Geekbench AI Score

11816
Single Precision Score
13293
Half Precision Score
12569
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

User remusn
Upload Date October 20 2025 01:45 PM
Views 6

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M3 Pro
System Information
Operating System macOS 26.0.1 (Build 25A362)
Model MacBook Pro (14-inch, Nov 2023)
Model IDMac15,6
Motherboard Mac15,6
CPU Information
Name Apple M3 Pro
Topology 1 Processor, 11 Cores
Identifier Apple M3 Pro
Base Frequency 4.05 GHz
Cluster 15 Cores
Cluster 26 Cores
Memory Information
Size 36.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 5610
1.04 KIPS
 
Image Classification (HP)
100% 6022
1.12 KIPS
 
Image Classification (Q)
96% 5445
1.02 KIPS
 
Image Segmentation (SP)
100% 9296
150.7 IPS
 
Image Segmentation (HP)
100% 9973
161.7 IPS
 
Image Segmentation (Q)
99% 9594
155.5 IPS
 
Pose Estimation (SP)
100% 33694
39.3 IPS
 
Pose Estimation (HP)
100% 37377
43.6 IPS
 
Pose Estimation (Q)
96% 36167
42.4 IPS
 
Object Detection (SP)
100% 5502
436.4 IPS
 
Object Detection (HP)
100% 5789
459.2 IPS
 
Object Detection (Q)
92% 5399
430.9 IPS
 
Face Detection (SP)
100% 16546
196.6 IPS
 
Face Detection (HP)
100% 20411
242.5 IPS
 
Face Detection (Q)
100% 16589
197.1 IPS
 
Depth Estimation (SP)
100% 22918
176.6 IPS
 
Depth Estimation (HP)
99% 25076
193.2 IPS
 
Depth Estimation (Q)
86% 22645
176.9 IPS
 
Style Transfer (SP)
100% 76185
97.9 IPS
 
Style Transfer (HP)
100% 86871
111.7 IPS
 
Style Transfer (Q)
96% 84296
108.8 IPS
 
Image Super-Resolution (SP)
100% 13663
504.5 IPS
 
Image Super-Resolution (HP)
100% 14686
542.3 IPS
 
Image Super-Resolution (Q)
99% 12514
462.1 IPS
 
Text Classification (SP)
100% 2973
3.97 KIPS
 
Text Classification (HP)
99% 5029
6.71 KIPS
 
Text Classification (Q)
93% 4888
6.56 KIPS
 
Machine Translation (SP)
100% 4678
80.6 IPS
 
Machine Translation (HP)
100% 4040
69.6 IPS
 
Machine Translation (Q)
98% 4981
86.1 IPS
 

Compare

Set Baseline Geekbench 6 now available