Geekbench ML Score

9890
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

User mrdbourke
Upload Date December 14 2023 01:34 AM
Views 48

System Information

System Information
Operating System macOS 14.2 (Build 23C64)
Model MacBook Pro (14-inch, Nov 2023)
Model IDMac15,6
Motherboard Mac15,6
CPU Information
Name Apple M3 Pro
Topology 1 Processor, 11 Cores
Identifier Apple M3 Pro
Base Frequency 4.05 GHz
Cluster 15 Cores
Cluster 26 Cores
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 18.00 GB
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4804
899.0 IPS
 
Image Classification (F16)
100% 7295
1.37 KIPS
 
Image Classification (I8)
99% 7988
1.49 KIPS
 
Image Segmentation (F32)
100% 1850
30.9 IPS
 
Image Segmentation (F16)
100% 2030
33.9 IPS
 
Image Segmentation (I8)
100% 2071
34.6 IPS
 
Pose Estimation (F32)
100% 33044
40.0 IPS
 
Pose Estimation (F16)
100% 95981
116.2 IPS
 
Pose Estimation (I8)
100% 95988
116.2 IPS
 
Object Detection (F32)
100% 3442
257.0 IPS
 
Object Detection (F16)
100% 5694
425.1 IPS
 
Object Detection (I8)
97% 3838
286.5 IPS
 
Face Detection (F32)
100% 14589
173.5 IPS
 
Face Detection (F16)
97% 15193
180.7 IPS
 
Face Detection (I8)
96% 13264
157.7 IPS
 
Depth Estimation (F32)
100% 22354
173.4 IPS
 
Depth Estimation (F16)
100% 43910
340.5 IPS
 
Depth Estimation (I8)
37% 47031
364.7 IPS
 
Style Transfer (F32)
100% 73890
97.2 IPS
 
Style Transfer (F16)
100% 147092
193.5 IPS
 
Style Transfer (I8)
100% 147643
194.2 IPS
 
Image Super-Resolution (F32)
100% 9907
353.8 IPS
 
Image Super-Resolution (F16)
100% 17860
637.9 IPS
 
Image Super-Resolution (I8)
100% 19904
710.8 IPS
 
Text Classification (F32)
100% 417
599.4 IPS
 
Text Classification (F16)
100% 3890
5.59 KIPS
 
Text Classification (I8)
96% 4144
5.96 KIPS
 
Machine Translation (F32)
100% 1026
18.9 IPS
 
Machine Translation (F16)
100% 2900
53.4 IPS
 
Machine Translation (I8)
99% 941
17.3 IPS
 

Compare

Set Baseline Geekbench 6 now available