Intel Arc B370 vs NVIDIA GeForce RTX 5090 D Comparison
Intel Arc B370
GeForce RTX 5090 D
PERFORMANCE BENCHMARKS
Analysis: Intel Arc B370 vs NVIDIA GeForce RTX 5090 D
The Intel Arc B370 and NVIDIA GeForce RTX 5090 D occupy opposite extremes of the GPU performance spectrum. The recorded database measurements place the Arc B370 at the 5th percentile among all GPUs, while the RTX 5090 D sits at the 92nd percentile. The single shared benchmark, 3DMark Steel Nomad DX12, shows the RTX 5090 D scoring 14,326 points against 1,184 points for the Arc B370, a delta of -91.7% from the NVIDIA part’s perspective. The data indicates a decisive performance gap, but the two products serve fundamentally different purposes, as their architecture and physical characteristics reveal.
The Verdict
The benchmark data presents a clear hierarchy. The NVIDIA GeForce RTX 5090 D wins the only head-to-head test available, 3DMark Steel Nomad DX12, with a score of 14,326 versus 1,184 for the Intel Arc B370. That represents a 91.7% lead for the NVIDIA part. The RTX 5090 D also holds an average benchmark score of 77,712 across all recorded tests, while the Arc B370 averages just 1,184. This places the Arc B370 near the bottom of the database, at the 5th percentile, meaning 95% of all GPUs score higher. The RTX 5090 D, at the 92nd percentile, outperforms the vast majority of the field.
The Arc B370’s nearest rivals in the database are ATI Mobility Radeon HD 5570 (average score 1,186, delta -0.2%), ATI Radeon HD 5770 (1,190, -0.5%), AMD Radeon HD 7650M (1,192, -0.7%), and AMD FirePro M2000 (1,168, +1.4%). These deltas are tiny, confirming the Arc B370 clusters with decade-old mobile and entry desktop parts. The RTX 5090 D’s nearest rivals are AMD Radeon RX 6650M XT (76,904, +1.1%), AMD Radeon RX 6850M XT (78,940, -1.6%), NVIDIA Tesla P100 PCIe 12 GB (79,396, -2.1%), and NVIDIA Tesla P100 PCIe 16 GB (79,605, -2.4%). The RTX 5090 D sits within a few percentage points of these high-end parts.
For a user selecting between these two, the data leaves no ambiguity. The RTX 5090 D delivers over twelve times the 3DMark Steel Nomad score. It is the only choice for any workload requiring substantial graphics compute. The Arc B370, with its 25 W power envelope and integrated design, fits scenarios where low power consumption and a compact footprint matter more than performance. The RTX 5090 D requires a 950 W suggested PSU, a dual-slot cooler, and a PCIe 5.0 x16 interface, while the Arc B370 uses no power connectors and connects via IGP. These are not competing products; they are answers to different questions.
Architecture Differences
The two GPUs share no architectural lineage. The Intel Arc B370 uses the Panther Lake chip with Xe3-LPG architecture, built on a 3 nm process at Intel. It belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA GeForce RTX 5090 D uses the GB202 chip with Blackwell 2.0 architecture, fabricated on a 5 nm process at TSMC. The RTX 5090 D has 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9M per mm². The Arc B370’s transistor count and die size are listed as unknown in the database.
Compute resources differ by an order of magnitude. The Arc B370 has 1,280 shading units, 40 texture mapping units, 20 render output units, and 10 ray tracing cores. The RTX 5090 D has 21,760 shading units, 680 TMUs, 176 ROPs, and 170 ray tracing cores. The NVIDIA part also includes 680 tensor cores, a feature the Arc B370 does not list. Pixel rate for the Arc B370 is 48.00 GPixel/s, while the RTX 5090 D achieves 423.6 GPixel/s. Texture rate stands at 96.00 GTexel/s for Intel versus 1,636.8 GTexel/s for NVIDIA.
FP32 compute shows a 17x gap: 6.144 TFLOPS for the Arc B370 versus 104.8 TFLOPS for the RTX 5090 D. FP16 performance differs in ratio as well. The Arc B370 delivers 12.29 TFLOPS at a 2:1 ratio, while the RTX 5090 D delivers 104.8 TFLOPS at a 1:1 ratio, meaning no FP16 advantage over FP32 on the NVIDIA part.
Memory architecture is fundamentally different. The Arc B370 uses system shared memory, with type, bus width, and bandwidth all marked as system dependent. The RTX 5090 D has 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s bandwidth. Memory clock for the NVIDIA part is 1750 MHz with 28 Gbps effective. The Arc B370’s base clock is 300 MHz with a 2400 MHz boost; the RTX 5090 D runs at 2017 MHz base and 2407 MHz boost.
Power and physical specs reinforce the split. The Arc B370 has a 25 W TDP, is an integrated graphics processor (IGP), and requires no power connectors. The RTX 5090 D has a 575 W TDP, uses a dual-slot cooler, requires one 16-pin connector, and measures 304 mm by 137 mm by 48 mm. The Arc B370’s display outputs are portable device dependent; the RTX 5090 D offers 1x HDMI 2.1b and 3x DisplayPort 2.1b.
Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Release dates differ: the Arc B370 launched on 2026-01-26, while the RTX 5090 D launched on 2025-01-29. The RTX 5090 D has a listed predecessor (GeForce 40) and successor (GeForce 60); the Arc B370 lists none.
Where Each One Wins
The RTX 5090 D wins the only direct comparison in the database. In 3DMark Steel Nomad DX12, it scores 14,326 against the Arc B370’s 1,184. That single result dominates the head-to-head tally, which shows one win for NVIDIA and zero for Intel.
Beyond that test, the RTX 5090 D’s other benchmark results illustrate its breadth. It scores 310,674 in Geekbench OpenCL and 376,915 in Geekbench Vulkan. In PassMark tests, it records 44,065 in G3D, 28,396 in GPU Compute, 1,487 in G2D, and 434 in DirectX 9. The Arc B370 has no scores for any of these tests in the database, so no direct comparison exists outside the single 3DMark result.
The Arc B370’s wins are not in raw performance but in physical characteristics. Its 25 W TDP versus 575 W for the RTX 5090 D means the Intel part consumes 23 times less power. It needs no power connector, no external cooler beyond the integrated design, and no PCIe slot, as it is an IGP. The RTX 5090 D requires a 950 W suggested PSU and a dual-slot physical footprint. For portable devices, the Arc B370’s display outputs are device dependent, which suits integrated designs. The RTX 5090 D cannot operate in such a form factor given its dimensions and power requirements.
The data also shows the RTX 5090 D has a higher transistor density and a larger die, but the Arc B370 uses a smaller process node (3 nm versus 5 nm). This does not translate into performance parity; the NVIDIA part’s massive resource count overrides the process advantage. The Arc B370’s nearest rivals all score within 1.4% of its average, indicating it sits in a performance band far below the RTX 5090 D’s neighborhood.
FAQ
Q: Which GPU has the higher 3DMark Steel Nomad DX12 score?
A: The NVIDIA GeForce RTX 5090 D scores 14,326, while the Intel Arc B370 scores 1,184. The NVIDIA part leads by 91.7%.
Q: How do their power requirements compare?
A: The Intel Arc B370 has a 25 W TDP and uses no power connectors. The NVIDIA GeForce RTX 5090 D has a 575 W TDP and requires one 16-pin connector, with a suggested PSU of 950 W.
Q: What memory configurations do they use?
A: The Arc B370 uses system shared memory with system dependent bandwidth. The RTX 5090 D has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth.
Q: Are their API supports the same?
A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
Q: What are their release dates?
A: The Intel Arc B370 was released on 2026-01-26. The NVIDIA GeForce RTX 5090 D was released on 2025-01-29.
Q: How do their shading unit counts compare?
A: The Arc B370 has 1,280 shading units. The RTX 5090 D has 21,760 shading units, which is 17 times more.
Head-to-Head Benchmarks
The database contains exactly one shared benchmark between the two GPUs: 3DMark Steel Nomad DX12. The RTX 5090 D scores 14,326 points. The Arc B370 scores 1,184 points. The delta percentage from the NVIDIA part’s perspective is -91.7%, meaning the Intel GPU delivers only 8.3% of the NVIDIA score. This is the largest possible single-test gap recorded in the head-to-head section.
The RTX 5090 D’s average benchmark score of 77,712 across all its tests dwarfs the Arc B370’s average of 1,184. The NVIDIA part’s percentile rank of 92 versus the Intel part’s rank of 5 quantifies the distance. In the nearest rivals data, the Arc B370’s closest competitor, the ATI Mobility Radeon HD 5570, scores 1,186, just 0.2% above the Intel part. The RTX 5090 D’s closest rival, the AMD Radeon RX 6650M XT, scores 76,904, which is 1.1% above the NVIDIA part. The RTX 5090 D also trails the AMD Radeon RX 6850M XT by 1.6%, the NVIDIA Tesla P100 PCIe 12 GB by 2.1%, and the NVIDIA Tesla P100 PCIe 16 GB by 2.4%. These small deltas show the RTX 5090 D is competitive with top-tier laptop and workstation parts, while the Arc B370 matches only legacy entry-level GPUs.
The Geekbench and PassMark results for the RTX 5090 D provide additional context for its compute capabilities. A Geekbench OpenCL score of 310,674 and a Vulkan score of 376,915 indicate strong general-purpose and graphics workloads. PassMark GPU Compute at 28,396 reinforces the compute orientation. The Arc B370 has no such scores, so these figures stand alone as evidence of the NVIDIA part’s breadth.
The pixel rate comparison tells a similar story. The RTX 5090 D’s 423.6 GPixel/s is 8.8 times the Arc B370’s 48.00 GPixel/s. Texture rate is 17 times higher at 1,636.8 GTexel/s versus 96.00 GTexel/s. FP32 compute is 17 times higher. These ratios align closely with the shading unit disparity, confirming the architectural scaling.
The physical comparison remains stark. The RTX 5090 D’s 92,200 million transistors on a 750 mm² die with a 122.9M per mm² density represents a flagship-class component. The Arc B370’s transistor count is unknown, but its 3 nm process and 25 W TDP indicate a low-power integrated design. The RTX 5090 D’s 304 mm length and dual-slot width require a full desktop chassis; the Arc B370’s IGP bus interface fits inside a processor package. The database records no dimensions for the Arc B370, as it is not a discrete card.
The 3DMark Steel Nomad result is the sole direct numerical comparison, and it leaves no room for interpretation. The RTX 5090 D outperforms the Arc B370 by a factor of 12.1. All other data, including percentiles, average scores, and architectural specifications, corroborates this gap. For any benchmark-driven selection, the RTX 5090 D is the clear performance leader, while the Arc B370’s advantages lie entirely in power efficiency and integration, not in measured speed.