Geekbench AI Score

15149
Single Precision Score
16994
Half Precision Score
16216
Quantized Score
Geekbench AI 1.3.0 for macOS AArch64

Result Information

User BennyDaBall
Upload Date November 22 2025 02:56 PM
Views 9

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Pro
System Information
Operating System macOS 26.2 (Build 25C5048a)
Model Mac mini (2024)
Model IDMac16,11
Motherboard Mac16,11
CPU Information
Name Apple M4 Pro
Topology 1 Processor, 14 Cores
Identifier Apple M4 Pro
Base Frequency 4.51 GHz
Cluster 110 Cores
Cluster 24 Cores
Memory Information
Size 48.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7469
1.39 KIPS
 
Image Classification (HP)
100% 7932
1.48 KIPS
 
Image Classification (Q)
96% 7234
1.35 KIPS
 
Image Segmentation (SP)
100% 14111
228.8 IPS
 
Image Segmentation (HP)
100% 14958
242.5 IPS
 
Image Segmentation (Q)
99% 14405
233.5 IPS
 
Pose Estimation (SP)
100% 54431
63.5 IPS
 
Pose Estimation (HP)
100% 59409
69.3 IPS
 
Pose Estimation (Q)
96% 57039
66.8 IPS
 
Object Detection (SP)
100% 6692
530.8 IPS
 
Object Detection (HP)
100% 7077
561.3 IPS
 
Object Detection (Q)
92% 6864
547.9 IPS
 
Face Detection (SP)
100% 25577
303.9 IPS
 
Face Detection (HP)
100% 28780
342.0 IPS
 
Face Detection (Q)
100% 24120
286.6 IPS
 
Depth Estimation (SP)
100% 32952
253.9 IPS
 
Depth Estimation (HP)
99% 34700
267.3 IPS
 
Depth Estimation (Q)
86% 31880
249.0 IPS
 
Style Transfer (SP)
100% 119179
153.2 IPS
 
Style Transfer (HP)
100% 133173
171.2 IPS
 
Style Transfer (Q)
96% 130926
169.0 IPS
 
Image Super-Resolution (SP)
100% 20391
752.9 IPS
 
Image Super-Resolution (HP)
100% 20378
752.5 IPS
 
Image Super-Resolution (Q)
99% 17926
661.9 IPS
 
Text Classification (SP)
100% 3093
4.13 KIPS
 
Text Classification (HP)
99% 5318
7.10 KIPS
 
Text Classification (Q)
93% 5309
7.13 KIPS
 
Machine Translation (SP)
100% 2618
45.1 IPS
 
Machine Translation (HP)
100% 2795
48.1 IPS
 
Machine Translation (Q)
98% 3218
55.6 IPS
 

Compare

Set Baseline Geekbench 6 now available