Geekbench AI Score

2349
Single Precision Score
14903
Half Precision Score
16800
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

User stanleyruppert
Upload Date September 11 2024 02:52 AM
Views 4

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 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 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1127
209.5 IPS
 
Image Classification (HP)
100% 7784
1.45 KIPS
 
Image Classification (Q)
96% 8555
1.60 KIPS
 
Image Segmentation (SP)
100% 737
11.9 IPS
 
Image Segmentation (HP)
100% 5147
83.4 IPS
 
Image Segmentation (Q)
99% 8688
140.8 IPS
 
Pose Estimation (SP)
100% 11184
13.1 IPS
 
Pose Estimation (HP)
100% 92765
108.2 IPS
 
Pose Estimation (Q)
95% 87480
102.5 IPS
 
Object Detection (SP)
100% 1207
95.8 IPS
 
Object Detection (HP)
99% 9358
744.4 IPS
 
Object Detection (Q)
93% 10101
806.0 IPS
 
Face Detection (SP)
100% 2146
25.5 IPS
 
Face Detection (HP)
100% 11865
141.0 IPS
 
Face Detection (Q)
100% 13680
162.5 IPS
 
Depth Estimation (SP)
100% 3760
29.0 IPS
 
Depth Estimation (HP)
99% 56204
433.0 IPS
 
Depth Estimation (Q)
85% 67783
529.7 IPS
 
Style Transfer (SP)
100% 13244
17.0 IPS
 
Style Transfer (HP)
100% 146325
188.1 IPS
 
Style Transfer (Q)
95% 134440
173.6 IPS
 
Image Super-Resolution (SP)
100% 2451
90.5 IPS
 
Image Super-Resolution (HP)
100% 20598
760.6 IPS
 
Image Super-Resolution (Q)
99% 28258
1.04 KIPS
 
Text Classification (SP)
100% 912
1.22 KIPS
 
Text Classification (HP)
100% 3808
5.08 KIPS
 
Text Classification (Q)
93% 3809
5.11 KIPS
 
Machine Translation (SP)
100% 1917
33.0 IPS
 
Machine Translation (HP)
100% 2031
35.0 IPS
 
Machine Translation (Q)
98% 2033
35.1 IPS
 

Compare

Set Baseline Geekbench 6 now available