Geekbench AI Score

10388
Single Precision Score
12093
Half Precision Score
10961
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User kirdol
Upload Date December 24 2024 11:02 PM
Views 2

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M3 Pro
System Information
Operating System macOS 15.2 (Build 24C101)
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
Memory Information
Size 18.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 5608
1.04 KIPS
 
Image Classification (HP)
100% 5938
1.10 KIPS
 
Image Classification (Q)
97% 4955
924.8 IPS
 
Image Segmentation (SP)
100% 6668
108.1 IPS
 
Image Segmentation (HP)
100% 8579
139.1 IPS
 
Image Segmentation (Q)
99% 8824
143.0 IPS
 
Pose Estimation (SP)
100% 34769
40.6 IPS
 
Pose Estimation (HP)
100% 36616
42.7 IPS
 
Pose Estimation (Q)
95% 34845
40.8 IPS
 
Object Detection (SP)
100% 5483
434.9 IPS
 
Object Detection (HP)
100% 5887
466.9 IPS
 
Object Detection (Q)
91% 4988
398.6 IPS
 
Face Detection (SP)
100% 15684
186.4 IPS
 
Face Detection (HP)
100% 19246
228.7 IPS
 
Face Detection (Q)
100% 14204
168.8 IPS
 
Depth Estimation (SP)
100% 22969
177.0 IPS
 
Depth Estimation (HP)
99% 24423
188.2 IPS
 
Depth Estimation (Q)
85% 21406
167.3 IPS
 
Style Transfer (SP)
100% 76193
97.9 IPS
 
Style Transfer (HP)
100% 86408
111.1 IPS
 
Style Transfer (Q)
96% 81425
105.1 IPS
 
Image Super-Resolution (SP)
100% 14448
533.5 IPS
 
Image Super-Resolution (HP)
100% 16098
594.4 IPS
 
Image Super-Resolution (Q)
99% 12325
455.1 IPS
 
Text Classification (SP)
100% 2723
3.64 KIPS
 
Text Classification (HP)
100% 4762
6.36 KIPS
 
Text Classification (Q)
93% 4779
6.41 KIPS
 
Machine Translation (SP)
100% 1901
32.8 IPS
 
Machine Translation (HP)
100% 1957
33.7 IPS
 
Machine Translation (Q)
98% 2259
39.0 IPS
 

Compare

Set Baseline Geekbench 6 now available