Geekbench ML Score

4508
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date March 27 2025 03:56 AM
Views 1

System Information

System Information
Operating System iOS 18.3.2
Model iPhone17,2
Model IDiPhone17,2
Motherboard D94AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 4.04 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.45 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 11437
1.23 KIPS
 
Image Classification (F16)
100% 11295
1.21 KIPS
 
Image Classification (I8)
81% 983
105.4 IPS
 
Image Segmentation (F32)
100% 4054
25.0 IPS
 
Image Segmentation (F16)
100% 3998
24.7 IPS
 
Image Segmentation (I8)
89% 1768
10.9 IPS
 
Pose Estimation (F32)
100% 40630
164.4 IPS
 
Pose Estimation (F16)
100% 40200
162.7 IPS
 
Pose Estimation (I8)
80% 303
1.23 IPS
 
Object Detection (F32)
100% 10122
355.2 IPS
 
Object Detection (F16)
100% 9652
338.7 IPS
 
Object Detection (I8)
52% 1356
47.6 IPS
 
Face Detection (F32)
100% 13074
150.2 IPS
 
Face Detection (F16)
100% 12997
149.3 IPS
 
Face Detection (I8)
75% 1391
16.0 IPS
 
Text Classification (F32)
100% 2222
878.7 IPS
 
Text Classification (F16)
100% 2233
883.2 IPS
 
Machine Translation (F32)
100% 3088
475.9 IPS
 
Machine Translation (F16)
100% 3088
475.9 IPS
 

Compare

Set Baseline Geekbench 6 now available