Geekbench AI Score

4175
Single Precision Score
23620
Half Precision Score
25821
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

Upload Date September 18 2024 01:53 PM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 15.0 (Build 24A335)
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 3.67 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1395
259.4 IPS
 
Image Classification (HP)
100% 14026
2.61 KIPS
 
Image Classification (Q)
96% 16154
3.02 KIPS
 
Image Segmentation (SP)
100% 1698
27.5 IPS
 
Image Segmentation (HP)
100% 10224
165.7 IPS
 
Image Segmentation (Q)
99% 11403
184.8 IPS
 
Pose Estimation (SP)
100% 12997
15.2 IPS
 
Pose Estimation (HP)
100% 106403
124.2 IPS
 
Pose Estimation (Q)
95% 104379
122.3 IPS
 
Object Detection (SP)
100% 1691
134.1 IPS
 
Object Detection (HP)
99% 15577
1.24 KIPS
 
Object Detection (Q)
91% 17244
1.38 KIPS
 
Face Detection (SP)
100% 3690
43.8 IPS
 
Face Detection (HP)
100% 36209
430.2 IPS
 
Face Detection (Q)
100% 46956
557.9 IPS
 
Depth Estimation (SP)
100% 6276
48.3 IPS
 
Depth Estimation (HP)
99% 87507
674.2 IPS
 
Depth Estimation (Q)
85% 109180
853.2 IPS
 
Style Transfer (SP)
100% 25041
32.2 IPS
 
Style Transfer (HP)
100% 207475
266.7 IPS
 
Style Transfer (Q)
96% 190870
246.3 IPS
 
Image Super-Resolution (SP)
100% 5089
187.9 IPS
 
Image Super-Resolution (HP)
100% 41024
1.51 KIPS
 
Image Super-Resolution (Q)
99% 48753
1.80 KIPS
 
Text Classification (SP)
100% 2270
3.03 KIPS
 
Text Classification (HP)
100% 3956
5.28 KIPS
 
Text Classification (Q)
93% 3932
5.28 KIPS
 
Machine Translation (SP)
100% 4622
79.6 IPS
 
Machine Translation (HP)
100% 2132
36.7 IPS
 
Machine Translation (Q)
98% 2119
36.6 IPS
 

Compare

Set Baseline Geekbench 6 now available