Geekbench AI Score

13934
Single Precision Score
15423
Half Precision Score
14160
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User sse
Upload Date November 29 2024 05:04 AM
Views 3

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M2 Max
System Information
Operating System macOS 15.1.1 (Build 24B91)
Model MacBook Pro (16-inch, 2023)
Model IDMac14,6
Motherboard Mac14,6
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.62 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7185
1.34 KIPS
 
Image Classification (HP)
100% 7328
1.36 KIPS
 
Image Classification (Q)
97% 6344
1.18 KIPS
 
Image Segmentation (SP)
100% 12706
206.0 IPS
 
Image Segmentation (HP)
100% 12835
208.1 IPS
 
Image Segmentation (Q)
99% 12766
206.9 IPS
 
Pose Estimation (SP)
100% 84665
98.8 IPS
 
Pose Estimation (HP)
100% 88375
103.1 IPS
 
Pose Estimation (Q)
95% 83187
97.5 IPS
 
Object Detection (SP)
100% 5728
454.4 IPS
 
Object Detection (HP)
100% 6967
552.7 IPS
 
Object Detection (Q)
91% 6204
495.7 IPS
 
Face Detection (SP)
100% 28811
342.3 IPS
 
Face Detection (HP)
100% 29846
354.6 IPS
 
Face Detection (Q)
100% 22056
262.1 IPS
 
Depth Estimation (SP)
100% 34740
267.6 IPS
 
Depth Estimation (HP)
99% 35768
275.6 IPS
 
Depth Estimation (Q)
85% 30088
235.2 IPS
 
Style Transfer (SP)
100% 137337
176.5 IPS
 
Style Transfer (HP)
100% 155940
200.5 IPS
 
Style Transfer (Q)
96% 145570
187.9 IPS
 
Image Super-Resolution (SP)
100% 21109
779.4 IPS
 
Image Super-Resolution (HP)
100% 21625
798.5 IPS
 
Image Super-Resolution (Q)
99% 17825
658.2 IPS
 
Text Classification (SP)
100% 2278
3.04 KIPS
 
Text Classification (HP)
100% 4007
5.35 KIPS
 
Text Classification (Q)
93% 3975
5.34 KIPS
 
Machine Translation (SP)
100% 943
16.2 IPS
 
Machine Translation (HP)
100% 912
15.7 IPS
 
Machine Translation (Q)
98% 1133
19.6 IPS
 

Compare

Set Baseline Geekbench 6 now available