Geekbench AI Score

3447
Single Precision Score
26312
Half Precision Score
29017
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User EdwinValdezEXD
Upload Date June 28 2025 10:49 PM
Views 5

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2
System Information
Operating System macOS 16.0 (Build 25A5295e)
Model MacBook Pro (13-inch, 2022)
Model IDMac14,7
Motherboard Mac14,7
CPU Information
Name Apple M2
Topology 1 Processor, 8 Cores
Identifier Apple M2
Base Frequency 3.29 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1369
254.5 IPS
 
Image Classification (HP)
100% 14164
2.63 KIPS
 
Image Classification (Q)
96% 14464
2.70 KIPS
 
Image Segmentation (SP)
100% 1471
23.9 IPS
 
Image Segmentation (HP)
100% 19701
319.4 IPS
 
Image Segmentation (Q)
99% 23166
375.5 IPS
 
Pose Estimation (SP)
100% 6824
7.96 IPS
 
Pose Estimation (HP)
100% 104966
122.5 IPS
 
Pose Estimation (Q)
95% 105425
123.6 IPS
 
Object Detection (SP)
100% 1528
121.2 IPS
 
Object Detection (HP)
99% 15360
1.22 KIPS
 
Object Detection (Q)
91% 17129
1.37 KIPS
 
Face Detection (SP)
100% 3088
36.7 IPS
 
Face Detection (HP)
100% 34259
407.1 IPS
 
Face Detection (Q)
100% 44174
524.9 IPS
 
Depth Estimation (SP)
100% 5487
42.3 IPS
 
Depth Estimation (HP)
99% 86709
668.0 IPS
 
Depth Estimation (Q)
85% 110038
859.9 IPS
 
Style Transfer (SP)
100% 18577
23.9 IPS
 
Style Transfer (HP)
100% 204693
263.1 IPS
 
Style Transfer (Q)
96% 195737
252.6 IPS
 
Image Super-Resolution (SP)
100% 3948
145.8 IPS
 
Image Super-Resolution (HP)
100% 39105
1.44 KIPS
 
Image Super-Resolution (Q)
99% 46706
1.72 KIPS
 
Text Classification (SP)
100% 2354
3.14 KIPS
 
Text Classification (HP)
99% 3732
4.98 KIPS
 
Text Classification (Q)
93% 3729
5.00 KIPS
 
Machine Translation (SP)
100% 3862
66.5 IPS
 
Machine Translation (HP)
100% 3985
68.6 IPS
 
Machine Translation (Q)
98% 4221
73.0 IPS
 

Compare

Set Baseline Geekbench 6 now available