Geekbench ML Score

4339
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 08 2025 05:24 AM
Views 5

System Information

System Information
Operating System iOS 18.3
Model iPhone17,5
Model IDiPhone17,5
Motherboard V59AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.61 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.54 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 10883
1.17 KIPS
 
Image Classification (F16)
100% 11149
1.19 KIPS
 
Image Classification (I8)
81% 949
101.7 IPS
 
Image Segmentation (F32)
100% 3832
23.7 IPS
 
Image Segmentation (F16)
100% 3746
23.1 IPS
 
Image Segmentation (I8)
89% 1629
10.1 IPS
 
Pose Estimation (F32)
100% 40422
163.6 IPS
 
Pose Estimation (F16)
100% 39419
159.5 IPS
 
Pose Estimation (I8)
80% 282
1.14 IPS
 
Object Detection (F32)
100% 9772
342.9 IPS
 
Object Detection (F16)
100% 10006
351.1 IPS
 
Object Detection (I8)
52% 1260
44.2 IPS
 
Face Detection (F32)
100% 12699
145.9 IPS
 
Face Detection (F16)
100% 12362
142.0 IPS
 
Face Detection (I8)
75% 1289
14.8 IPS
 
Text Classification (F32)
100% 2223
879.1 IPS
 
Text Classification (F16)
100% 2262
894.8 IPS
 
Machine Translation (F32)
100% 2915
449.2 IPS
 
Machine Translation (F16)
100% 2921
450.2 IPS
 

Compare

Set Baseline Geekbench 6 now available