Geekbench AI Score

4193
Single Precision Score
26878
Half Precision Score
30115
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

Upload Date January 04 2025 04:48 PM
Views 1

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Pro
System Information
Operating System macOS 15.2 (Build 24C101)
Model MacBook Pro (16-inch, 2023)
Model IDMac14,10
Motherboard Mac14,10
CPU Information
Name Apple M2 Pro
Topology 1 Processor, 12 Cores
Identifier Apple M2 Pro
Base Frequency 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1416
263.2 IPS
 
Image Classification (HP)
100% 14620
2.72 KIPS
 
Image Classification (Q)
96% 17241
3.22 KIPS
 
Image Segmentation (SP)
100% 1720
27.9 IPS
 
Image Segmentation (HP)
100% 19401
314.5 IPS
 
Image Segmentation (Q)
99% 24681
400.1 IPS
 
Pose Estimation (SP)
100% 12797
14.9 IPS
 
Pose Estimation (HP)
100% 107343
125.3 IPS
 
Pose Estimation (Q)
95% 104390
122.4 IPS
 
Object Detection (SP)
100% 1694
134.4 IPS
 
Object Detection (HP)
99% 15097
1.20 KIPS
 
Object Detection (Q)
91% 16936
1.35 KIPS
 
Face Detection (SP)
100% 3719
44.2 IPS
 
Face Detection (HP)
100% 35395
420.6 IPS
 
Face Detection (Q)
100% 45190
537.0 IPS
 
Depth Estimation (SP)
100% 6513
50.2 IPS
 
Depth Estimation (HP)
99% 87497
674.1 IPS
 
Depth Estimation (Q)
85% 110756
865.5 IPS
 
Style Transfer (SP)
100% 24419
31.4 IPS
 
Style Transfer (HP)
100% 203164
261.2 IPS
 
Style Transfer (Q)
96% 192140
247.9 IPS
 
Image Super-Resolution (SP)
100% 5171
190.9 IPS
 
Image Super-Resolution (HP)
100% 42001
1.55 KIPS
 
Image Super-Resolution (Q)
99% 49430
1.83 KIPS
 
Text Classification (SP)
100% 2285
3.05 KIPS
 
Text Classification (HP)
100% 4017
5.36 KIPS
 
Text Classification (Q)
93% 3992
5.36 KIPS
 
Machine Translation (SP)
100% 4558
78.5 IPS
 
Machine Translation (HP)
100% 4034
69.5 IPS
 
Machine Translation (Q)
98% 4299
74.3 IPS
 

Compare

Set Baseline Geekbench 6 now available