Geekbench AI Score

3458
Single Precision Score
26499
Half Precision Score
29482
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User EdwinValdezEXD
Upload Date June 28 2025 10:53 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 3.48 GHz
Cluster 14 Cores
Cluster 24 Cores
Memory Information
Size 8.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1370
254.7 IPS
 
Image Classification (HP)
100% 14328
2.66 KIPS
 
Image Classification (Q)
96% 15411
2.88 KIPS
 
Image Segmentation (SP)
100% 1488
24.1 IPS
 
Image Segmentation (HP)
100% 19889
322.4 IPS
 
Image Segmentation (Q)
99% 24284
393.7 IPS
 
Pose Estimation (SP)
100% 6817
7.95 IPS
 
Pose Estimation (HP)
100% 106197
123.9 IPS
 
Pose Estimation (Q)
95% 105993
124.2 IPS
 
Object Detection (SP)
100% 1543
122.4 IPS
 
Object Detection (HP)
99% 15936
1.27 KIPS
 
Object Detection (Q)
91% 17832
1.42 KIPS
 
Face Detection (SP)
100% 3082
36.6 IPS
 
Face Detection (HP)
100% 34084
405.0 IPS
 
Face Detection (Q)
100% 44301
526.4 IPS
 
Depth Estimation (SP)
100% 5511
42.5 IPS
 
Depth Estimation (HP)
99% 86817
668.9 IPS
 
Depth Estimation (Q)
85% 107957
843.6 IPS
 
Style Transfer (SP)
100% 18628
23.9 IPS
 
Style Transfer (HP)
100% 205209
263.8 IPS
 
Style Transfer (Q)
96% 192161
248.0 IPS
 
Image Super-Resolution (SP)
100% 3984
147.1 IPS
 
Image Super-Resolution (HP)
100% 39486
1.46 KIPS
 
Image Super-Resolution (Q)
99% 48257
1.78 KIPS
 
Text Classification (SP)
100% 2346
3.13 KIPS
 
Text Classification (HP)
99% 3634
4.85 KIPS
 
Text Classification (Q)
93% 3706
4.97 KIPS
 
Machine Translation (SP)
100% 3860
66.5 IPS
 
Machine Translation (HP)
100% 4063
70.0 IPS
 
Machine Translation (Q)
98% 4268
73.8 IPS
 

Compare

Set Baseline Geekbench 6 now available