Geekbench AI Score

4051
Single Precision Score
23288
Half Precision Score
25764
Quantized Score
Geekbench AI 1.1.0 for macOS AArch64

Result Information

Upload Date November 09 2024 05:46 PM
Views 2

System Information

AI Information
Framework Core ML
Backend Neural Engine
Device Apple M2 Max
System Information
Operating System macOS 15.0.1 (Build 24A348)
Model MacBook Pro (14-inch, 2023)
Model IDMac14,5
Motherboard Mac14,5
CPU Information
Name Apple M2 Max
Topology 1 Processor, 12 Cores
Identifier Apple M2 Max
Base Frequency 3.46 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 32.00 GB

AI Performance

Workload Accuracy Score
Image Classification (SP)
100% 1388
258.1 IPS
 
Image Classification (HP)
100% 15243
2.83 KIPS
 
Image Classification (Q)
96% 16675
3.11 KIPS
 
Image Segmentation (SP)
100% 1580
25.6 IPS
 
Image Segmentation (HP)
100% 10194
165.3 IPS
 
Image Segmentation (Q)
99% 11277
182.8 IPS
 
Pose Estimation (SP)
100% 12393
14.5 IPS
 
Pose Estimation (HP)
100% 106746
124.6 IPS
 
Pose Estimation (Q)
95% 105219
123.3 IPS
 
Object Detection (SP)
100% 1677
133.0 IPS
 
Object Detection (HP)
99% 15447
1.23 KIPS
 
Object Detection (Q)
91% 17288
1.38 KIPS
 
Face Detection (SP)
100% 3278
38.9 IPS
 
Face Detection (HP)
100% 31279
371.7 IPS
 
Face Detection (Q)
100% 44593
529.9 IPS
 
Depth Estimation (SP)
100% 5894
45.4 IPS
 
Depth Estimation (HP)
99% 86461
666.1 IPS
 
Depth Estimation (Q)
85% 109855
858.5 IPS
 
Style Transfer (SP)
100% 24971
32.1 IPS
 
Style Transfer (HP)
100% 207155
266.3 IPS
 
Style Transfer (Q)
96% 191526
247.2 IPS
 
Image Super-Resolution (SP)
100% 5104
188.5 IPS
 
Image Super-Resolution (HP)
100% 42418
1.57 KIPS
 
Image Super-Resolution (Q)
99% 50869
1.88 KIPS
 
Text Classification (SP)
100% 2289
3.06 KIPS
 
Text Classification (HP)
100% 4007
5.35 KIPS
 
Text Classification (Q)
93% 3920
5.26 KIPS
 
Machine Translation (SP)
100% 4634
79.8 IPS
 
Machine Translation (HP)
100% 1923
33.1 IPS
 
Machine Translation (Q)
98% 2014
34.8 IPS
 

Compare

Set Baseline Geekbench 6 now available