Intel Arc Pro B65 vs Arc B570

We compared two discrete desktop graphics cards: the Intel Arc Pro B65 32 GB with 20 pipelines and 2560 shaders against the 1 year and 4 months older Arc B570 10 GB that utilizes 18 pipelines and 2304 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Please note that the tests on the Intel Arc Pro B65 are done on an engineering sample provided by our insiders. The data will be more accurate after the final version of this GPU is available.

Key differences

Key distinctions and advantages of Arc B570 over Arc Pro B65
Reasons to consider the Intel Arc Pro B65
  • Includes 22 GB more video memory
  • Has 60% higher memory bandwidth: 608 vs 380 GB/s

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5 -
113
66
59
38
The Witcher 3 -
126
110
80
40
Counter-Strike 2 -
152
108
79
39
Far Cry 6 -
97
88
67
34
Hogwarts Legacy -
61
50
37
18
CoD: Modern Warfare III -
65
67
47
28
Ghost of Tsushima -
63
53
37
21
Cyberpunk 2077 -
76
68
45
18
Shadow of the Tomb Raider -
108
94
68
40
Average FPS by Resolution
1080p High - 96
1080p Ultra - 78
1440p Ultra - 58
4K Ultra - 31
Margin of Error High 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
Time Spy - 12564
Solar Bay - 48698
Port Royal - 6742
Fire Strike - 31264
Wild Life Extreme - 24446
Night Raid - 112674
Sources: 3DMark [1]

GeekBench 6 GPU Compute

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
85640
Background Blur - 223.7 img/sec
Face Detection - 115.2 img/sec
Horizon Detection - 2.14 Gpixels/sec
Edge Detection - 3.95 Gpixels/sec
Gaussian Blur - 4.81 Gpixels/sec
Feature Matching - 0.93 Gpixels/sec
Stereo Matching - 294.6 Gpixels/sec
Particle Physics - 11270.6 FPS
API - OpenCL
Sources: Geekbench [3]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
14187
G2D Mark - 629
DirectX 11 - 110 FPS
DirectX 12 - 70 FPS
GPU Compute - 7407 Ops/s
Sources: PassMark [5] – 503 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
1782.66
Sources: Blender [9] – 21 samples

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
20296
GB6 ML Half Precision
33136
GB6 ML Quantized
12966
Image Classification (SP) - 9924
Image Segmentation (HP) - 20640
Image Super Resolution (Q) - 14215
Face Detection (HP) - 39045
Pose Estimation (Q) - 56787
Text Classification (SP) - 3028
Machine Translation (HP) - 3740
Object Detection (SP) - 13018
Depth Estimation (Q) - 31035
Style Transfer (SP) - 176206
Framework - ONNX
Backend - DirectML
Sources: Geekbench [9]

Specifications

Technical specifications of Intel Arc Pro B65 and Arc B570

General

Vendor Intel Intel
Build Discrete Discrete
Released March 25, 2026 December 3, 2024
Launch price (MSRP) - $219
Case Desktop Desktop
Purpose Professional Gaming
Segment Mid-range Mid-range
Architecture Battlemage Pro Series Generation 12.7
GPU Codename BMG-G21 BMG-G21
Rival Equivalent - - GeForce RTX 4060
Recommended CPU - - Intel Core Ultra 5 245K or above
Desktop GPU rating (#59th place)

Graphics Processing Unit

Base Clock 2000 MHz 1700 MHz
Boost Clock 2400 MHz 2500 MHz
Shading Units 2560 2304
Texture Mapping Units (TMUs) 160 144
Render Output Units (ROPs) 80 72
Compute Units (Pipelines) 20 18
Tensor Cores 160 144
Ray-tracing Cores 20 18
L1 Cache 256KB per cluster 256KB per cluster
L2 Cache 10MB shared 10MB shared
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 192 GPixel/s 180 GPixel/s
Texture Fill Rate 384 GTexel/s 360 GTexel/s
FLOPS (FP32)
12.3 TFLOPS
11.5 TFLOPS

Physical

Interface PCIe 5.0 x16 PCIe 4.0 x8
TGP 200 W 150 W
Manufacturing TSMC TSMC
Fabrication Process 5 nm 5 nm
Die Size 271.95 mm² 272 mm²
Transistor Count 19.6 billion 19.6 billion
Transistor Density 72.07 MTr/mm² 72.06 MTr/mm²

Memory

Memory Type GDDR6 GDDR6
Memory Size 32 GB 10 GB
Memory Clock 2375 MHz 2375 MHz
Effective Memory Speed 19000 Mbps 19000 Mbps
Bus 256-bit 160-bit
ECC No No
Memory Bandwidth
608 GB/s
380 GB/s

API

DirectX 12.2 12
Vulkan 1.3 1.3
OpenGL 4.6 4.6
OpenCL 3.0 3.0
CUDA No No
Ray Tracing Yes Yes
DLSS No No
DisplayPort 2.1a 2.1

Cast your vote

Choose between two graphics cards
0 (0%)
0 (0%)
Total votes: < 1

User opinions

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