Geekbench AI Score

3641
Single Precision Score
16452
Half Precision Score
16423
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

Upload Date April 13 2025 07:42 AM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1 Pro
System Information
Operating System macOS 15.4 (Build 24E248)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1339
249.0 IPS
 
Image Classification (HP)
100% 6886
1.28 KIPS
 
Image Classification (Q)
96% 6617
1.24 KIPS
 
Image Segmentation (SP)
100% 1540
25.0 IPS
 
Image Segmentation (HP)
100% 9690
157.1 IPS
 
Image Segmentation (Q)
99% 10451
169.4 IPS
 
Pose Estimation (SP)
100% 11104
13.0 IPS
 
Pose Estimation (HP)
100% 70323
82.1 IPS
 
Pose Estimation (Q)
95% 67317
78.9 IPS
 
Object Detection (SP)
100% 1550
123.0 IPS
 
Object Detection (HP)
99% 7994
635.9 IPS
 
Object Detection (Q)
91% 7511
600.2 IPS
 
Face Detection (SP)
100% 3135
37.3 IPS
 
Face Detection (HP)
100% 16091
191.2 IPS
 
Face Detection (Q)
100% 15129
179.8 IPS
 
Depth Estimation (SP)
100% 5774
44.5 IPS
 
Depth Estimation (HP)
99% 51587
397.4 IPS
 
Depth Estimation (Q)
85% 53410
417.4 IPS
 
Style Transfer (SP)
100% 21845
28.1 IPS
 
Style Transfer (HP)
100% 119664
153.8 IPS
 
Style Transfer (Q)
96% 116053
149.8 IPS
 
Image Super-Resolution (SP)
100% 4140
152.9 IPS
 
Image Super-Resolution (HP)
100% 26390
974.5 IPS
 
Image Super-Resolution (Q)
99% 28089
1.04 KIPS
 
Text Classification (SP)
100% 2298
3.07 KIPS
 
Text Classification (HP)
100% 4015
5.36 KIPS
 
Text Classification (Q)
93% 4013
5.39 KIPS
 
Machine Translation (SP)
100% 3068
52.9 IPS
 
Machine Translation (HP)
100% 3682
63.4 IPS
 
Machine Translation (Q)
98% 3863
66.8 IPS
 

Compare

Set Baseline Geekbench 6 now available