Geekbench AI Score

3717
Single Precision Score
16287
Half Precision Score
16117
Quantized Score
Geekbench AI 1.4.0 for macOS AArch64

Result Information

Upload Date August 06 2025 05:54 PM
Views 6

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1 Pro
System Information
Operating System macOS 15.1 (Build 24B83)
Model MacBook Pro (16-inch, 2021)
Model IDMacBookPro18,1
Motherboard MacBookPro18,1
CPU Information
Name Apple M1 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M1 Pro
Base Frequency 3.19 GHz
Cluster 18 Cores
Cluster 22 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1331
247.5 IPS
 
Image Classification (HP)
100% 6805
1.27 KIPS
 
Image Classification (Q)
96% 6478
1.21 KIPS
 
Image Segmentation (SP)
100% 1603
26.0 IPS
 
Image Segmentation (HP)
100% 9497
154.0 IPS
 
Image Segmentation (Q)
99% 10058
163.1 IPS
 
Pose Estimation (SP)
100% 11097
12.9 IPS
 
Pose Estimation (HP)
100% 71509
83.4 IPS
 
Pose Estimation (Q)
95% 67775
79.4 IPS
 
Object Detection (SP)
100% 1578
125.2 IPS
 
Object Detection (HP)
99% 7772
618.3 IPS
 
Object Detection (Q)
91% 7297
583.1 IPS
 
Face Detection (SP)
100% 3201
38.0 IPS
 
Face Detection (HP)
100% 15563
184.9 IPS
 
Face Detection (Q)
100% 14196
168.7 IPS
 
Depth Estimation (SP)
100% 5754
44.3 IPS
 
Depth Estimation (HP)
99% 51176
394.3 IPS
 
Depth Estimation (Q)
85% 53584
418.7 IPS
 
Style Transfer (SP)
100% 22592
29.0 IPS
 
Style Transfer (HP)
100% 119928
154.2 IPS
 
Style Transfer (Q)
96% 115139
148.6 IPS
 
Image Super-Resolution (SP)
100% 4452
164.4 IPS
 
Image Super-Resolution (HP)
100% 25830
953.8 IPS
 
Image Super-Resolution (Q)
99% 27567
1.02 KIPS
 
Text Classification (SP)
100% 2237
2.99 KIPS
 
Text Classification (HP)
100% 3917
5.23 KIPS
 
Text Classification (Q)
93% 3906
5.24 KIPS
 
Machine Translation (SP)
100% 3258
56.1 IPS
 
Machine Translation (HP)
100% 3786
65.2 IPS
 
Machine Translation (Q)
98% 3894
67.3 IPS
 

Compare

Set Baseline Geekbench 6 now available