Geekbench AI Score

2277
Single Precision Score
14985
Half Precision Score
15959
Quantized Score
Geekbench AI 1.0.0 for macOS AArch64

Result Information

User Leomotors
Upload Date August 19 2024 01:31 PM
Views 6

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 14.6.1 (Build 23G93)
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 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1113
207.1 IPS
 
Image Classification (HP)
100% 8008
1.49 KIPS
 
Image Classification (Q)
99% 8666
1.62 KIPS
 
Image Segmentation (SP)
100% 716
11.6 IPS
 
Image Segmentation (HP)
100% 5115
82.9 IPS
 
Image Segmentation (Q)
100% 5171
83.8 IPS
 
Pose Estimation (SP)
100% 11217
13.1 IPS
 
Pose Estimation (HP)
100% 92920
108.4 IPS
 
Pose Estimation (Q)
94% 87848
103.0 IPS
 
Object Detection (SP)
100% 1243
98.6 IPS
 
Object Detection (HP)
99% 9363
744.8 IPS
 
Object Detection (Q)
93% 10044
801.4 IPS
 
Face Detection (SP)
100% 2018
24.0 IPS
 
Face Detection (HP)
100% 11618
138.1 IPS
 
Face Detection (Q)
100% 13897
165.1 IPS
 
Depth Estimation (SP)
100% 3811
29.4 IPS
 
Depth Estimation (HP)
99% 56243
433.3 IPS
 
Depth Estimation (Q)
97% 61199
473.2 IPS
 
Style Transfer (SP)
100% 13055
16.8 IPS
 
Style Transfer (HP)
100% 147130
189.1 IPS
 
Style Transfer (Q)
100% 146497
188.3 IPS
 
Image Super-Resolution (SP)
100% 2276
84.0 IPS
 
Image Super-Resolution (HP)
100% 20877
770.9 IPS
 
Image Super-Resolution (Q)
98% 28019
1.04 KIPS
 
Text Classification (SP)
100% 760
1.01 KIPS
 
Text Classification (HP)
100% 3991
5.33 KIPS
 
Text Classification (Q)
93% 3914
5.25 KIPS
 
Machine Translation (SP)
100% 1943
33.5 IPS
 
Machine Translation (HP)
100% 2000
34.4 IPS
 
Machine Translation (Q)
98% 1984
34.3 IPS
 

Compare

Set Baseline Geekbench 6 now available