Intel Arc Pro B370 vs Intel Arc Pro B60 Dual Comparison

Intel
GPU

Intel Arc Pro B370

CORE STATE Panther Lake
VRAM System Shared
CLOCK SPEED 2400 MHz
TDP 25 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026
VS
Intel
GPU

Arc Pro B60 Dual

CORE STATE BMG-G21
VRAM 24 GB
CLOCK SPEED 2400 MHz
TDP 400 W
BUS WIDTH 192 bit
ARCHITECTURE Xe2-HPG
nm
PROCESS 5 nm
LAUNCH DATE 2025

Analysis: Intel Arc Pro B370 vs Intel Arc Pro B60 Dual

Intel Arc Pro B370 and Intel Arc Pro B60 Dual occupy opposite ends of the same product family, and the recorded data shows a clear split in purpose. The B370 is an integrated graphics processor built for efficiency and portability, while the B60 Dual is a massive discrete workstation card aimed at maximum throughput. The benchmark database shows no direct head-to-head scores, but the specification data provides a definitive picture of where each part belongs.

Where Each One Wins

The Intel Arc Pro B370 wins on integration and power economy. It is an IGP, meaning it lives inside the processor package and requires no separate card, no power connectors, and no cooling solution beyond what the host system already has. Its 25 W TDP makes it suitable for thin-and-light mobile workstations or compact desktops where a discrete GPU cannot fit. The B370 uses system shared memory, so it does not need its own VRAM allocation, which keeps the bill of materials low. For tasks like office productivity, media playback, or light GPU-accelerated workloads that do not demand high sustained throughput, the B370 delivers a functional graphics solution with a 50th percentile standing among all GPUs in the database.

The Intel Arc Pro B60 Dual wins on raw performance and memory capacity. It is a dual-slot discrete card with a 400 W TDP, a 16-pin power connector, and a suggested 800 W power supply, so it is built for a workstation chassis with serious power delivery. The B60 Dual carries 24 GB of GDDR6 memory on a 192-bit bus, delivering 456.0 GB/s of bandwidth. That combination is a clear advantage for large datasets, rendering scenes, or compute workloads that exceed the shared-memory limits of the B370. The B60 Dual also has twice the shading units, four times the texture units and ROPs, and double the ray tracing cores, all of which point to a part designed for professional 3D workloads rather than everyday graphics.

Architecture Differences

The two GPUs come from different architectural generations and different foundries. The Arc Pro B370 uses the Panther Lake chip based on the Xe3-LPG architecture, built on a 3 nm process at Intel. The B60 Dual uses the BMG-G21 chip based on Xe2-HPG architecture, built on a 5 nm process at TSMC. The process node difference is notable: the B370 uses a more advanced 3 nm process, but the B60 Dual compensates with a much larger die. The B60 Dual's die measures 272 mm² and packs 19,600 million transistors, giving a transistor density of 72.1M per mm². The B370's transistor count and die size are not recorded, but its 3 nm node indicates a newer manufacturing approach.

The memory architectures are fundamentally different. The B370 uses system shared memory with a system dependent bandwidth, meaning it borrows from the host's RAM and its performance scales with the platform's memory speed. The B60 Dual uses dedicated 24 GB of GDDR6 with a fixed 456.0 GB/s bandwidth. The B370's memory clock is listed as system shared, while the B60 Dual runs its memory at 2375 MHz with 19 Gbps effective speed.

The API support is identical: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The shading architecture also scales directly: the B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores, while the B60 Dual doubles each of those to 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. Both lack tensor cores, so neither part relies on dedicated AI acceleration hardware.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between the B370 and the B60 Dual, so the comparison relies on the recorded specification data. The most significant gaps appear in throughput rates. The B370 achieves a pixel rate of 48.00 GPixel/s and a texture rate of 96.00 GTexel/s. The B60 Dual reaches 192.0 GPixel/s and 384.0 GTexel/s, which is exactly four times the pixel throughput and four times the texture throughput of the B370. That means the B60 Dual can fill the screen and apply textures at a rate the B370 cannot approach, which translates directly to higher resolution rendering and more complex scenes.

Compute performance shows a similar 2x scaling. The B370 delivers 6.144 TFLOPS of FP32 compute and 12.29 TFLOPS of FP16 with a 2:1 ratio. The B60 Dual delivers 12.29 TFLOPS of FP32 and 24.58 TFLOPS of FP16, again exactly double. For any single-precision compute workload, the B60 Dual is twice as fast on paper. The FP16 numbers indicate both parts can use the 2:1 rate when the workload permits, but the B60 Dual's absolute advantage remains the same factor of two.

Clock speeds are not the differentiator. Both parts boost to 2400 MHz, but the base clocks differ hugely. The B370 runs at a 300 MHz base clock, while the B60 Dual starts at 2000 MHz. The B370's low base clock is typical of an IGP that ramps up under load to save power when idle. The B60 Dual's high base clock reflects a card that is expected to sustain heavy workloads without dropping below a high frequency floor.

The memory bandwidth gap is the largest single spec difference. The B370's bandwidth is system dependent, so it cannot be quantified in the database. The B60 Dual's 456.0 GB/s is a fixed figure that dwarfs what any shared-memory IGP can typically access, especially in dual-channel laptop configurations. For workloads that stream large textures or datasets, that bandwidth advantage is the deciding factor.

Specification Differences

The two parts differ across nearly every measurable category. The B370 is a 25 W IGP with no power connectors and no slot width, while the B60 Dual is a 400 W dual-slot card requiring a 16-pin connector and an 800 W suggested power supply. The B370 uses system shared memory with no dedicated VRAM, while the B60 Dual has 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth. The B370's memory clock is system shared, while the B60 Dual runs at 2375 MHz with 19 Gbps effective speed.

The B370 has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores, while the B60 Dual has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The B370's pixel rate is 48.00 GPixel/s and its texture rate is 96.00 GTexel/s, while the B60 Dual records 192.0 GPixel/s and 384.0 GTexel/s. FP32 compute is 6.144 TFLOPS for the B370 and 12.29 TFLOPS for the B60 Dual. FP16 is 12.29 TFLOPS and 24.58 TFLOPS respectively.

The B370 is built on a 3 nm Intel process using the Panther Lake chip and Xe3-LPG architecture. The B60 Dual is built on a 5 nm TSMC process using the BMG-G21 chip and Xe2-HPG architecture. The B60 Dual has a recorded die size of 272 mm², 19,600 million transistors, and a transistor density of 72.1M per mm²; none of those figures are recorded for the B370.

The bus interface differs as well. The B370 connects via IGP, meaning it is integrated into the processor package. The B60 Dual uses PCIe 5.0 x8, giving it a dedicated high-bandwidth link to the host. Display outputs also differ: the B370's outputs are portable device dependent, while the B60 Dual has 4x mini-DisplayPort 2.1 connectors. Physical dimensions are only recorded for the B60 Dual: 300 mm length (11.8 inches), 110 mm height (4.3 inches), and 40 mm width (1.6 inches).

Release timing also separates the parts. The B60 Dual launched on 2025-09-04 with a launch MSRP of 1,199 USD. The B370 launched later, on 2026-01-26, and has no recorded MSRP. The B370's predecessor is listed as HD Graphics-WM, while the B60 Dual has no predecessor recorded.

FAQ

Q: Which GPU has more shading units?

A: The Arc Pro B60 Dual has 2560 shading units, exactly double the 1280 found in the Arc Pro B370.

Q: How much memory does each GPU have?

A: The Arc Pro B370 uses system shared memory with no dedicated VRAM. The Arc Pro B60 Dual has 24 GB of GDDR6 on a 192-bit bus.

Q: What is the power draw difference?

A: The Arc Pro B370 has a 25 W TDP, while the Arc Pro B60 Dual has a 400 W TDP and requires a 16-pin power connector with a suggested 800 W power supply.

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the memory bandwidth of each GPU?

A: The Arc Pro B370's bandwidth is system dependent. The Arc Pro B60 Dual delivers 456.0 GB/s.

Q: Which GPU has a higher boost clock?

A: Both GPUs boost to 2400 MHz. The base clocks differ: the B370 runs at 300 MHz, while the B60 Dual runs at 2000 MHz.

The Verdict

The data points to a straightforward choice based on the system form factor and workload demands. The Arc Pro B370 is the pick for a compact, power-limited system where a discrete card is not an option. Its 25 W TDP, IGP bus interface, and shared memory mean it fits into a laptop or small desktop without additional power delivery or cooling. The 3 nm Intel process and Xe3-LPG architecture make it a modern, efficient part, but its 6.144 TFLOPS FP32 compute and system dependent bandwidth cap its ceiling for heavy rendering.

The Arc Pro B60 Dual is the pick for a professional workstation that needs sustained high throughput. Its 12.29 TFLOPS FP32 compute is double the B370, its 456.0 GB/s of dedicated bandwidth is a fixed and massive advantage, and its 24 GB of GDDR6 memory removes any capacity limits. The 400 W TDP, dual-slot cooler, and 800 W suggested power supply make it a serious installation, but the performance data justifies that requirement. The B60 Dual also launched earlier, in September 2025, and carries a launch MSRP of 1,199 USD, while the B370 has no recorded price.

The 50th percentile standing among all GPUs is identical for both parts, but that is a coarse measure. The specification sheets show a 2x gap in shading units, TMUs, ROPs, RT cores, FP32, and FP16, and a 4x gap in pixel rate and texture rate. The B370's 48.00 GPixel/s and 96.00 GTexel/s are respectable for an IGP, but the B60 Dual's 192.0 GPixel/s and 384.0 GTexel/s are in a different class. For someone building a portable workstation or a low-power desktop, the B370 delivers a functional graphics solution with no add-in card required. For anyone running professional 3D, video, or compute workloads that can use a 400 W card, the B60 Dual is the only choice between these two.

DETAILED SPECIFICATIONS

SPECIFICATION
Pro B370
Pro B60 Dual
Core Specs
Shading Units
1,280
2,560 +100.0%
Shaders
1,280
2,560 +100.0%
TMUs
40
160 +300.0%
ROPs
20
80 +300.0%
Execution Units
10
20 +100.0%
Clocks
Base Clock
300 MHz
2000 MHz
Boost Clock
2400 MHz
2400 MHz
Memory Clock
System Shared
2375 MHz 19 Gbps effective
Memory
Memory Size
System Shared
24 GB
VRAM (MB)
24,576
Memory Type
System Shared
GDDR6
Memory Bus
System Shared
192 bit
Bandwidth
System Dependent
456.0 GB/s
Cache
L1 Cache
64 KB (per EU)
L2 Cache
16 MB
10 MB
Performance
Pixel Rate
48.00 GPixel/s
192.0 GPixel/s
Texture Rate
96.00 GTexel/s
384.0 GTexel/s
FP32 (TFLOPS)
6.144 TFLOPS
12.29 TFLOPS
FP64 (TFLOPS)
768.0 GFLOPS (1:8)
3.072 TFLOPS (1:4)
FP16 (TFLOPS)
12.29 TFLOPS (2:1)
24.58 TFLOPS (2:1)
AI/RT
RT Cores
10
20 +100.0%
XMX Cores
80
160 +100.0%
Power
TDP
25 W
400 W
TDP (W)
25
400 +1500.0%
Suggested PSU
800 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
Xe3-LPG
Xe2-HPG
GPU Name
Panther Lake
BMG-G21
Generation
Arc Graphics-WM (Panther Lake)
Battlemage (Pro Series)
Process Size
3 nm
5 nm
Transistors
unknown
19,600 million
Die Size
unknown
272 mm²
Foundry
Intel
TSMC
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
6.9
6.6
Physical
Slot Width
IGP
Dual-slot
Length
300 mm 11.8 inches
Height
110 mm 4.3 inches
Outputs
Portable Device Dependent
4x mini-DisplayPort 2.1
Bus Interface
IGP
PCIe 5.0 x8
Other
Launch Price
1,199 USD
Production
Active
Active
Predecessor
HD Graphics-WM
View Arc Pro B370 Details View Arc Pro B60 Dual Details