Geekbench ML Score

3350
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date May 08 2024 10:29 PM
Views 1

System Information

System Information
Operating System iOS 17.4.1
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,6
Motherboard J518AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.33 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1190
222.6 IPS
 
Image Classification (F16)
100% 1184
221.5 IPS
 
Image Classification (I8)
99% 1415
264.7 IPS
 
Image Segmentation (F32)
100% 824
13.8 IPS
 
Image Segmentation (F16)
100% 830
13.9 IPS
 
Image Segmentation (I8)
100% 880
14.7 IPS
 
Pose Estimation (F32)
100% 16511
20.0 IPS
 
Pose Estimation (F16)
100% 17992
21.8 IPS
 
Pose Estimation (I8)
100% 17771
21.5 IPS
 
Object Detection (F32)
100% 1539
114.9 IPS
 
Object Detection (F16)
100% 1518
113.3 IPS
 
Object Detection (I8)
97% 1519
113.4 IPS
 
Face Detection (F32)
100% 5934
70.6 IPS
 
Face Detection (F16)
98% 7160
85.1 IPS
 
Face Detection (I8)
97% 7130
84.8 IPS
 
Depth Estimation (F32)
100% 12154
94.3 IPS
 
Depth Estimation (F16)
100% 13715
106.4 IPS
 
Depth Estimation (I8)
37% 12624
97.9 IPS
 
Style Transfer (F32)
100% 26630
35.0 IPS
 
Style Transfer (F16)
100% 32442
42.7 IPS
 
Style Transfer (I8)
100% 32073
42.2 IPS
 
Image Super-Resolution (F32)
100% 5121
182.9 IPS
 
Image Super-Resolution (F16)
100% 5339
190.7 IPS
 
Image Super-Resolution (I8)
100% 4915
175.5 IPS
 
Text Classification (F32)
100% 1152
1.66 KIPS
 
Text Classification (F16)
100% 763
1.10 KIPS
 
Text Classification (I8)
96% 763
1.10 KIPS
 
Machine Translation (F32)
100% 532
9.80 IPS
 
Machine Translation (F16)
100% 543
9.98 IPS
 
Machine Translation (I8)
99% 547
10.1 IPS
 

Compare

Set Baseline Geekbench 6 now available