Geekbench AI Score

3600
Single Precision Score
16041
Half Precision Score
15903
Quantized Score
Geekbench AI 1.5.0 for macOS AArch64

Result Information

Upload Date November 22 2025 07:28 PM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M1 Pro
System Information
Operating System macOS 26.1 (Build 25B78)
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 3.22 GHz
Cluster 18 Cores
Cluster 22 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1336
248.4 IPS
 
Image Classification (HP)
100% 6308
1.17 KIPS
 
Image Classification (Q)
96% 6043
1.13 KIPS
 
Image Segmentation (SP)
100% 1515
24.6 IPS
 
Image Segmentation (HP)
100% 9342
151.4 IPS
 
Image Segmentation (Q)
99% 9978
161.7 IPS
 
Pose Estimation (SP)
100% 10418
12.2 IPS
 
Pose Estimation (HP)
100% 68157
79.5 IPS
 
Pose Estimation (Q)
95% 63520
74.4 IPS
 
Object Detection (SP)
100% 1496
118.7 IPS
 
Object Detection (HP)
99% 7253
577.0 IPS
 
Object Detection (Q)
91% 6786
542.3 IPS
 
Face Detection (SP)
100% 3279
39.0 IPS
 
Face Detection (HP)
100% 13371
158.9 IPS
 
Face Detection (Q)
100% 12721
151.1 IPS
 
Depth Estimation (SP)
100% 5705
44.0 IPS
 
Depth Estimation (HP)
99% 46890
361.3 IPS
 
Depth Estimation (Q)
85% 48063
375.6 IPS
 
Style Transfer (SP)
100% 21990
28.3 IPS
 
Style Transfer (HP)
100% 116826
150.2 IPS
 
Style Transfer (Q)
96% 111209
143.5 IPS
 
Image Super-Resolution (SP)
100% 4013
148.2 IPS
 
Image Super-Resolution (HP)
100% 25440
939.4 IPS
 
Image Super-Resolution (Q)
99% 25639
946.7 IPS
 
Text Classification (SP)
100% 2368
3.16 KIPS
 
Text Classification (HP)
99% 4206
5.61 KIPS
 
Text Classification (Q)
93% 4207
5.65 KIPS
 
Machine Translation (SP)
100% 2969
51.1 IPS
 
Machine Translation (HP)
100% 4943
85.1 IPS
 
Machine Translation (Q)
98% 5430
93.8 IPS
 

Compare

Set Baseline Geekbench 6 now available