Geekbench ML Score

3444
Core ML CPU Inference Score
Geekbench ML 0.6.0 for macOS AArch64

Result Information

Upload Date August 15 2024 05:30 PM
Views 1

System Information

System Information
Operating System macOS 14.5 (Build 23F79)
Model MacBook Pro (14-inch, 2023)
Model IDMac14,9
Motherboard Mac14,9
CPU Information
Name Apple M2 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M2 Pro
Base Frequency 3.48 GHz
Cluster 16 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 16.00 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1450
271.4 IPS
 
Image Classification (F16)
100% 1812
339.2 IPS
 
Image Classification (I8)
99% 1799
336.7 IPS
 
Image Segmentation (F32)
100% 881
14.7 IPS
 
Image Segmentation (F16)
100% 879
14.7 IPS
 
Image Segmentation (I8)
100% 872
14.6 IPS
 
Pose Estimation (F32)
100% 5951
7.21 IPS
 
Pose Estimation (F16)
100% 14163
17.2 IPS
 
Pose Estimation (I8)
100% 14214
17.2 IPS
 
Object Detection (F32)
100% 1456
108.7 IPS
 
Object Detection (F16)
100% 1961
146.4 IPS
 
Object Detection (I8)
97% 1467
109.5 IPS
 
Face Detection (F32)
100% 2862
34.0 IPS
 
Face Detection (F16)
97% 4228
50.3 IPS
 
Face Detection (I8)
97% 4286
51.0 IPS
 
Depth Estimation (F32)
100% 5448
42.3 IPS
 
Depth Estimation (F16)
100% 8475
65.7 IPS
 
Depth Estimation (I8)
99% 8293
64.3 IPS
 
Style Transfer (F32)
100% 16692
22.0 IPS
 
Style Transfer (F16)
100% 25964
34.2 IPS
 
Style Transfer (I8)
100% 26022
34.2 IPS
 
Image Super-Resolution (F32)
100% 3934
140.5 IPS
 
Image Super-Resolution (F16)
100% 4874
174.1 IPS
 
Image Super-Resolution (I8)
100% 4832
172.6 IPS
 
Text Classification (F32)
100% 2065
2.97 KIPS
 
Text Classification (F16)
100% 3188
4.58 KIPS
 
Text Classification (I8)
96% 3187
4.58 KIPS
 
Machine Translation (F32)
100% 1115
20.5 IPS
 
Machine Translation (F16)
100% 1542
28.4 IPS
 
Machine Translation (I8)
99% 1085
20.0 IPS
 

Compare

Set Baseline Geekbench 6 now available