Geekbench AI Score

4153
Single Precision Score
27428
Half Precision Score
30555
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

Upload Date September 03 2025 10:22 PM
Views 4

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 15.6.1 (Build 24G90)
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 3.48 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 64.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1410
262.2 IPS
 
Image Classification (HP)
100% 15008
2.79 KIPS
 
Image Classification (Q)
96% 18358
3.43 KIPS
 
Image Segmentation (SP)
100% 1651
26.8 IPS
 
Image Segmentation (HP)
100% 19937
323.2 IPS
 
Image Segmentation (Q)
99% 24737
401.0 IPS
 
Pose Estimation (SP)
100% 13058
15.2 IPS
 
Pose Estimation (HP)
100% 105806
123.5 IPS
 
Pose Estimation (Q)
95% 104244
122.2 IPS
 
Object Detection (SP)
100% 1682
133.4 IPS
 
Object Detection (HP)
99% 15787
1.26 KIPS
 
Object Detection (Q)
91% 17417
1.39 KIPS
 
Face Detection (SP)
100% 3568
42.4 IPS
 
Face Detection (HP)
100% 35433
421.0 IPS
 
Face Detection (Q)
100% 45566
541.4 IPS
 
Depth Estimation (SP)
100% 6139
47.3 IPS
 
Depth Estimation (HP)
99% 88726
683.6 IPS
 
Depth Estimation (Q)
85% 110625
864.5 IPS
 
Style Transfer (SP)
100% 25109
32.3 IPS
 
Style Transfer (HP)
100% 203692
261.8 IPS
 
Style Transfer (Q)
96% 189750
244.9 IPS
 
Image Super-Resolution (SP)
100% 5124
189.2 IPS
 
Image Super-Resolution (HP)
100% 41745
1.54 KIPS
 
Image Super-Resolution (Q)
99% 49646
1.83 KIPS
 
Text Classification (SP)
100% 2378
3.17 KIPS
 
Text Classification (HP)
100% 4286
5.72 KIPS
 
Text Classification (Q)
93% 4136
5.55 KIPS
 
Machine Translation (SP)
100% 4458
76.8 IPS
 
Machine Translation (HP)
100% 4208
72.5 IPS
 
Machine Translation (Q)
98% 4381
75.7 IPS
 

Compare

Set Baseline Geekbench 6 now available