Geekbench AI Score

7156
Single Precision Score
7965
Half Precision Score
6992
Quantized Score
Geekbench AI 1.2.0 for macOS AArch64

Result Information

User oridwanbello
Upload Date March 12 2025 10:15 PM
Views 4

System Information

AI Information
Framework Core ML
Backend GPU
Device Apple M1 Pro
System Information
Operating System macOS 15.3.1 (Build 24D70)
Model MacBook Pro (14-inch, 2021)
Model IDMacBookPro18,3
Motherboard MacBookPro18,3
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 8 Cores
Identifier Apple M1 Pro
Base Frequency 3.22 GHz
Cluster 16 Cores
Cluster 22 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 3830
712.3 IPS
 
Image Classification (HP)
100% 3977
739.7 IPS
 
Image Classification (Q)
97% 3261
608.7 IPS
 
Image Segmentation (SP)
100% 5848
94.8 IPS
 
Image Segmentation (HP)
100% 5958
96.6 IPS
 
Image Segmentation (Q)
99% 5758
93.3 IPS
 
Pose Estimation (SP)
100% 29168
34.0 IPS
 
Pose Estimation (HP)
100% 31230
36.4 IPS
 
Pose Estimation (Q)
95% 28838
33.8 IPS
 
Object Detection (SP)
100% 3439
272.8 IPS
 
Object Detection (HP)
100% 3750
297.5 IPS
 
Object Detection (Q)
91% 3237
258.7 IPS
 
Face Detection (SP)
100% 12848
152.7 IPS
 
Face Detection (HP)
100% 13627
161.9 IPS
 
Face Detection (Q)
100% 9899
117.6 IPS
 
Depth Estimation (SP)
100% 17507
134.9 IPS
 
Depth Estimation (HP)
99% 17861
137.6 IPS
 
Depth Estimation (Q)
85% 14794
115.6 IPS
 
Style Transfer (SP)
100% 50039
64.3 IPS
 
Style Transfer (HP)
100% 58991
75.8 IPS
 
Style Transfer (Q)
96% 54425
70.2 IPS
 
Image Super-Resolution (SP)
100% 10525
388.7 IPS
 
Image Super-Resolution (HP)
100% 10831
399.9 IPS
 
Image Super-Resolution (Q)
99% 8563
316.2 IPS
 
Text Classification (SP)
100% 2328
3.11 KIPS
 
Text Classification (HP)
100% 3950
5.27 KIPS
 
Text Classification (Q)
93% 3955
5.31 KIPS
 
Machine Translation (SP)
100% 569
9.79 IPS
 
Machine Translation (HP)
100% 603
10.4 IPS
 
Machine Translation (Q)
98% 591
10.2 IPS
 

Compare

Set Baseline Geekbench 6 now available