Geekbench AI Score

4340
Single Precision Score
24168
Half Precision Score
26471
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

Upload Date September 17 2024 02:06 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 (14-inch, 2023)
Model IDMac14,5
Motherboard Mac14,5
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.47 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1461
271.8 IPS
 
Image Classification (HP)
100% 14983
2.79 KIPS
 
Image Classification (Q)
96% 17726
3.31 KIPS
 
Image Segmentation (SP)
100% 1807
29.3 IPS
 
Image Segmentation (HP)
100% 10310
167.1 IPS
 
Image Segmentation (Q)
99% 11517
186.7 IPS
 
Pose Estimation (SP)
100% 12944
15.1 IPS
 
Pose Estimation (HP)
100% 106866
124.7 IPS
 
Pose Estimation (Q)
95% 105354
123.5 IPS
 
Object Detection (SP)
100% 1809
143.5 IPS
 
Object Detection (HP)
99% 16687
1.33 KIPS
 
Object Detection (Q)
91% 18461
1.48 KIPS
 
Face Detection (SP)
100% 3813
45.3 IPS
 
Face Detection (HP)
100% 36613
435.0 IPS
 
Face Detection (Q)
100% 46699
554.9 IPS
 
Depth Estimation (SP)
100% 6257
48.2 IPS
 
Depth Estimation (HP)
99% 88918
685.1 IPS
 
Depth Estimation (Q)
85% 111514
871.4 IPS
 
Style Transfer (SP)
100% 26457
34.0 IPS
 
Style Transfer (HP)
100% 207413
266.6 IPS
 
Style Transfer (Q)
96% 193436
249.6 IPS
 
Image Super-Resolution (SP)
100% 5460
201.6 IPS
 
Image Super-Resolution (HP)
100% 43439
1.60 KIPS
 
Image Super-Resolution (Q)
99% 50760
1.87 KIPS
 
Text Classification (SP)
100% 2300
3.07 KIPS
 
Text Classification (HP)
100% 4038
5.39 KIPS
 
Text Classification (Q)
93% 4018
5.39 KIPS
 
Machine Translation (SP)
100% 4848
83.5 IPS
 
Machine Translation (HP)
100% 2084
35.9 IPS
 
Machine Translation (Q)
98% 2071
35.8 IPS
 

Compare

Set Baseline Geekbench 6 now available