Geekbench AI Score

4850
Single Precision Score
36836
Half Precision Score
53112
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

User callearvid
Upload Date November 29 2025 03:50 PM
Views 13

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M4
System Information
Operating System macOS 15.7.2 (Build 24G325)
Model Mac mini (2024)
Model IDMac16,10
Motherboard Mac16,10
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% 2100
390.6 IPS
 
Image Classification (HP)
100% 17404
3.24 KIPS
 
Image Classification (Q)
97% 25440
4.75 KIPS
 
Image Segmentation (SP)
100% 2148
34.8 IPS
 
Image Segmentation (HP)
100% 21877
354.6 IPS
 
Image Segmentation (Q)
99% 30528
494.9 IPS
 
Pose Estimation (SP)
100% 9905
11.6 IPS
 
Pose Estimation (HP)
100% 123214
143.8 IPS
 
Pose Estimation (Q)
95% 232222
272.2 IPS
 
Object Detection (SP)
100% 2473
196.2 IPS
 
Object Detection (HP)
100% 18386
1.46 KIPS
 
Object Detection (Q)
91% 26005
2.08 KIPS
 
Face Detection (SP)
100% 4345
51.6 IPS
 
Face Detection (HP)
100% 44666
530.7 IPS
 
Face Detection (Q)
100% 63925
759.6 IPS
 
Depth Estimation (SP)
100% 8755
67.4 IPS
 
Depth Estimation (HP)
99% 99892
769.6 IPS
 
Depth Estimation (Q)
85% 169801
1.33 KIPS
 
Style Transfer (SP)
100% 21884
28.1 IPS
 
Style Transfer (HP)
100% 232263
298.6 IPS
 
Style Transfer (Q)
96% 298883
385.7 IPS
 
Image Super-Resolution (SP)
100% 6089
224.8 IPS
 
Image Super-Resolution (HP)
100% 49733
1.84 KIPS
 
Image Super-Resolution (Q)
99% 85411
3.15 KIPS
 
Text Classification (SP)
100% 2923
3.90 KIPS
 
Text Classification (HP)
100% 6192
8.27 KIPS
 
Text Classification (Q)
93% 7489
10.1 KIPS
 
Machine Translation (SP)
100% 4405
75.9 IPS
 
Machine Translation (HP)
100% 16711
287.8 IPS
 
Machine Translation (Q)
98% 18355
317.2 IPS
 

Compare

Set Baseline Geekbench 6 now available