AMD Radeon PRO W7500 vs Intel Arc B390 Comparison

AMD
RADEON

AMD Radeon PRO W7500

CORE STATE Navi 33
VRAM 8 GB
CLOCK SPEED 1700 MHz
TDP 70 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 6 nm
LAUNCH DATE 2023
VS
Intel
GPU

Arc B390

CORE STATE Panther Lake
VRAM System Shared
CLOCK SPEED 2500 MHz
TDP 80 W
BUS WIDTH System Shared
ARCHITECTURE Xe3-LPG
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

geekbench_opencl
58,213
N/A
geekbench_vulkan
68,634
N/A
passmark_directx_10
65
N/A
passmark_directx_11
125
N/A
passmark_directx_12
46
N/A
passmark_directx_9
200
N/A
passmark_g2d
1,174
N/A
passmark_g3d
13,368
N/A
passmark_gpu_compute
5,910
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
1,482

Analysis: AMD Radeon PRO W7500 vs Intel Arc B390

Head-to-Head Benchmarks

The recorded database contains a limited set of directly comparable benchmark outputs for these two parts. The AMD Radeon PRO W7500 has comprehensive results across multiple API and workload tests, while the Intel Arc B390 only has a single 3DMark Steel Nomad DX12 entry. With no overlapping test entries in the head-to-head file, the comparison must rely on the average benchmark score and the percentile ranking against all GPUs.

The AMD Radeon PRO W7500 produces an average benchmark score of 16415 across its nine recorded tests. This places it at the 59th percentile of all GPUs in the database. Its nearest rival by average score is the NVIDIA RTX PRO 6000 Blackwell at 16408, a delta of 0 percent. The AMD Radeon RX 5700 XT trails at 16361, which is 0.3 percent behind, and the AMD Radeon Pro 5600M sits at 16351, 0.4 percent behind. The only competitor ahead in this group is the NVIDIA GeForce RTX 5090 D V2 at 16504, putting the W7500 0.5 percent behind it.

The Intel Arc B390 delivers an average benchmark score of 1482, based solely on its 3DMark Steel Nomad DX12 result. This lands at the 9th percentile of all GPUs. Its nearest rivals are all legacy NVIDIA parts: the GeForce GT 520MX at 1463 (1.3 percent behind), the GeForce 800M at 1460 (1.5 percent behind), the GeForce GT 625 OEM at 1446 (2.5 percent behind), and the GeForce GT 710 at 1443 (2.7 percent behind). The Arc B390 is ahead of all four of these comparison points.

The margin between the two products is substantial. The W7500's average score of 16415 is roughly 11 times higher than the Arc B390's 1482. That gap reflects a completely different performance class, as the W7500 ranks in the upper half of the database while the Arc B390 sits near the bottom. The data does not show any test where the Arc B390 comes close to the W7500 on a per-benchmark basis, because no shared benchmark exists between them.

The W7500's individual benchmark scores provide context for its average. In Geekbench OpenCL it records 58213, and in Geekbench Vulkan it reaches 68634. Passmark results include a graphics 3D score of 13368, a G2D score of 1174, and a GPU compute score of 5910. The DirectX legacy tests show 200 in DirectX 9, 125 in DirectX 11, 65 in DirectX 10, and 46 in DirectX 12. These figures indicate a strong general-purpose compute and graphics workload profile, with the Vulkan result being the standout.

The Arc B390 has no comparable per-test breakdown beyond its single 3DMark Steel Nomad DX12 score of 1482. That test is a modern DX12 workload, and the recorded value places it far below the W7500's DirectX 12 Passmark score of 46, though direct comparison is not possible because the tests differ. The percentile gap tells the story: 59 versus 9.

The Verdict

The data indicates a clear performance hierarchy between these two products. The AMD Radeon PRO W7500 is a discrete workstation GPU with a 59th percentile ranking and an average score of 16415. The Intel Arc B390 is an integrated graphics processor with a 9th percentile ranking and an average score of 1482. Any user selecting between them based on raw benchmark performance should choose the W7500, as its recorded scores are an order of magnitude higher.

The W7500 targets workloads that require sustained compute throughput, given its strong Geekbench OpenCL and Vulkan results. The Arc B390, by contrast, shows results typical of an entry-level integrated solution, with its nearest rivals being older NVIDIA mobile and OEM parts. The delta percentages against those rivals are small, meaning the Arc B390 does not dramatically outperform even those low-end parts.

For workstation use, the W7500's benchmark profile supports tasks like GPU compute, rendering, and API-heavy applications. The Arc B390's single benchmark result does not demonstrate capability in those areas. The database shows no scenario where the Arc B390 wins a head-to-head comparison, as the wins counter for both products is zero due to the absence of shared tests.

Architecture Differences

The two products come from different manufacturers and use fundamentally different architectures. The AMD Radeon PRO W7500 is built on RDNA 3.0, with the chip codename Navi 33 and the internal codename Hotpink Bonefish. It belongs to the Radeon Pro Navi generation, specifically the Navi III Series. The process node is 6 nm, fabricated by TSMC, with 13,300 million transistors on a die size of 204 mm². The transistor density is 65.2 million per square millimeter.

The Intel Arc B390 uses the Xe3-LPG architecture with the chip codename Panther Lake. It belongs to the Arc Graphics-M generation, also labeled Panther Lake. The process node is 3 nm, fabricated by Intel. Transistor count, die size, and transistor density are listed as unknown in the database, so no numerical comparison is possible for those fields.

The W7500 is a discrete GPU with a single-slot form factor and no power connectors, drawing a TDP of 70 W with a suggested PSU of 250 W. The Arc B390 is an integrated graphics processor (IGP) with a TDP of 80 W, no power connectors, and no suggested PSU listed. The bus interface differs as well: the W7500 uses PCIe 4.0 x8, while the Arc B390 uses IGP, meaning it connects through the processor rather than a dedicated slot.

Display outputs also diverge. The W7500 provides 4x DisplayPort 2.1, while the Arc B390's outputs are listed as portable device dependent, reflecting its integrated nature. The W7500 has physical dimensions of 216 mm length, 115 mm height, and 20 mm width. The Arc B390 has no recorded dimensions.

Both products share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The W7500 supports PCIe 4.0 x8, while the Arc B390 uses an integrated interface, which limits its bandwidth compared to a dedicated slot.

Specification Differences

The W7500 has 1792 shading units, 112 texture mapping units, and 64 render output units. It includes 28 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, and 24 ROPs, with 12 ray tracing cores. These differences indicate the W7500 has more parallel processing resources across every category.

Clock speeds differ significantly. The W7500 has a base clock of 1500 MHz and a boost clock of 1700 MHz. The Arc B390 has a much lower base clock of 300 MHz but a higher boost clock of 2500 MHz. Memory clocks also differ: the W7500 runs at 2000 MHz with 16 Gbps effective, while the Arc B390 uses system shared memory with no dedicated clock.

Memory configuration is a major differentiator. The W7500 has 8 GB of GDDR6 memory on a 128-bit bus, delivering 256.0 GB/s of bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth, meaning its performance scales with the host system's memory configuration.

Pixel and texture rates reflect the compute resource differences. The W7500 achieves 108.8 GPixel/s and 190.4 GTexel/s. The Arc B390 achieves 60.00 GPixel/s and 120.0 GTexel/s. Floating point performance also favors the W7500: 12.19 TFLOPS FP32 and 24.37 TFLOPS FP16 (2:1), versus the Arc B390's 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1).

Power characteristics are close. The W7500 has a TDP of 70 W, while the Arc B390 has a TDP of 80 W. The W7500 requires a 250 W suggested PSU, while the Arc B390 lists no suggested PSU. The W7500 is a single-slot card, while the Arc B390 is an IGP. Release dates differ: the W7500 launched on 2023-08-02, and the Arc B390 launched on 2026-01-26. The W7500 has a launch MSRP of 429 USD, while the Arc B390 has no recorded launch MSRP.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The AMD Radeon PRO W7500 has an average score of 16415, while the Intel Arc B390 has an average score of 1482.

Q: How do the two GPUs rank against all other GPUs in the database?

A: The W7500 sits at the 59th percentile, while the Arc B390 sits at the 9th percentile.

Q: What is the closest competitor to the W7500 by average score?

A: The NVIDIA RTX PRO 6000 Blackwell matches the W7500 with a delta of 0 percent, at an average score of 16408.

Q: What is the closest competitor to the Arc B390 by average score?

A: The NVIDIA GeForce GT 520MX is the nearest rival, with an average score of 1463, which is 1.3 percent behind the Arc B390.

Q: Which GPU has more ray tracing cores?

A: The W7500 has 28 ray tracing cores, while the Arc B390 has 12.

Q: Which GPU has higher FP32 performance?

A: The W7500 delivers 12.19 TFLOPS FP32, while the Arc B390 delivers 7.680 TFLOPS FP32.

Where Each One Wins

The AMD Radeon PRO W7500 wins in every category where the database provides comparable data. Its average benchmark score of 16415 versus 1482 makes it the dominant performer overall. It holds the advantage in shading units (1792 versus 1536), texture mapping units (112 versus 48), render output units (64 versus 24), and ray tracing cores (28 versus 12). Its pixel rate of 108.8 GPixel/s and texture rate of 190.4 GTexel/s are both higher than the Arc B390's 60.00 GPixel/s and 120.0 GTexel/s. Floating point throughput is also higher on the W7500, with 12.19 TFLOPS FP32 versus 7.680 TFLOPS.

The W7500 also wins on memory. It has dedicated 8 GB of GDDR6 with 256.0 GB/s bandwidth, while the Arc B390 relies on system shared memory with system dependent bandwidth. This makes the W7500 more suitable for memory-intensive workloads such as large compute tasks and high-resolution rendering. Its PCIe 4.0 x8 interface provides a dedicated connection, whereas the Arc B390's IGP bus is integrated into the processor.

The Intel Arc B390 wins on process node efficiency, using a 3 nm process from Intel compared to the W7500's 6 nm process from TSMC. It also has a higher boost clock at 2500 MHz versus the W7500's 1700 MHz, though its base clock is much lower at 300 MHz versus 1500 MHz. The Arc B390 has a lower TDP of 80 W versus 70 W? No, the Arc B390 has an 80 W TDP and the W7500 has a 70 W TDP, so the W7500 actually draws less power. The Arc B390 has no distinct advantage in power consumption.

The Arc B390's integrated nature means it requires no separate card slot and has no physical dimensions recorded, making it suitable for compact portable devices. Its display outputs are portable device dependent, which fits a mobile or embedded use case. However, based strictly on benchmark scores, the W7500 is the clear winner in computational performance. The Arc B390's only recorded benchmark, 3DMark Steel Nomad DX12 at 1482, places it near the bottom of the database, while the W7500 sits comfortably in the upper half.

For users prioritizing compute throughput, workstation tasks, or any GPU-accelerated workload, the W7500 is the only viable choice between the two. For users who need an integrated GPU with no discrete card and can accept low-end performance, the Arc B390 exists as an option, but the data shows it delivers only a fraction of the W7500's capability.

DETAILED SPECIFICATIONS

SPECIFICATION
PRO W7500
B390
Core Specs
Shading Units
1,792
1,536 -14.3%
Shaders
1,792
1,536 -14.3%
TMUs
112
48 -57.1%
ROPs
64
24 -62.5%
Compute Units
28
Execution Units
12
Clocks
Base Clock
1500 MHz
300 MHz
Boost Clock
1700 MHz
2500 MHz
Memory Clock
2000 MHz 16 Gbps effective
System Shared
Memory
Memory Size
8 GB
System Shared
VRAM (MB)
8,192
Memory Type
GDDR6
System Shared
Memory Bus
128 bit
System Shared
Bandwidth
256.0 GB/s
System Dependent
Cache
L1 Cache
128 KB per Array
64 KB (per EU)
L2 Cache
2 MB
16 MB
L3 Cache
32 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
108.8 GPixel/s
60.00 GPixel/s
Texture Rate
190.4 GTexel/s
120.0 GTexel/s
FP32 (TFLOPS)
12.19 TFLOPS
7.680 TFLOPS
FP64 (TFLOPS)
380.8 GFLOPS (1:32)
960.0 GFLOPS (1:8)
FP16 (TFLOPS)
24.37 TFLOPS (2:1)
15.36 TFLOPS (2:1)
AI/RT
RT Cores
28
12 -57.1%
XMX Cores
96
Matrix Cores
56
Power
TDP
70 W
80 W
TDP (W)
70
80 +14.3%
Suggested PSU
250 W
Power Connectors
None
None
Architecture
Architecture
RDNA 3.0
Xe3-LPG
GPU Name
Navi 33
Panther Lake
Codename
Hotpink Bonefish
Generation
Radeon Pro Navi (Navi III Series)
Arc Graphics-M (Panther Lake)
Process Size
6 nm
3 nm
Transistors
13,300 million
unknown
Die Size
204 mm²
unknown
Foundry
TSMC
Intel
Density
65.2M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.2
3.0
Shader Model
6.8
6.9
Physical
Slot Width
Single-slot
IGP
Length
216 mm 8.5 inches
Height
115 mm 4.5 inches
Outputs
4x DisplayPort 2.1
Portable Device Dependent
Bus Interface
PCIe 4.0 x8
IGP
Other
Launch Price
429 USD
Production
Active
Active
Predecessor
Radeon Pro Vega
View Radeon PRO W7500 Details View Arc B390 Details