AMD Radeon PRO W7700 vs Intel Arc B370 Comparison

AMD
RADEON

AMD Radeon PRO W7700

CORE STATE Navi 32
VRAM 16 GB
CLOCK SPEED 2600 MHz
TDP 190 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 5 nm
LAUNCH DATE 2023
VS
Intel
GPU

Arc 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

PERFORMANCE BENCHMARKS

geekbench_opencl
108,245
N/A
geekbench_vulkan
129,706
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
1,184

Analysis: AMD Radeon PRO W7700 vs Intel Arc B370

Head-to-Head Benchmarks

The recorded data for these two GPUs is starkly asymmetrical, with each part measured by a different benchmark suite. The AMD Radeon PRO W7700 delivers results from Geekbench OpenCL and Vulkan testing, while the Intel Arc B370 has a single 3DMark Steel Nomad DX12 score. Direct head-to-head comparisons are therefore limited to the database’s overall average benchmark score, where the gap is dramatic.

The AMD Radeon PRO W7700 posts an average benchmark score of 118,976. That places it in the 95th percentile among all GPUs in the database. Its nearest rivals are all professional or data center parts: the NVIDIA GB10 scores 117,393, a delta of 1.3% behind; the NVIDIA RTX 4000 SFF Ada Generation scores 117,088, a 1.6% gap; the NVIDIA Tesla V100 SXM2 16 GB scores 114,395, trailing by 4%; and the NVIDIA RTX A5500 Mobile scores 113,944, 4.4% behind. The W7700 outperforms all four of these directly comparable parts, with the margin ranging from just over one percent against the GB10 to nearly four and a half percent against the RTX A5500 Mobile.

The Intel Arc B370’s average benchmark score is 1,184, which sits in the 5th percentile of all GPUs. Its nearest rivals are legacy or low-end parts: the ATI Mobility Radeon HD 5570 scores 1,186, a delta of -0.2% relative to the B370; the ATI Radeon HD 5770 scores 1,190, a -0.5% delta; the AMD Radeon HD 7650M scores 1,192, a -0.7% delta; and the AMD FirePro M2000 scores 1,168, a 1.4% delta. The B370 is effectively at parity with these older parts, with deltas under one percent in either direction for three of them and a 1.4% lead over the FirePro M2000.

The raw score difference between the two parts is enormous: 118,976 versus 1,184. The W7700 is roughly 100 times higher in average benchmark score. However, these numbers come from different test suites, so the comparison should be read as indicative of overall performance class rather than a direct per-test measurement. Still, the percentile placements tell a clear story: the W7700 ranks in the top 5% of all GPUs, while the B370 ranks in the bottom 5%. The W7700’s individual scores are 108,245 in Geekbench OpenCL and 129,706 in Geekbench Vulkan, both far above the B370’s single 3DMark Steel Nomad score of 1,184.

In the database’s head-to-head benchmark field, neither part records a win over the other, as no common test was run on both. The wins tally shows zero for each side. The practical interpretation is that the W7700 occupies a professional workstation tier, while the B370 is an integrated graphics solution in a mobile processor. Their performance envelopes do not overlap.

The Verdict

The data indicates that the AMD Radeon PRO W7700 is the far more capable GPU in absolute performance terms. Its average benchmark score of 118,976 versus 1,184 for the Intel Arc B370, along with its 95th versus 5th percentile ranking, leaves no ambiguity about which part delivers higher throughput. The W7700 also leads in every measured compute specification: 31.95 TFLOPS FP32 versus 6.144 TFLOPS, 63.90 TFLOPS FP16 versus 12.29 TFLOPS, 249.6 GPixel/s versus 48.00 GPixel/s, and 499.2 GTexel/s versus 96.00 GTexel/s.

The Intel Arc B370 is not a competitor to the W7700 in any benchmark-driven sense. It is an integrated GPU (IGP) with system-shared memory, designed for portable devices, and its performance aligns with graphics parts from roughly a decade earlier. The B370’s nearest rivals include the ATI Radeon HD 5770 and the AMD Radeon HD 7650M, all within a one percent delta. The W7700’s nearest rivals are current-generation NVIDIA professional GPUs, and it beats each of them by at least 1.3%.

For a user selecting a discrete workstation GPU, the W7700 is the only viable choice between these two. For a user selecting an integrated mobile graphics solution, the B370 is the only applicable option, as the W7700 is a dual-slot, 190 W discrete card with a 1x 8-pin power connector. The two parts serve entirely different product categories. The database does not record a scenario where the B370 outperforms the W7700 in any metric.

Where Each One Wins

The AMD Radeon PRO W7700 wins in every recorded performance category. Its Geekbench OpenCL score of 108,245 and Vulkan score of 129,706 are the only two benchmark results for the part, and both are extremely high relative to all GPUs. Its average score of 118,976 places it above the NVIDIA GB10, RTX 4000 SFF Ada, Tesla V100 SXM2, and RTX A5500 Mobile. In raw throughput, it leads the B370 by factors of 5.2 in FP32, 5.2 in FP16, 5.2 in pixel rate, and 5.2 in texture rate. The W7700 also has 16 GB of dedicated GDDR6 memory with a 256-bit bus and 576.0 GB/s bandwidth, compared to the B370’s system-shared memory with system-dependent bandwidth.

The Intel Arc B370 wins in the categories of power efficiency and physical integration. Its TDP is 25 W versus 190 W, it requires no power connectors, and it is an IGP rather than a dual-slot card. The B370 is manufactured on a 3 nm process from Intel, while the W7700 uses a 5 nm TSMC process, which gives the B370 a process-node advantage in density and power characteristics. The B370 also has a production status of Active, while the W7700’s production status is not recorded in the database. The B370’s base clock of 300 MHz is lower than the W7700’s 1900 MHz, but its boost clock of 2400 MHz approaches the W7700’s 2600 MHz. These clock differences do not translate into performance wins for the B370.

The B370’s single benchmark result, 3DMark Steel Nomad DX12 at 1,184, does not beat any W7700 result. The use case split is therefore clean: the W7700 is for compute-heavy workstation tasks requiring high FP32, FP16, pixel, and texture throughput, while the B370 is for battery-conscious portable devices where an integrated GPU with shared memory is acceptable.

FAQ

Q: How does the AMD Radeon PRO W7700 compare to the Intel Arc B370 in average benchmark score?

A: The W7700 has an average benchmark score of 118,976, while the B370 has an average score of 1,184. The W7700 ranks in the 95th percentile of all GPUs, and the B370 ranks in the 5th percentile.

Q: What is the FP32 compute performance of each GPU?

A: The AMD Radeon PRO W7700 delivers 31.95 TFLOPS FP32, and the Intel Arc B370 delivers 6.144 TFLOPS FP32. The W7700 is approximately 5.2 times higher in this metric.

Q: What memory configurations do the two GPUs use?

A: The W7700 has 16 GB of GDDR6 memory with a 256-bit bus and 576.0 GB/s bandwidth. The B370 uses system-shared memory with a system-shared type, bus width, and system-dependent bandwidth.

Q: Which GPU has a higher pixel rate?

A: The W7700 has a pixel rate of 249.6 GPixel/s, and the B370 has a pixel rate of 48.00 GPixel/s. The W7700 is about 5.2 times faster.

Q: What are the power consumption figures?

A: The W7700 has a TDP of 190 W and requires a 1x 8-pin power connector with a suggested PSU of 450 W. The B370 has a TDP of 25 W, uses no power connectors, and is an IGP.

Q: How do their nearest rivals compare?

A: The W7700’s nearest rival is the NVIDIA GB10 with an average score of 117,393, a 1.3% delta. The B370’s nearest rival is the ATI Mobility Radeon HD 5570 with an average score of 1,186, a -0.2% delta.

Architecture Differences

The AMD Radeon PRO W7700 uses the Navi 32 chip based on RDNA 3.0 architecture, with the codename Wheat Nas. It belongs to the Radeon Pro Navi (Navi III Series) generation. The chip is fabricated on a 5 nm process at TSMC, containing 28,100 million transistors on a 346 mm² die, yielding a transistor density of 81.2M per mm².

The Intel Arc B370 uses the Panther Lake chip based on Xe3-LPG architecture, with no recorded codename. It belongs to the Arc Graphics-M (Panther Lake) generation. The chip is fabricated on a 3 nm process at Intel, with transistor count and die size listed as unknown in the database.

Compute unit counts differ significantly. The W7700 has 3,072 shading units, 192 texture mapping units, 96 raster operation units, and 48 ray tracing cores. The B370 has 1,280 shading units, 40 TMUs, 20 ROPs, and 10 ray tracing cores. The W7700 has 2.4 times the shading units, 4.8 times the TMUs, 4.8 times the ROPs, and 4.8 times the RT cores.

Clock behavior also differs. The W7700 has a base clock of 1900 MHz and a boost clock of 2600 MHz, with memory clocked at 2250 MHz (18 Gbps effective). The B370 has a base clock of 300 MHz and a boost clock of 2400 MHz, with memory clock listed as System Shared.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither has tensor cores listed in the database. The W7700 uses a PCIe 4.0 x16 bus interface, while the B370 uses an IGP bus interface. The W7700 has 4x DisplayPort 2.1 outputs, while the B370’s display outputs are listed as Portable Device Dependent.

Specification Differences

The following fields differ between the two GPUs according to the database:

  • Process Node: The W7700 uses 5 nm from TSMC; the B370 uses 3 nm from Intel.
  • Transistors: The W7700 has 28,100 million; the B370 is unknown.
  • Die Size: The W7700 is 346 mm²; the B370 is unknown.
  • Transistor Density: The W7700 is 81.2M / mm²; the B370 is not recorded.
  • Base Clock: The W7700 is 1900 MHz; the B370 is 300 MHz.
  • Boost Clock: The W7700 is 2600 MHz; the B370 is 2400 MHz.
  • Memory Clock: The W7700 is 2250 MHz (18 Gbps effective); the B370 is System Shared.
  • Memory Size: The W7700 is 16 GB; the B370 is System Shared.
  • Memory Type: The W7700 is GDDR6; the B370 is System Shared.
  • Memory Bus Width: The W7700 is 256 bit; the B370 is System Shared.
  • Memory Bandwidth: The W7700 is 576.0 GB/s; the B370 is System Dependent.
  • Shading Units: The W7700 has 3,072; the B370 has 1,280.
  • TMUs: The W7700 has 192; the B370 has 40.
  • ROPs: The W7700 has 96; the B370 has 20.
  • RT Cores: The W7700 has 48; the B370 has 10.
  • Pixel Rate: The W7700 is 249.6 GPixel/s; the B370 is 48.00 GPixel/s.
  • Texture Rate: The W7700 is 499.2 GTexel/s; the B370 is 96.00 GTexel/s.
  • FP32: The W7700 is 31.95 TFLOPS; the B370 is 6.144 TFLOPS.
  • FP16: The W7700 is 63.90 TFLOPS (2:1); the B370 is 12.29 TFLOPS (2:1).
  • TDP: The W7700 is 190 W; the B370 is 25 W.
  • Slot Width: The W7700 is Dual-slot; the B370 is IGP.
  • Power Connectors: The W7700 is 1x 8-pin; the B370 is None.
  • Suggested PSU: The W7700 is 450 W; the B370 is not recorded.
  • Bus Interface: The W7700 is PCIe 4.0 x16; the B370 is IGP.
  • Display Outputs: The W7700 is 4x DisplayPort 2.1; the B370 is Portable Device Dependent.
  • Dimensions: The W7700 is 241 mm (9.5 inches) long and 111 mm (4.4 inches) high; the B370 has no recorded dimensions.
  • Production Status: The W7700 is not recorded; the B370 is Active.
  • Release Date: The W7700 is 2023-11-12; the B370 is 2026-01-26.
  • Launch MSRP: The W7700 is 999 USD; the B370 has none recorded.
  • Predecessor: The W7700’s predecessor is Radeon Pro Vega; the B370 has none recorded.
  • Benchmark Scores: The W7700 has Geekbench OpenCL 108,245 and Vulkan 129,706; the B370 has 3DMark Steel Nomad DX12 1,184.
  • Percentile: The W7700 is 95; the B370 is 5.
  • Average Benchmark Score: The W7700 is 118,976; the B370 is 1,184.

DETAILED SPECIFICATIONS

SPECIFICATION
PRO W7700
B370
Core Specs
Shading Units
3,072
1,280 -58.3%
Shaders
3,072
1,280 -58.3%
TMUs
192
40 -79.2%
ROPs
96
20 -79.2%
Compute Units
48
Execution Units
10
Clocks
Base Clock
1900 MHz
300 MHz
Boost Clock
2600 MHz
2400 MHz
Memory Clock
2250 MHz 18 Gbps effective
System Shared
Memory
Memory Size
16 GB
System Shared
VRAM (MB)
16,384
Memory Type
GDDR6
System Shared
Memory Bus
256 bit
System Shared
Bandwidth
576.0 GB/s
System Dependent
Cache
L1 Cache
128 KB per Array
64 KB (per EU)
L2 Cache
2 MB
16 MB
L3 Cache
64 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
249.6 GPixel/s
48.00 GPixel/s
Texture Rate
499.2 GTexel/s
96.00 GTexel/s
FP32 (TFLOPS)
31.95 TFLOPS
6.144 TFLOPS
FP64 (TFLOPS)
998.4 GFLOPS (1:32)
768.0 GFLOPS (1:8)
FP16 (TFLOPS)
63.90 TFLOPS (2:1)
12.29 TFLOPS (2:1)
AI/RT
RT Cores
48
10 -79.2%
XMX Cores
80
Matrix Cores
96
Power
TDP
190 W
25 W
TDP (W)
190
25 -86.8%
Suggested PSU
450 W
Power Connectors
1x 8-pin
None
Architecture
Architecture
RDNA 3.0
Xe3-LPG
GPU Name
Navi 32
Panther Lake
Codename
Wheat Nas
Generation
Radeon Pro Navi (Navi III Series)
Arc Graphics-M (Panther Lake)
Process Size
5 nm
3 nm
Transistors
28,100 million
unknown
Die Size
346 mm²
unknown
Foundry
TSMC
Intel
Density
81.2M / 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
Dual-slot
IGP
Length
241 mm 9.5 inches
Height
111 mm 4.4 inches
Outputs
4x DisplayPort 2.1
Portable Device Dependent
Bus Interface
PCIe 4.0 x16
IGP
Other
Launch Price
999 USD
Production
Active
Predecessor
Radeon Pro Vega
View Radeon PRO W7700 Details View Arc B370 Details