Geekbench AI Score

4855
Single Precision Score
36639
Half Precision Score
51684
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

User dg7mza
Upload Date August 20 2025 02:51 PM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 15.5 (Build 24F74)
Model MacBook Pro (14-inch, 2024)
Model IDMac16,1
Motherboard Mac16,1
CPU Information
Name Apple M4
Topology 1 Processor, 10 Cores
Identifier Apple M4
Base Frequency 4.41 GHz
Cluster 14 Cores
Cluster 26 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2090
388.7 IPS
 
Image Classification (HP)
100% 17194
3.20 KIPS
 
Image Classification (Q)
97% 24349
4.54 KIPS
 
Image Segmentation (SP)
100% 2239
36.3 IPS
 
Image Segmentation (HP)
100% 21764
352.8 IPS
 
Image Segmentation (Q)
99% 29760
482.4 IPS
 
Pose Estimation (SP)
100% 9944
11.6 IPS
 
Pose Estimation (HP)
100% 122725
143.2 IPS
 
Pose Estimation (Q)
95% 231473
271.3 IPS
 
Object Detection (SP)
100% 2447
194.1 IPS
 
Object Detection (HP)
100% 19151
1.52 KIPS
 
Object Detection (Q)
91% 26211
2.09 KIPS
 
Face Detection (SP)
100% 4332
51.5 IPS
 
Face Detection (HP)
100% 43829
520.8 IPS
 
Face Detection (Q)
100% 64898
771.1 IPS
 
Depth Estimation (SP)
100% 8707
67.1 IPS
 
Depth Estimation (HP)
99% 99540
766.9 IPS
 
Depth Estimation (Q)
85% 168247
1.32 KIPS
 
Style Transfer (SP)
100% 21752
28.0 IPS
 
Style Transfer (HP)
100% 229486
295.0 IPS
 
Style Transfer (Q)
96% 297102
383.4 IPS
 
Image Super-Resolution (SP)
100% 6077
224.4 IPS
 
Image Super-Resolution (HP)
100% 50101
1.85 KIPS
 
Image Super-Resolution (Q)
99% 85016
3.14 KIPS
 
Text Classification (SP)
100% 2947
3.93 KIPS
 
Text Classification (HP)
100% 6010
8.02 KIPS
 
Text Classification (Q)
93% 6116
8.21 KIPS
 
Machine Translation (SP)
100% 4352
75.0 IPS
 
Machine Translation (HP)
100% 16443
283.2 IPS
 
Machine Translation (Q)
98% 18344
317.0 IPS
 

Compare

Set Baseline Geekbench 6 now available