Geekbench ML Score

1810
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 10:18 AM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPhone 11 Pro Max
Model IDiPhone12,5
Motherboard D431AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.66 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4445
476.3 IPS
 
Image Classification (F16)
100% 4472
479.1 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 1489
9.19 IPS
 
Image Segmentation (F16)
100% 1480
9.14 IPS
 
Image Segmentation (I8)
89% 830
5.13 IPS
 
Pose Estimation (F32)
100% 8414
34.0 IPS
 
Pose Estimation (F16)
100% 8454
34.2 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
94% 5412
189.9 IPS
 
Object Detection (F16)
94% 5572
195.5 IPS
 
Object Detection (I8)
52% 641
22.5 IPS
 
Face Detection (F32)
67% 5785
66.5 IPS
 
Face Detection (F16)
67% 5714
65.6 IPS
 
Face Detection (I8)
75% 636
7.30 IPS
 
Text Classification (F32)
100% 858
339.5 IPS
 
Text Classification (F16)
100% 865
342.0 IPS
 
Machine Translation (F32)
100% 1219
187.9 IPS
 
Machine Translation (F16)
100% 1211
186.7 IPS
 

Compare

Set Baseline Geekbench 6 now available