Geekbench ML Score

1887
Core ML Neural Engine Inference Score
Geekbench ML 0.6.0 for macOS AVX2

Result Information

Upload Date August 21 2024 12:56 AM
Views 2

System Information

System Information
Operating System macOS 14.5 (Build 23F79)
Model iMac (27-inch Retina Late 2015)
Model IDiMac17,1
Motherboard Apple Inc. Mac-B809C3757DA9BB8D iMac17,1
CPU Information
Name Intel Core i7-6700K
Topology 1 Processor, 4 Cores, 8 Threads
Identifier GenuineIntel Family 6 Model 94 Stepping 3
Base Frequency 4.00 GHz
Cluster 14 Cores
L1 Instruction Cache32.0 KB x 4
L1 Data Cache32.0 KB x 4
L2 Cache256 KB x 4
L3 Cache8.00 MB x 1
Memory Information
Size 32.00 GB
Transfer Rate1867 MT/s
Type DDR3
Inference Information
Framework Core ML
Backend Neural Engine
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1548
289.6 IPS
 
Image Classification (F16)
100% 1604
300.2 IPS
 
Image Classification (I8)
99% 1576
294.9 IPS
 
Image Segmentation (F32)
100% 355
5.92 IPS
 
Image Segmentation (F16)
100% 345
5.75 IPS
 
Image Segmentation (I8)
100% 338
5.64 IPS
 
Pose Estimation (F32)
100% 9338
11.3 IPS
 
Pose Estimation (F16)
100% 9746
11.8 IPS
 
Pose Estimation (I8)
100% 10204
12.4 IPS
 
Object Detection (F32)
100% 1205
89.9 IPS
 
Object Detection (F16)
100% 1214
90.6 IPS
 
Object Detection (I8)
97% 1260
94.1 IPS
 
Face Detection (F32)
100% 4766
56.7 IPS
 
Face Detection (F16)
98% 5658
67.3 IPS
 
Face Detection (I8)
97% 5582
66.4 IPS
 
Depth Estimation (F32)
100% 5888
45.7 IPS
 
Depth Estimation (F16)
100% 5973
46.3 IPS
 
Depth Estimation (I8)
37% 5460
42.3 IPS
 
Style Transfer (F32)
100% 16611
21.9 IPS
 
Style Transfer (F16)
100% 17956
23.6 IPS
 
Style Transfer (I8)
100% 19012
25.0 IPS
 
Image Super-Resolution (F32)
100% 3025
108.0 IPS
 
Image Super-Resolution (F16)
100% 2948
105.3 IPS
 
Image Super-Resolution (I8)
100% 2925
104.5 IPS
 
Text Classification (F32)
100% 223
320.9 IPS
 
Text Classification (F16)
100% 212
304.3 IPS
 
Text Classification (I8)
96% 242
347.7 IPS
 
Machine Translation (F32)
100% 243
4.46 IPS
 
Machine Translation (F16)
100% 231
4.26 IPS
 
Machine Translation (I8)
99% 248
4.57 IPS
 

Compare

Set Baseline Geekbench 6 now available