Intel Arc B570 vs Intel Arc Graphics 2 Xe Mobile Comparison

Intel
GPU

Intel Arc B570

CORE STATE BMG-G21
VRAM 10 GB
CLOCK SPEED 2500 MHz
TDP 150 W
BUS WIDTH 160 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2025
VS
Intel
GPU

Arc Graphics 2 Xe Mobile

CORE STATE Wildcat Lake
VRAM System Shared
CLOCK SPEED 2500 MHz
TDP 25 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,649
N/A
geekbench_opencl
83,514
N/A
geekbench_vulkan
96,844
N/A
passmark_directx_10
65
N/A
passmark_directx_11
118
N/A
passmark_directx_12
72
N/A
passmark_directx_9
164
N/A
passmark_g2d
661
N/A
passmark_g3d
14,195
N/A
passmark_gpu_compute
7,281
N/A

Analysis: Intel Arc B570 vs Intel Arc Graphics 2 Xe Mobile

Head-to-Head Benchmarks

The recorded data shows a fundamental mismatch in scale between these two Intel graphics parts. The Intel Arc B570 is a discrete desktop graphics card built on the Xe2-HPG architecture with 2304 shading units, while the Intel Arc Graphics 2 Xe Mobile is an integrated processor graphics solution on the Xe3-LPG architecture with just 256 shading units. The database contains no overlapping benchmark scores for these two products, as the mobile part has no recorded entries in the benchmark suite, but the raw specifications alone establish the performance gap.

The Intel Arc B570 delivers an average benchmark score of 20,556 across all recorded tests, placing it in the 65th percentile of all GPUs in the database. Its closest rival, the NVIDIA GeForce RTX 3070 Mobile, scores 20,534, a difference of only 0.1 percent, indicating the B570 sits in a tightly competitive performance band. The Intel Arc A750 is a near mirror image, scoring 20,582, which is 0.1 percent higher than the B570, making the two Intel discrete cards effectively interchangeable in raw compute performance. The AMD Radeon R9 M390X scores 20,662, putting it 0.5 percent ahead of the B570, while the NVIDIA Quadro M4000M trails at 20,480, a 0.4 percent deficit.

For the Intel Arc Graphics 2 Xe Mobile, the database shows zero benchmark scores and an average score of zero, with no nearest rivals listed. The percentile rank of 50 indicates it sits at the median of all GPUs in the database, but this is based on its specification profile rather than measured results. The compute gap between the two parts is stark: the B570 delivers 11.52 TFLOPS of FP32 throughput, while the mobile part manages 1,280.0 GFLOPS, which is 1.28 TFLOPS. That difference is an order of magnitude, and it manifests across every measured metric in the specification sheets.

Pixel throughput tells a similar story. The B570 achieves 200.0 GPixel/s, while the mobile part reaches 20.00 GPixel/s, a 10x gap. Texture fill rates are 360.0 GTexel/s versus 40.00 GTexel/s, again a 9x difference. The B570 has 144 texture mapping units and 80 raster output units, compared to 16 TMUs and 8 ROPs on the mobile part. Ray tracing cores number 18 on the B570 versus 2 on the mobile solution.

Memory bandwidth is another decisive separator. The B570 uses 10 GB of GDDR6 memory on a 160-bit bus, delivering 380.0 GB/s of bandwidth. The mobile part relies on system shared memory, with bandwidth described as system dependent. This means the mobile GPU's memory performance is tied to whatever laptop chassis it resides in, typically far below dedicated VRAM bandwidth. The B570's memory clock runs at 2375 MHz, or 19 Gbps effective, while the mobile part has no dedicated memory clock to report.

Where Each One Wins

The Intel Arc B570 wins decisively in every category where the database records measurable performance. Its 3DMark Steel Nomad DX12 score of 2,649 demonstrates strong DirectX 12 capability for modern gaming workloads. Geekbench OpenCL results show 83,514, while Geekbench Vulkan reaches 96,844, indicating solid cross-API compute performance. PassMark G3D scores 14,195, placing it well above the median GPU in the database. The B570 also posts a PassMark GPU Compute score of 7,281, confirming its ability to handle compute-heavy applications beyond pure graphics rendering.

The B570's advantage extends to legacy API support as well. PassMark DirectX 9 scores 164, DirectX 10 scores 65, DirectX 11 scores 118, and DirectX 12 scores 72. These results show the card handles older titles with ease while maintaining modern API throughput. The PassMark G2D score of 661 indicates strong 2D and desktop compositing performance, useful for productivity and content creation workloads.

The Intel Arc Graphics 2 Xe Mobile wins in the categories of power efficiency and physical footprint, though the database records no benchmark scores to quantify the performance trade-off. Its TDP is 25 W, compared to 150 W for the B570. The mobile part is an IGP with no power connectors, while the B570 requires a single 8-pin connector and a suggested 450 W power supply. The mobile part is built on a 3 nm process from Intel, while the B570 uses a 5 nm process from TSMC. The smaller process node suggests the mobile part achieves its low power draw through architectural efficiency, though the database does not provide measured efficiency figures.

The mobile part's base clock is 300 MHz with a boost of 2500 MHz, matching the B570's boost clock of 2500 MHz. However, the B570 runs at a constant 2500 MHz base and boost, meaning it sustains its peak frequency continuously. The mobile part's 300 MHz base clock indicates it idles much lower, which contributes to its 25 W power envelope. The B570's dual-slot form factor and 272 mm length stand in contrast to the mobile part's IGP design, which occupies no expansion slot and requires no cooling solution beyond what the laptop chassis provides.

The Verdict

The data indicates the Intel Arc B570 is the only viable choice for any workload that requires measurable graphics performance. Its 65th percentile ranking among all GPUs in the database, combined with an average benchmark score of 20,556, places it in the same performance class as the NVIDIA GeForce RTX 3070 Mobile, within 0.1 percent. The B570's nearest rivals all fall within a 0.5 percent band, meaning the B570 is competitive with established mid-range discrete GPUs.

The Intel Arc Graphics 2 Xe Mobile has no recorded benchmark scores, making direct performance comparison impossible from the database. Its 50th percentile ranking is based on specifications alone, and its 256 shading units, 16 TMUs, and 8 ROPs represent a fraction of the B570's resources. The mobile part's 1,280.0 GFLOPS FP32 throughput is roughly one-ninth of the B570's 11.52 TFLOPS. For gaming, rendering, or compute workloads, the B570 is the clear choice.

The mobile part's advantage lies in its integration. At 25 W TDP with no power connectors and no expansion slot requirement, it suits thin-and-light laptops where dedicated graphics is not feasible. The B570 requires a 450 W power supply, a dual-slot chassis, and a PCIe 4.0 x8 slot. For users building a desktop system, the B570 delivers measurable performance. For users purchasing a portable device, the mobile part is the only option in this comparison, but the database does not quantify its real-world performance.

The release timeline also matters. The B570 launched on January 15, 2025, with a launch MSRP of 219 USD, while the mobile part has a release date of April 15, 2026. The mobile part belongs to the Arc Graphics-M generation based on the Wildcat Lake chip, succeeding HD Graphics-M. The B570 belongs to the Battlemage generation, succeeding the Alchemist architecture. Both are listed as active production parts.

FAQ

Q: How does the Intel Arc B570 compare to its nearest rival, the NVIDIA GeForce RTX 3070 Mobile?

A: The B570 has an average benchmark score of 20,556, while the RTX 3070 Mobile scores 20,534, a difference of 0.1 percent in favor of the B570. Both parts sit in the same performance tier according to the database.

Q: What is the performance gap between the Intel Arc B570 and the Intel Arc Graphics 2 Xe Mobile?

A: The database records no overlapping benchmark scores. Based on specifications, the B570 delivers 11.52 TFLOPS of FP32 throughput versus 1,280.0 GFLOPS for the mobile part, and 200.0 GPixel/s pixel rate versus 20.00 GPixel/s.

Q: Does the Intel Arc Graphics 2 Xe Mobile support modern graphics APIs?

A: Yes, it supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, identical to the Intel Arc B570's API support.

Q: What memory configuration does each part use?

A: The B570 uses 10 GB of GDDR6 memory on a 160-bit bus with 380.0 GB/s bandwidth. The mobile part uses system shared memory with system dependent bandwidth.

Q: What are the power requirements for each part?

A: The B570 has a TDP of 150 W and requires a 450 W suggested power supply plus a single 8-pin connector. The mobile part has a 25 W TDP, no power connectors, and is an IGP.

Q: How does the Intel Arc B570 perform in compute workloads?

A: The B570 scores 83,514 in Geekbench OpenCL, 96,844 in Geekbench Vulkan, and 7,281 in PassMark GPU Compute, indicating strong compute capability for a mid-range discrete GPU.

Architecture Differences

The Intel Arc B570 uses the BMG-G21 chip built on the Xe2-HPG architecture, manufactured on a 5 nm process at TSMC. The die contains 19,600 million transistors across a 272 mm² area, yielding a transistor density of 72.1M per mm². The Intel Arc Graphics 2 Xe Mobile uses the Wildcat Lake chip on the Xe3-LPG architecture, manufactured on a 3 nm process at Intel. Its transistor count and die size are unknown in the database.

The B570 belongs to the Battlemage generation, specifically the Arc 5 tier, and succeeds the Alchemist architecture. The mobile part belongs to the Arc Graphics-M generation under the Wildcat Lake codename and succeeds HD Graphics-M. The generation names reflect their positioning: Battlemage targets discrete desktop graphics, while Arc Graphics-M targets integrated mobile graphics.

Compute resources differ by an order of magnitude. The B570 has 2304 shading units, 144 TMUs, and 80 ROPs, along with 18 ray tracing cores. The mobile part has 256 shading units, 16 TMUs, and 8 ROPs, with 2 ray tracing cores. Neither part lists tensor cores in the database. The B570's FP16 throughput is 23.04 TFLOPS at a 2:1 ratio, while the mobile part achieves 2.560 TFLOPS at the same ratio.

Memory architecture separates the two fundamentally. The B570 features dedicated GDDR6 memory with a 160-bit bus and fixed 380.0 GB/s bandwidth. The mobile part uses system shared memory, meaning its bandwidth depends on the host platform's memory subsystem. The B570's memory clock is 2375 MHz (19 Gbps effective), while the mobile part has no dedicated memory clock. This distinction affects latency, bandwidth consistency, and overall performance stability.

Power delivery reflects their different roles. The B570 is a dual-slot card measuring 272 mm in length and 115 mm in height, requiring a PCIe 4.0 x8 slot and a single 8-pin power connector. Its TDP is 150 W with a suggested 450 W power supply. The mobile part is an IGP with no slot, no power connectors, and a 25 W TDP. It uses the PCIe IGP bus interface, meaning it integrates directly into the processor package.

Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs differ: the B570 provides 1x HDMI 2.1a and 3x DisplayPort 2.1, while the mobile part's display outputs are portable device dependent. The B570's clock behavior is steady at 2500 MHz for both base and boost, while the mobile part ranges from 300 MHz base to 2500 MHz boost, reflecting its power management strategy for laptop use.

DETAILED SPECIFICATIONS

SPECIFICATION
B570
Graphics 2 Xe Mobile
Core Specs
Shading Units
2,304
256 -88.9%
Shaders
2,304
256 -88.9%
TMUs
144
16 -88.9%
ROPs
80
8 -90.0%
Execution Units
18
4 -77.8%
Clocks
Base Clock
2500 MHz
300 MHz
Boost Clock
2500 MHz
2500 MHz
Memory Clock
2375 MHz 19 Gbps effective
System Shared
Memory
Memory Size
10 GB
System Shared
VRAM (MB)
10,240
Memory Type
GDDR6
System Shared
Memory Bus
160 bit
System Shared
Bandwidth
380.0 GB/s
System Dependent
Cache
L1 Cache
256 KB (per EU)
64 KB (per EU)
L2 Cache
13.5 MB
16 MB
Performance
Pixel Rate
200.0 GPixel/s
20.00 GPixel/s
Texture Rate
360.0 GTexel/s
40.00 GTexel/s
FP32 (TFLOPS)
11.52 TFLOPS
1,280.0 GFLOPS
FP64 (TFLOPS)
720.0 GFLOPS (1:16)
160.0 GFLOPS (1:8)
FP16 (TFLOPS)
23.04 TFLOPS (2:1)
2.560 TFLOPS (2:1)
AI/RT
RT Cores
18
2 -88.9%
XMX Cores
144
32 -77.8%
Power
TDP
150 W
25 W
TDP (W)
150
25 -83.3%
Suggested PSU
450 W
Power Connectors
1x 8-pin
None
Architecture
Architecture
Xe2-HPG
Xe3-LPG
GPU Name
BMG-G21
Wildcat Lake
Generation
Battlemage (Arc 5)
Arc Graphics-M (Wildcat Lake)
Process Size
5 nm
3 nm
Transistors
19,600 million
unknown
Die Size
272 mm²
unknown
Foundry
TSMC
Intel
Density
72.1M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
Shader Model
6.6
6.9
Physical
Slot Width
Dual-slot
IGP
Length
272 mm 10.7 inches
Height
115 mm 4.5 inches
Outputs
1x HDMI 2.1a3x DisplayPort 2.1
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
IGP
Other
Launch Price
219 USD
Production
Active
Active
Predecessor
Alchemist
HD Graphics-M
View Arc B570 Details View Arc Graphics 2 Xe Mobile Details