Geekbench ML Score

407
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 18 2024 08:40 AM
Views 1

System Information

System Information
Operating System iOS 17.5
Model iPad Pro (10.5-inch)
Model IDiPad7,3
Motherboard J207AP
CPU Information
Name Apple A10X Fusion
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 2.34 GHz
Cluster 13 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.91 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 244
45.7 IPS
 
Image Classification (F16)
100% 217
40.6 IPS
 
Image Classification (I8)
99% 217
40.6 IPS
 
Image Segmentation (F32)
100% 151
2.52 IPS
 
Image Segmentation (F16)
100% 149
2.49 IPS
 
Image Segmentation (I8)
100% 149
2.49 IPS
 
Pose Estimation (F32)
100% 1484
1.80 IPS
 
Pose Estimation (F16)
100% 1474
1.79 IPS
 
Pose Estimation (I8)
100% 1476
1.79 IPS
 
Object Detection (F32)
100% 270
20.1 IPS
 
Object Detection (F16)
100% 235
17.5 IPS
 
Object Detection (I8)
97% 265
19.8 IPS
 
Face Detection (F32)
100% 515
6.13 IPS
 
Face Detection (F16)
100% 493
5.86 IPS
 
Face Detection (I8)
99% 490
5.82 IPS
 
Depth Estimation (F32)
100% 627
4.86 IPS
 
Depth Estimation (F16)
100% 577
4.47 IPS
 
Depth Estimation (I8)
99% 576
4.46 IPS
 
Style Transfer (F32)
100% 1983
2.61 IPS
 
Style Transfer (F16)
100% 1954
2.57 IPS
 
Style Transfer (I8)
100% 1911
2.51 IPS
 
Image Super-Resolution (F32)
100% 596
21.3 IPS
 
Image Super-Resolution (F16)
100% 588
21.0 IPS
 
Image Super-Resolution (I8)
100% 587
21.0 IPS
 
Text Classification (F32)
100% 144
206.5 IPS
 
Text Classification (F16)
100% 118
170.2 IPS
 
Text Classification (I8)
96% 120
172.3 IPS
 
Machine Translation (F32)
100% 237
4.36 IPS
 
Machine Translation (F16)
100% 204
3.75 IPS
 
Machine Translation (I8)
99% 241
4.43 IPS
 

Compare

Set Baseline Geekbench 6 now available