Geekbench AI Score

4316
Single Precision Score
29330
Half Precision Score
32797
Quantized Score
Geekbench AI 1.7.0 for macOS AArch64

Result Information

User Mojoxer
Upload Date April 07 2026 10:03 PM
Views 12

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Pro
System Information
Operating System macOS 26.4 (Build 25E246)
Model Mac mini (2023)
Model IDMac14,12
Motherboard Mac14,12
CPU Information
Name Apple M2 Pro
Topology 1 Processor, 10 Cores
Identifier Apple M2 Pro
Base Frequency 3.48 GHz
Cluster 16 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1347
250.6 IPS
 
Image Classification (HP)
100% 14928
2.78 KIPS
 
Image Classification (Q)
97% 18485
3.45 KIPS
 
Image Segmentation (SP)
100% 1628
26.4 IPS
 
Image Segmentation (HP)
100% 20153
326.7 IPS
 
Image Segmentation (Q)
99% 24517
397.4 IPS
 
Pose Estimation (SP)
100% 11633
13.6 IPS
 
Pose Estimation (HP)
100% 107707
125.7 IPS
 
Pose Estimation (Q)
95% 105718
123.9 IPS
 
Object Detection (SP)
100% 1638
129.9 IPS
 
Object Detection (HP)
99% 15907
1.27 KIPS
 
Object Detection (Q)
89% 18200
1.46 KIPS
 
Face Detection (SP)
100% 3561
42.3 IPS
 
Face Detection (HP)
100% 38108
452.8 IPS
 
Face Detection (Q)
100% 52395
622.6 IPS
 
Depth Estimation (SP)
100% 6045
46.6 IPS
 
Depth Estimation (HP)
99% 89353
688.4 IPS
 
Depth Estimation (Q)
85% 113199
885.5 IPS
 
Style Transfer (SP)
100% 25496
32.8 IPS
 
Style Transfer (HP)
100% 208309
267.8 IPS
 
Style Transfer (Q)
96% 192826
248.8 IPS
 
Image Super-Resolution (SP)
100% 4925
181.9 IPS
 
Image Super-Resolution (HP)
100% 43723
1.61 KIPS
 
Image Super-Resolution (Q)
99% 52278
1.93 KIPS
 
Text Classification (SP)
100% 4633
6.18 KIPS
 
Text Classification (HP)
100% 7097
9.47 KIPS
 
Text Classification (Q)
92% 6575
8.83 KIPS
 
Machine Translation (SP)
100% 4293
74.0 IPS
 
Machine Translation (HP)
100% 4154
71.6 IPS
 
Machine Translation (Q)
98% 4201
72.6 IPS
 

Compare

Set Baseline Geekbench AI now available