
Object Detection (F32)
100% 4995
175.3 IPS
 
Object Detection (F16)
100% 4969
174.4 IPS
 
Object Detection (I8)
52% 600
21.1 IPS
 
Face Detection (F32)
100% 6124
70.4 IPS
 
Face Detection (F16)
100% 6125
70.4 IPS
 
Face Detection (I8)
75% 587
6.75 IPS
 
Text Classification (F32)
100% 688
271.9 IPS
 
Text Classification (F16)
100% 690
272.8 IPS
 
Machine Translation (F32)
100% 1128
173.8 IPS
 
Machine Translation (F16)
100% 1141
175.9 IPS
 

Compare

Set Baseline Geekbench 6 now available