Intel Arc B390 vs NVIDIA GeForce RTX 5080 Comparison
Intel Arc B390
GeForce RTX 5080
PERFORMANCE BENCHMARKS
Analysis: Intel Arc B390 vs NVIDIA GeForce RTX 5080
FAQ
Q: How do the two GPUs compare in the recorded 3DMark Steel Nomad DX12 benchmark?
A: The NVIDIA GeForce RTX 5080 scored 8,637, while the Intel Arc B390 scored 1,482. This represents a delta of -82.8% for the Intel part relative to the NVIDIA card.
Q: What is the average benchmark score for each GPU in the database?
A: The Intel Arc B390 has an average benchmark score of 1,482, based solely on its single 3DMark result. The NVIDIA GeForce RTX 5080 has an average benchmark score of 56,083, computed across ten recorded tests including 3DMark Steel Nomad, Geekbench OpenCL, Geekbench Vulkan, and multiple Passmark tests.
Q: How does each GPU rank relative to all other GPUs in the database?
A: The Intel Arc B390 sits at the 9th percentile of all GPUs, which places it near the performance level of the NVIDIA GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710. The RTX 5080 sits at the 87th percentile, with closest rivals being the AMD Radeon 8060S, Radeon RX 6750 GRE 12 GB, Radeon Pro W5700X, and Radeon RX 9070 GRE.
Q: What are the nearest rivals for the Intel Arc B390 according to the recorded data?
A: The closest recorded rivals are the NVIDIA GeForce GT 520MX (1.3% faster), NVIDIA GeForce 800M (1.5% faster), NVIDIA GeForce GT 625 OEM (2.5% faster), and NVIDIA GeForce GT 710 (2.7% faster). All of these are within a few percentage points of the Arc B390's score.
Q: What are the nearest rivals for the NVIDIA GeForce RTX 5080 according to the recorded data?
A: The closest recorded rivals are the AMD Radeon 8060S (0.6% faster), AMD Radeon RX 6750 GRE 12 GB (0.7% faster), AMD Radeon Pro W5700X (2.3% faster), and AMD Radeon RX 9070 GRE (2.2% slower). The RTX 5080 is essentially at parity with these cards in the aggregate.
Q: What is the recorded launch MSRP for the NVIDIA GeForce RTX 5080?
A: The launch MSRP is 999 USD. No launch MSRP is recorded for the Intel Arc B390.
The Verdict
The recorded database entries describe two GPUs that do not occupy the same performance tier. The Intel Arc B390 is an integrated graphics processor with a 3DMark Steel Nomad score of 1,482, placing it at the 9th percentile of all GPUs. Its nearest rivals are legacy NVIDIA parts from the GT 500, 800M, and GT 600/700 series. The NVIDIA GeForce RTX 5080 is a discrete add-in card with a 3DMark Steel Nomad score of 8,637, an 87th percentile ranking, and an average benchmark score of 56,083 across ten tests.
The data indicates that the RTX 5080 is the appropriate choice for any workload that depends on raw graphics throughput, ray tracing, or compute performance. The Arc B390, by contrast, is positioned for systems where the GPU is integrated into the processor and no separate graphics card is used. The 80 W TDP of the Arc B390 and its IGP form factor make it suitable for compact or low-power platforms, while the RTX 5080's 360 W TDP, dual-slot cooler, and 16-pin power connector require a full desktop build with a 750 W suggested PSU.
The verdict from the data is straightforward: the RTX 5080 is the only choice for high-performance rendering and compute, while the Arc B390 is a functional integrated solution whose benchmark position is far below the discrete card. There is no scenario in the recorded data where the two compete for the same buyer.
Head-to-Head Benchmarks
The database contains a single head-to-head comparison between the two GPUs: 3DMark Steel Nomad DX12. In that test, the NVIDIA GeForce RTX 5080 scored 8,637, and the Intel Arc B390 scored 1,482. The delta is -82.8% for the Intel part, meaning the RTX 5080 delivers roughly 5.8 times the score of the Arc B390 in this workload.
The RTX 5080's average benchmark score of 56,083, when compared to the Arc B390's 1,482, shows a gap that persists across the full set of recorded tests. The RTX 5080 also posts additional results that the Arc B390 does not have in the database, including a Geekbench OpenCL score of 235,901, a Geekbench Vulkan score of 255,450, and Passmark scores of 36,565 in G3D and 21,789 in GPU Compute. These results reinforce the dominance of the RTX 5080 in every measured dimension.
The Arc B390's only recorded result is the 3DMark Steel Nomad score. Its nearest rivals in that test, the GT 520MX at 1,463, the GeForce 800M at 1,460, the GT 625 OEM at 1,446, and the GT 710 at 1,443, are all within 2.7% of the Arc B390's score. This places the Arc B390 in a performance band that is far removed from the RTX 5080's neighborhood, where the closest competitor, the AMD Radeon RX 9070 GRE, is only 2.2% faster than the RTX 5080.
Specification Differences
The two GPUs differ in nearly every fundamental specification. The Intel Arc B390 uses system shared memory, with a memory bus and bandwidth that are also system dependent. The NVIDIA GeForce RTX 5080 uses 16 GB of GDDR7 memory on a 256-bit bus with a bandwidth of 960.0 GB/s.
Clock speeds differ substantially. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The RTX 5080 has a base clock of 2295 MHz and a boost clock of 2617 MHz, with memory running at 1875 MHz, equivalent to 30 Gbps effective.
The compute units are heavily skewed toward the RTX 5080. The Arc B390 has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The RTX 5080 has 10,752 shading units, 336 TMUs, 112 ROPs, and 84 ray tracing cores. The RTX 5080 also has 336 tensor cores; no tensor core count is recorded for the Arc B390.
Fill rates and throughput follow the same pattern. The Arc B390 delivers 60.00 GPixel/s and 120.0 GTexel/s, with FP32 performance of 7.680 TFLOPS and FP16 performance of 15.36 TFLOPS (2:1). The RTX 5080 delivers 293.1 GPixel/s and 879.3 GTexel/s, with FP32 performance of 56.28 TFLOPS and FP16 performance of 56.28 TFLOPS (1:1).
Power and physical configuration also diverge. The Arc B390 is rated at 80 W, uses no power connectors, and is an IGP with a bus interface of IGP. The RTX 5080 is rated at 360 W, uses a single 16-pin connector, requires a suggested PSU of 750 W, occupies a dual-slot form factor, and connects via PCIe 5.0 x16. The RTX 5080 has recorded dimensions of 304 mm in length, 137 mm in height, and 40 mm in width.
Display outputs differ as well. The Arc B390's outputs are portable device dependent, while the RTX 5080 provides 1x HDMI 2.1b and 3x DisplayPort 2.1b.
Architecture Differences
The Intel Arc B390 is built on the Xe3-LPG architecture and uses the Panther Lake chip. It is manufactured on a 3 nm process by Intel and belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA GeForce RTX 5080 uses the Blackwell 2.0 architecture with the GB203 chip, fabricated by TSMC on a 5 nm process. The RTX 5080 has a recorded transistor count of 45,600 million on a die size of 378 mm², with a transistor density of 120.6 million per mm². Transistor count and die size for the Arc B390 are listed as unknown.
The memory architecture is fundamentally different. The Arc B390 shares system memory, making its memory bandwidth system dependent. The RTX 5080 has dedicated GDDR7 memory with a fixed bandwidth of 960.0 GB/s. This distinction is central to the performance gap, as the RTX 5080 does not compete with other system components for memory bandwidth.
The RTX 5080 includes tensor cores, which the Arc B390 does not list. Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5080's FP16 throughput matches its FP32 throughput at a 1:1 ratio, while the Arc B390 halves FP16 throughput to 15.36 TFLOPS at a 2:1 ratio. The RTX 5080's predecessor is recorded as GeForce 40 and its successor as GeForce 60. No predecessor or successor is recorded for the Arc B390.
Where Each One Wins
The RTX 5080 wins in every benchmark category where both have recorded data. In the single head-to-head test, 3DMark Steel Nomad DX12, it outscores the Arc B390 by 7,155 points. The RTX 5080 also has recorded wins in Geekbench OpenCL (235,901), Geekbench Vulkan (255,450), Passmark G3D (36,565), and Passmark GPU Compute (21,789). The Arc B390 has no scores in these tests, so no direct comparison exists, but the average score gap, 56,083 versus 1,482, indicates a consistent advantage.
The Arc B390's strengths are not in performance but in integration and power. Its 80 W TDP, lack of power connectors, and IGP form factor make it a fit for systems where a discrete GPU is not an option. The RTX 5080, with its 360 W TDP, 16-pin connector, and dual-slot design, is a dedicated desktop component.
For use cases involving high-resolution rendering, ray tracing, compute workloads, or any application that stresses GPU throughput, the RTX 5080 is the only viable option in this comparison. For low-power, compact, or integrated systems where the GPU must share system memory and fit within the processor package, the Arc B390 is the applicable part. The recorded data does not show any workload where the Arc B390 outperforms the RTX 5080.