Geekbench ML Score

2296
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date February 22 2023 12:39 PM
Views 1

System Information

System Information
Operating System iOS 16.3.1
Model iPhone 13 Pro Max
Model IDiPhone14,3
Motherboard D64AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2839
304.1 IPS
 
Image Classification (F16)
100% 4392
470.6 IPS
 
Image Classification (I8)
81% 696
74.6 IPS
 
Image Segmentation (F32)
100% 5898
36.4 IPS
 
Image Segmentation (F16)
100% 8374
51.7 IPS
 
Image Segmentation (I8)
89% 1273
7.86 IPS
 
Pose Estimation (F32)
100% 1904
7.71 IPS
 
Pose Estimation (F16)
100% 4876
19.7 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 3236
113.6 IPS
 
Object Detection (F16)
100% 3341
117.2 IPS
 
Object Detection (I8)
52% 996
35.0 IPS
 
Face Detection (F32)
100% 5056
58.1 IPS
 
Face Detection (F16)
97% 9205
105.8 IPS
 
Face Detection (I8)
75% 967
11.1 IPS
 
Text Classification (F32)
100% 1933
764.4 IPS
 
Text Classification (F16)
100% 1517
600.0 IPS
 
Machine Translation (F32)
100% 2042
314.8 IPS
 
Machine Translation (F16)
100% 2049
315.8 IPS
 

Compare

Set Baseline Geekbench 6 now available