Geekbench AI Score

4157
Single Precision Score
26912
Half Precision Score
30305
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User jwchess
Upload Date January 28 2025 02:24 PM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Pro
System Information
Operating System macOS 15.2 (Build 24C101)
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 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1407
261.6 IPS
 
Image Classification (HP)
100% 14915
2.77 KIPS
 
Image Classification (Q)
96% 18227
3.40 KIPS
 
Image Segmentation (SP)
100% 1699
27.5 IPS
 
Image Segmentation (HP)
100% 19770
320.5 IPS
 
Image Segmentation (Q)
99% 24723
400.8 IPS
 
Pose Estimation (SP)
100% 12419
14.5 IPS
 
Pose Estimation (HP)
100% 106844
124.7 IPS
 
Pose Estimation (Q)
95% 105396
123.5 IPS
 
Object Detection (SP)
100% 1687
133.8 IPS
 
Object Detection (HP)
99% 15527
1.24 KIPS
 
Object Detection (Q)
91% 17775
1.42 KIPS
 
Face Detection (SP)
100% 3712
44.1 IPS
 
Face Detection (HP)
100% 33703
400.5 IPS
 
Face Detection (Q)
100% 43832
520.8 IPS
 
Depth Estimation (SP)
100% 6353
48.9 IPS
 
Depth Estimation (HP)
99% 87805
676.5 IPS
 
Depth Estimation (Q)
85% 109978
859.4 IPS
 
Style Transfer (SP)
100% 25032
32.2 IPS
 
Style Transfer (HP)
100% 204356
262.7 IPS
 
Style Transfer (Q)
96% 197419
254.8 IPS
 
Image Super-Resolution (SP)
100% 5079
187.6 IPS
 
Image Super-Resolution (HP)
100% 44358
1.64 KIPS
 
Image Super-Resolution (Q)
99% 51185
1.89 KIPS
 
Text Classification (SP)
100% 2266
3.02 KIPS
 
Text Classification (HP)
100% 3988
5.32 KIPS
 
Text Classification (Q)
93% 3995
5.36 KIPS
 
Machine Translation (SP)
100% 4534
78.1 IPS
 
Machine Translation (HP)
100% 3809
65.6 IPS
 
Machine Translation (Q)
98% 3978
68.7 IPS
 

Compare

Set Baseline Geekbench 6 now available