Geekbench AI Score

14365
Single Precision Score
15760
Half Precision Score
14046
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User kngo
Upload Date January 25 2025 12:42 AM
Views 3

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M2 Max
System Information
Operating System macOS 15.2 (Build 24C101)
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 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7107
1.32 KIPS
 
Image Classification (HP)
100% 6868
1.28 KIPS
 
Image Classification (Q)
97% 6033
1.13 KIPS
 
Image Segmentation (SP)
100% 12493
202.5 IPS
 
Image Segmentation (HP)
100% 12382
200.7 IPS
 
Image Segmentation (Q)
99% 12022
194.9 IPS
 
Pose Estimation (SP)
100% 82629
96.4 IPS
 
Pose Estimation (HP)
100% 86608
101.1 IPS
 
Pose Estimation (Q)
95% 81437
95.5 IPS
 
Object Detection (SP)
100% 6435
510.5 IPS
 
Object Detection (HP)
100% 6916
548.6 IPS
 
Object Detection (Q)
91% 5977
477.6 IPS
 
Face Detection (SP)
100% 28172
334.7 IPS
 
Face Detection (HP)
100% 28964
344.2 IPS
 
Face Detection (Q)
100% 21404
254.3 IPS
 
Depth Estimation (SP)
100% 33600
258.9 IPS
 
Depth Estimation (HP)
99% 34688
267.2 IPS
 
Depth Estimation (Q)
85% 29523
230.7 IPS
 
Style Transfer (SP)
100% 135262
173.9 IPS
 
Style Transfer (HP)
100% 152710
196.3 IPS
 
Style Transfer (Q)
96% 142800
184.3 IPS
 
Image Super-Resolution (SP)
100% 20767
766.8 IPS
 
Image Super-Resolution (HP)
100% 20762
766.7 IPS
 
Image Super-Resolution (Q)
99% 17076
630.6 IPS
 
Text Classification (SP)
100% 2275
3.04 KIPS
 
Text Classification (HP)
100% 3975
5.31 KIPS
 
Text Classification (Q)
93% 3948
5.30 KIPS
 
Machine Translation (SP)
100% 1311
22.6 IPS
 
Machine Translation (HP)
100% 1466
25.3 IPS
 
Machine Translation (Q)
98% 1392
24.1 IPS
 

Compare

Set Baseline Geekbench 6 now available