Geekbench AI Score

13747
Single Precision Score
14794
Half Precision Score
13229
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User jonvharrison
Upload Date December 08 2024 04:49 PM
Views 6

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M2 Max
System Information
Operating System macOS 15.1.1 (Build 24B91)
Model Mac Studio (2023)
Model IDMac14,13
Motherboard Mac14,13
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 6463
1.20 KIPS
 
Image Classification (HP)
100% 6511
1.21 KIPS
 
Image Classification (Q)
97% 5703
1.06 KIPS
 
Image Segmentation (SP)
100% 11990
194.4 IPS
 
Image Segmentation (HP)
100% 11767
190.7 IPS
 
Image Segmentation (Q)
99% 11683
189.4 IPS
 
Pose Estimation (SP)
100% 62027
72.4 IPS
 
Pose Estimation (HP)
100% 65053
75.9 IPS
 
Pose Estimation (Q)
95% 60063
70.4 IPS
 
Object Detection (SP)
100% 6087
482.8 IPS
 
Object Detection (HP)
100% 6303
499.9 IPS
 
Object Detection (Q)
91% 5523
441.3 IPS
 
Face Detection (SP)
100% 25293
300.5 IPS
 
Face Detection (HP)
100% 24730
293.8 IPS
 
Face Detection (Q)
100% 19109
227.1 IPS
 
Depth Estimation (SP)
100% 29251
225.4 IPS
 
Depth Estimation (HP)
99% 29845
229.9 IPS
 
Depth Estimation (Q)
85% 25014
195.5 IPS
 
Style Transfer (SP)
100% 114652
147.4 IPS
 
Style Transfer (HP)
100% 128396
165.1 IPS
 
Style Transfer (Q)
96% 119676
154.4 IPS
 
Image Super-Resolution (SP)
100% 19985
737.9 IPS
 
Image Super-Resolution (HP)
100% 20831
769.2 IPS
 
Image Super-Resolution (Q)
99% 16932
625.2 IPS
 
Text Classification (SP)
100% 2280
3.04 KIPS
 
Text Classification (HP)
100% 3997
5.33 KIPS
 
Text Classification (Q)
93% 3983
5.35 KIPS
 
Machine Translation (SP)
100% 2133
36.7 IPS
 
Machine Translation (HP)
100% 2026
34.9 IPS
 
Machine Translation (Q)
98% 1926
33.3 IPS
 

Compare

Set Baseline Geekbench 6 now available