Geekbench ML Score

432
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 09 2024 08:40 AM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (10.5-inch)
Model IDiPad7,4
Motherboard J208AP
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% 243
45.4 IPS
 
Image Classification (F16)
100% 212
39.7 IPS
 
Image Classification (I8)
99% 216
40.5 IPS
 
Image Segmentation (F32)
100% 152
2.54 IPS
 
Image Segmentation (F16)
100% 152
2.55 IPS
 
Image Segmentation (I8)
100% 153
2.55 IPS
 
Pose Estimation (F32)
100% 1493
1.81 IPS
 
Pose Estimation (F16)
100% 1481
1.79 IPS
 
Pose Estimation (I8)
100% 1485
1.80 IPS
 
Object Detection (F32)
100% 278
20.7 IPS
 
Object Detection (F16)
100% 245
18.3 IPS
 
Object Detection (I8)
97% 279
20.8 IPS
 
Face Detection (F32)
100% 532
6.33 IPS
 
Face Detection (F16)
100% 524
6.23 IPS
 
Face Detection (I8)
99% 524
6.23 IPS
 
Depth Estimation (F32)
100% 692
5.36 IPS
 
Depth Estimation (F16)
100% 626
4.86 IPS
 
Depth Estimation (I8)
99% 625
4.85 IPS
 
Style Transfer (F32)
100% 2184
2.87 IPS
 
Style Transfer (F16)
100% 2178
2.87 IPS
 
Style Transfer (I8)
100% 2181
2.87 IPS
 
Image Super-Resolution (F32)
100% 680
24.3 IPS
 
Image Super-Resolution (F16)
100% 667
23.8 IPS
 
Image Super-Resolution (I8)
100% 672
24.0 IPS
 
Text Classification (F32)
100% 162
232.2 IPS
 
Text Classification (F16)
100% 141
202.0 IPS
 
Text Classification (I8)
96% 133
191.5 IPS
 
Machine Translation (F32)
100% 250
4.60 IPS
 
Machine Translation (F16)
100% 212
3.90 IPS
 
Machine Translation (I8)
99% 251
4.61 IPS
 

Compare

Set Baseline Geekbench 6 now available