Intel Arc B390 vs Apple M5 Max GPU (40-core)

We compared two integrated laptop graphics cards: the Intel Arc B390 with 12 pipelines and 1536 shaders against the Apple M5 Max GPU (40-core) that utilizes 640 pipelines and 5120 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score

Key differences

Key distinctions and advantages of M5 Max GPU (40-core) over Arc B390
Reasons to consider the Apple M5 Max GPU (40-core)
  • Performs significantly better (up to 3.2x) in 3DMark Steel Nomad Lite
  • 2.2x higher maximum theoretical performance (16.6 vs 7.7 TFLOPS)
  • Achieves 2.6x more points in the GeekBench 6 Compute test (146K vs 56K)
  • Has 3.3x more shading units (5120 vs 1536)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
80
41
36
20
-
The Witcher 3
76
63
44
19
-
Counter-Strike 2
96
70
46
23
-
Far Cry 6
63
56
38
18
-
Hogwarts Legacy
33
24
18
-
-
CoD: Modern Warfare III
37
35
28
13
-
Ghost of Tsushima
37
31
24
12
-
Cyberpunk 2077
43
38
21
9
-
Shadow of the Tomb Raider
65
57
39
23
-
Average FPS by Resolution
1080p High 59 -
1080p Ultra 46 -
1440p Ultra 33 -
4K Ultra 16 -
Margin of Error Low Low

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
5461
17738
Time Spy 6880 -
Solar Bay 26783 79263
Port Royal 3880 -
Fire Strike 16845 -
Wild Life Extreme 11778 42423
Night Raid 72249 -
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
56204
146407
Background Blur 87.6 img/sec 257 img/sec
Face Detection 58.5 img/sec 182.1 img/sec
Horizon Detection 1.9 Gpixels/sec 5.4 Gpixels/sec
Edge Detection 2.68 Gpixels/sec 8.33 Gpixels/sec
Gaussian Blur 4.74 Gpixels/sec 8.86 Gpixels/sec
Feature Matching 1.01 Gpixels/sec 1.28 Gpixels/sec
Stereo Matching 249.7 Gpixels/sec 455.4 Gpixels/sec
Particle Physics 10821.1 FPS 21658 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
G2D Mark 812 -
DirectX 11 70 FPS -
DirectX 12 48 FPS -
GPU Compute 3669 Ops/s -
Sources: PassMark [5]425 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
1269.36
8095.71
Sources: Blender [9], [10]95 & 201 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Intel Arc B390
DateBenchmarkResult
📘 2026-09-05 -> asterismxGeekbench 6 OpenCL57164
Apple M5 Max GPU (40-core)
DateBenchmarkResult
📘 2026-04-16 -> Apple loverGeekbench 6 OpenCL146276
📘 2026-03-25 (Steven)Cinebench 20249283
📘 2026-03-25 (Steven)Steel Nomad Light18486

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
12930
29452
GB6 ML Half Precision
23819
GB6 ML Quantized
8437
43305
Image Classification (SP) 5487 10711
Image Segmentation (HP) 16864 42406
Image Super Resolution (Q) 8788 42905
Face Detection (HP) 25029 73489
Pose Estimation (Q) 18852 289766
Text Classification (SP) 2115 6087
Machine Translation (HP) 4266 8881
Object Detection (SP) 7449 10130
Depth Estimation (Q) 22207 84224
Style Transfer (SP) 95039 264552
Framework ONNX Core ML
Backend DirectML GPU
Sources: Geekbench [9], [10]
Results were compared using different ML frameworks

Specifications

Technical specifications of Intel Arc B390 and Apple M5 Max GPU (40-core)

General

Vendor Intel Apple
Build Integrated Integrated
Released January 5, 2026 March 3, 2026
Case Laptop Laptop
Purpose Gaming Professional
Segment Mid-range Mid-range
Architecture Celestial Apple M GPU
GPU Codename Panther Lake Custom
Recommended CPU - Intel Core Ultra X9 388H or above - Apple M5 Max (40-сore GPU) or above
Used in CPUs - Intel Core Ultra X9 378H
- Intel Core Ultra X7 368H
- Intel Core Ultra X9 388H
- Intel Core Ultra X7 358H
- Apple M5 Max (40-сore GPU)
Laptop GPU ranking (62nd and 6th place)

Graphics Processing Unit

Base Clock 300 MHz -
Boost Clock 2500 MHz 1620 MHz
Shading Units 1536 5120
Texture Mapping Units (TMUs) 48 320
Render Output Units (ROPs) 24 160
Compute Units (Pipelines) 12 640
Tensor Cores 96 -
Ray-tracing Cores 12 -
L1 Cache 64KB per cluster -
L2 Cache 16MB shared -
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 60 GPixel/s 259 GPixel/s
Texture Fill Rate 120 GTexel/s 518 GTexel/s
FLOPS (FP32)
7.7 TFLOPS
16.6 TFLOPS

Physical

Interface IGP Custom
TGP 30 W -
Manufacturing TSMC TSMC
Fabrication Process 3 nm 3 nm
Transistor Count - 28 billion
Max. Temperature 100°C 100°C

Memory

Memory Type System Shared System Shared
Memory Clock - 9600 MHz
Bus - 512-bit
ECC No No
Memory Bandwidth

API

DirectX 12.1 -
Vulkan 1.4 -
OpenGL 4.6 -
OpenCL 3.0 -
CUDA No -
Ray Tracing Yes Yes
DLSS No No
DisplayPort 2.1 -

Cast your vote

Choose between two graphics cards
0 (0%)
3 (100%)
Total votes: 3

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!