Geekbench AI Score

5014
Single Precision Score
43575
Half Precision Score
57935
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User Jeff1959w
Upload Date March 19 2026 11:43 PM
Views 7

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M5 Pro
System Information
Operating System macOS 26.3.1 (Build 25D2128)
Model Mac17,9
Model IDMac17,9
Motherboard Mac17,9
CPU Information
Name Apple M5 Pro
Topology 1 Processor, 18 Cores
Identifier Apple M5 Pro
Base Frequency 4.61 GHz
Cluster 16 Cores
Cluster 212 Cores
Memory Information
Size 24.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 2334
434.0 IPS
 
Image Classification (HP)
100% 19198
3.57 KIPS
 
Image Classification (Q)
97% 22938
4.28 KIPS
 
Image Segmentation (SP)
100% 2491
40.4 IPS
 
Image Segmentation (HP)
100% 25830
418.7 IPS
 
Image Segmentation (Q)
99% 36509
591.8 IPS
 
Pose Estimation (SP)
100% 11179
13.0 IPS
 
Pose Estimation (HP)
100% 182208
212.6 IPS
 
Pose Estimation (Q)
95% 334394
391.9 IPS
 
Object Detection (SP)
100% 2807
222.6 IPS
 
Object Detection (HP)
100% 21966
1.74 KIPS
 
Object Detection (Q)
91% 28445
2.27 KIPS
 
Face Detection (SP)
100% 5164
61.4 IPS
 
Face Detection (HP)
100% 48937
581.5 IPS
 
Face Detection (Q)
100% 70003
831.8 IPS
 
Depth Estimation (SP)
100% 9379
72.3 IPS
 
Depth Estimation (HP)
99% 135987
1.05 KIPS
 
Depth Estimation (Q)
85% 195551
1.53 KIPS
 
Style Transfer (SP)
100% 26786
34.4 IPS
 
Style Transfer (HP)
100% 286146
367.8 IPS
 
Style Transfer (Q)
96% 394597
509.2 IPS
 
Image Super-Resolution (SP)
100% 6012
222.0 IPS
 
Image Super-Resolution (HP)
100% 63982
2.36 KIPS
 
Image Super-Resolution (Q)
99% 96633
3.57 KIPS
 
Text Classification (SP)
100% 2916
3.89 KIPS
 
Text Classification (HP)
99% 5555
7.41 KIPS
 
Text Classification (Q)
93% 5422
7.28 KIPS
 
Machine Translation (SP)
100% 2425
41.8 IPS
 
Machine Translation (HP)
100% 18375
316.5 IPS
 
Machine Translation (Q)
98% 18899
326.6 IPS
 

Compare

Set Baseline Geekbench 6 now available