Geekbench AI Score

3610
Single Precision Score
15171
Half Precision Score
15635
Quantized Score
Geekbench AI 1.6.0 for macOS AArch64

Result Information

Upload Date January 17 2026 10:30 PM
Views 3

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1 Pro
System Information
Operating System macOS 26.2 (Build 25C56)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1304
242.5 IPS
 
Image Classification (HP)
100% 5900
1.10 KIPS
 
Image Classification (Q)
96% 5723
1.07 KIPS
 
Image Segmentation (SP)
100% 1512
24.5 IPS
 
Image Segmentation (HP)
100% 9216
149.4 IPS
 
Image Segmentation (Q)
99% 9964
161.5 IPS
 
Pose Estimation (SP)
100% 10562
12.3 IPS
 
Pose Estimation (HP)
100% 66205
77.3 IPS
 
Pose Estimation (Q)
95% 62604
73.4 IPS
 
Object Detection (SP)
100% 1503
119.2 IPS
 
Object Detection (HP)
99% 6875
546.9 IPS
 
Object Detection (Q)
91% 6520
521.0 IPS
 
Face Detection (SP)
100% 3271
38.9 IPS
 
Face Detection (HP)
100% 12941
153.8 IPS
 
Face Detection (Q)
100% 12226
145.3 IPS
 
Depth Estimation (SP)
100% 5642
43.5 IPS
 
Depth Estimation (HP)
99% 44709
344.5 IPS
 
Depth Estimation (Q)
85% 46727
365.2 IPS
 
Style Transfer (SP)
100% 22153
28.5 IPS
 
Style Transfer (HP)
100% 114578
147.3 IPS
 
Style Transfer (Q)
96% 108740
140.3 IPS
 
Image Super-Resolution (SP)
100% 4116
152.0 IPS
 
Image Super-Resolution (HP)
100% 23917
883.1 IPS
 
Image Super-Resolution (Q)
99% 25112
927.3 IPS
 
Text Classification (SP)
100% 2366
3.16 KIPS
 
Text Classification (HP)
99% 4086
5.45 KIPS
 
Text Classification (Q)
93% 4130
5.54 KIPS
 
Machine Translation (SP)
100% 3023
52.1 IPS
 
Machine Translation (HP)
100% 4030
69.4 IPS
 
Machine Translation (Q)
98% 5823
100.6 IPS
 

Compare

Set Baseline Geekbench 6 now available