Geekbench AI Score

15011
Single Precision Score
16786
Half Precision Score
15731
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

User Tolek
Upload Date July 22 2025 10:45 AM
Views 14

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M4 Pro
System Information
Operating System macOS 15.5 (Build 24F74)
Model MacBook Pro (14-inch, 2024)
Model IDMac16,8
Motherboard Mac16,8
CPU Information
Name Apple M4 Pro
Topology 1 Processor, 12 Cores
Identifier Apple M4 Pro
Base Frequency 4.51 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 24.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 7074
1.32 KIPS
 
Image Classification (HP)
100% 7507
1.40 KIPS
 
Image Classification (Q)
96% 6911
1.29 KIPS
 
Image Segmentation (SP)
100% 12419
201.3 IPS
 
Image Segmentation (HP)
100% 12873
208.7 IPS
 
Image Segmentation (Q)
99% 12230
198.3 IPS
 
Pose Estimation (SP)
100% 46091
53.8 IPS
 
Pose Estimation (HP)
100% 47523
55.5 IPS
 
Pose Estimation (Q)
96% 46738
54.7 IPS
 
Object Detection (SP)
100% 6545
519.2 IPS
 
Object Detection (HP)
100% 7345
582.6 IPS
 
Object Detection (Q)
92% 6577
525.0 IPS
 
Face Detection (SP)
100% 23332
277.2 IPS
 
Face Detection (HP)
100% 26055
309.6 IPS
 
Face Detection (Q)
100% 21827
259.3 IPS
 
Depth Estimation (SP)
100% 31342
241.5 IPS
 
Depth Estimation (HP)
99% 31948
246.1 IPS
 
Depth Estimation (Q)
86% 29449
230.0 IPS
 
Style Transfer (SP)
100% 105073
135.1 IPS
 
Style Transfer (HP)
100% 110526
142.1 IPS
 
Style Transfer (Q)
96% 109039
140.7 IPS
 
Image Super-Resolution (SP)
100% 17339
640.3 IPS
 
Image Super-Resolution (HP)
100% 17196
635.0 IPS
 
Image Super-Resolution (Q)
99% 15788
583.0 IPS
 
Text Classification (SP)
100% 2917
3.89 KIPS
 
Text Classification (HP)
100% 5370
7.17 KIPS
 
Text Classification (Q)
93% 5309
7.13 KIPS
 
Machine Translation (SP)
100% 5643
97.2 IPS
 
Machine Translation (HP)
100% 6199
106.8 IPS
 
Machine Translation (Q)
98% 6082
105.1 IPS
 

Compare

Set Baseline Geekbench 6 now available