Geekbench AI Score

3463
Single Precision Score
27541
Half Precision Score
30696
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User Aaronage
Upload Date November 14 2024 10:34 AM
Views 3

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2
System Information
Operating System macOS 15.1 (Build 24B83)
Model MacBook Pro (13-inch, 2022)
Model IDMac14,7
Motherboard Mac14,7
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier Apple M2
Base Frequency 3.47 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 24.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1393
259.1 IPS
 
Image Classification (HP)
100% 14284
2.66 KIPS
 
Image Classification (Q)
96% 15512
2.90 KIPS
 
Image Segmentation (SP)
100% 1524
24.7 IPS
 
Image Segmentation (HP)
100% 19124
310.0 IPS
 
Image Segmentation (Q)
99% 23575
382.2 IPS
 
Pose Estimation (SP)
100% 6879
8.03 IPS
 
Pose Estimation (HP)
100% 103865
121.2 IPS
 
Pose Estimation (Q)
95% 105657
123.8 IPS
 
Object Detection (SP)
100% 1574
124.8 IPS
 
Object Detection (HP)
99% 15400
1.23 KIPS
 
Object Detection (Q)
91% 17255
1.38 KIPS
 
Face Detection (SP)
100% 3121
37.1 IPS
 
Face Detection (HP)
100% 33596
399.2 IPS
 
Face Detection (Q)
100% 42500
505.0 IPS
 
Depth Estimation (SP)
100% 5675
43.7 IPS
 
Depth Estimation (HP)
99% 87284
672.5 IPS
 
Depth Estimation (Q)
85% 107228
837.9 IPS
 
Style Transfer (SP)
100% 18694
24.0 IPS
 
Style Transfer (HP)
100% 200017
257.1 IPS
 
Style Transfer (Q)
96% 189852
245.0 IPS
 
Image Super-Resolution (SP)
100% 4093
151.1 IPS
 
Image Super-Resolution (HP)
100% 39773
1.47 KIPS
 
Image Super-Resolution (Q)
99% 48443
1.79 KIPS
 
Text Classification (SP)
100% 2245
3.00 KIPS
 
Text Classification (HP)
100% 3802
5.07 KIPS
 
Text Classification (Q)
93% 3750
5.03 KIPS
 
Machine Translation (SP)
100% 3551
61.2 IPS
 
Machine Translation (HP)
100% 6479
111.6 IPS
 
Machine Translation (Q)
98% 7090
122.5 IPS
 

Compare

Set Baseline Geekbench 6 now available