Geekbench AI Score

4339
Single Precision Score
27851
Half Precision Score
31359
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User T1nue
Upload Date November 09 2024 08:48 AM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Pro
System Information
Operating System macOS 15.1 (Build 24B83)
Model Mac mini (2023)
Model IDMac14,12
Motherboard Mac14,12
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
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1475
274.2 IPS
 
Image Classification (HP)
100% 14758
2.74 KIPS
 
Image Classification (Q)
96% 17585
3.28 KIPS
 
Image Segmentation (SP)
100% 1816
29.4 IPS
 
Image Segmentation (HP)
100% 19264
312.3 IPS
 
Image Segmentation (Q)
99% 23185
375.9 IPS
 
Pose Estimation (SP)
100% 12770
14.9 IPS
 
Pose Estimation (HP)
100% 106687
124.5 IPS
 
Pose Estimation (Q)
95% 104342
122.3 IPS
 
Object Detection (SP)
100% 1803
143.0 IPS
 
Object Detection (HP)
99% 15838
1.26 KIPS
 
Object Detection (Q)
91% 17652
1.41 KIPS
 
Face Detection (SP)
100% 3825
45.5 IPS
 
Face Detection (HP)
100% 36650
435.5 IPS
 
Face Detection (Q)
100% 47264
561.6 IPS
 
Depth Estimation (SP)
100% 6502
50.1 IPS
 
Depth Estimation (HP)
99% 87895
677.2 IPS
 
Depth Estimation (Q)
85% 109609
856.5 IPS
 
Style Transfer (SP)
100% 26305
33.8 IPS
 
Style Transfer (HP)
100% 204703
263.1 IPS
 
Style Transfer (Q)
96% 192183
248.0 IPS
 
Image Super-Resolution (SP)
100% 5444
201.0 IPS
 
Image Super-Resolution (HP)
100% 42124
1.56 KIPS
 
Image Super-Resolution (Q)
99% 51873
1.92 KIPS
 
Text Classification (SP)
100% 2298
3.07 KIPS
 
Text Classification (HP)
100% 4032
5.38 KIPS
 
Text Classification (Q)
93% 4010
5.38 KIPS
 
Machine Translation (SP)
100% 4687
80.7 IPS
 
Machine Translation (HP)
100% 5220
89.9 IPS
 
Machine Translation (Q)
98% 5915
102.2 IPS
 

Compare

Set Baseline Geekbench 6 now available