Intel Arc B390 vs NVIDIA GeForce RTX 4080 SUPER Comparison

Head-to-Head Benchmarks

The recorded database contains a single direct comparison between the Intel Arc B390 and the NVIDIA GeForce RTX 4080 SUPER. In the 3DMark Steel Nomad DX12 test, the NVIDIA card scores 6600 points against 1482 points for the Intel part. That is a 77.5 percent deficit for the Intel Arc B390, or put another way, the RTX 4080 SUPER delivers roughly 4.45 times the score. This is a decisive win for NVIDIA in the only shared benchmark.

The Intel Arc B390 sits at the 9th percentile among all GPUs in the database, while the RTX 4080 SUPER ranks at the 86th percentile. The average benchmark score for the Intel part is 1482, while the NVIDIA card averages 54209 across all its recorded tests. The Intel chip's nearest rivals in the database are all entry-level NVIDIA parts: the GeForce GT 520MX (1463 average, 1.3 percent behind), the GeForce 800M (1460 average, 1.5 percent behind), the GeForce GT 625 OEM (1446 average, 2.5 percent behind), and the GeForce GT 710 (1443 average, 2.7 percent behind). The RTX 4080 SUPER instead competes with high-end parts: the RTX 4080 (54247 average, 0.1 percent ahead), the AMD Radeon Pro W5700X (54828 average, 1.1 percent ahead), the AMD Radeon RX 6750 GRE 12 GB (55698 average, 2.7 percent ahead), and the AMD Radeon 8060S (55757 average, 2.8 percent ahead).

Beyond the shared Steel Nomad test, the RTX 4080 SUPER has additional recorded scores. Its Geekbench OpenCL result is 219065, and its Geekbench Vulkan score is 260075. Passmark results include DirectX 9 at 381, DirectX 10 at 193, DirectX 11 at 301, DirectX 12 at 134, G2D at 1270, G3D at 34245, and GPU Compute at 19822. The Intel Arc B390 has no additional benchmark entries, so the database cannot show a multi-test comparison. The NVIDIA card wins the only head-to-head matchup, and it wins by a wide margin.

FAQ

Q: Which GPU has a higher 3DMark Steel Nomad DX12 score?

A: The NVIDIA GeForce RTX 4080 SUPER scores 6600, while the Intel Arc B390 scores 1482. The NVIDIA card leads by 77.5 percent.

Q: How does the Intel Arc B390 compare to its nearest rivals?

A: The Intel chip's average score of 1482 puts it just ahead of the GeForce GT 520MX (1463, 1.3 percent behind), GeForce 800M (1460, 1.5 percent behind), GeForce GT 625 OEM (1446, 2.5 percent behind), and GeForce GT 710 (1443, 2.7 percent behind). All of these are close competitors in the database.

Q: What is the percentile ranking for each GPU?

A: The Intel Arc B390 sits at the 9th percentile among all GPUs. The NVIDIA GeForce RTX 4080 SUPER sits at the 86th percentile.

Q: What memory configuration does each GPU use?

A: The Intel Arc B390 uses system-shared memory with a system-dependent bandwidth. The NVIDIA card has 16 GB of GDDR6X memory on a 256-bit bus with 736.3 GB/s bandwidth.

Q: What are the power requirements for each card?

A: The Intel Arc B390 has a TDP of 80 W with no power connectors, and it is an integrated graphics processor (IGP). The NVIDIA card has a TDP of 320 W, requires a 16-pin connector, and the database suggests a 700 W power supply.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 4080 SUPER has 10240 shading units, while the Intel Arc B390 has 1536. The NVIDIA card also has 320 texture mapping units versus 48, and 112 render output units versus 24.

Architecture Differences

The Intel Arc B390 uses the Panther Lake chip with Xe3-LPG architecture, built on a 3 nm process at Intel's foundry. It belongs to the Arc Graphics-M (Panther Lake) generation. The NVIDIA GeForce RTX 4080 SUPER uses the AD103 chip with Ada Lovelace architecture, built on a 5 nm process at TSMC. NVIDIA's card belongs to the GeForce 40 generation.

The Intel part has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. It has no dedicated tensor cores listed. The NVIDIA card has 10240 shading units, 320 TMUs, 112 ROPs, 80 ray tracing cores, and 320 tensor cores. These are large structural differences that explain the performance gap.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 4080 SUPER has a 1:1 FP16 to FP32 ratio, with both at 52.22 TFLOPS. The Intel Arc B390 has a 2:1 FP16 to FP32 ratio, with FP16 at 15.36 TFLOPS and FP32 at 7.680 TFLOPS. The NVIDIA card's compute capabilities are substantially higher across the board.

The RTX 4080 SUPER has 45,900 million transistors on a 379 mm² die, giving a transistor density of 121.1 million per square millimeter. The Intel part's transistor count and die size are unknown in the database. The Intel chip is an integrated graphics processor, while the NVIDIA card is a discrete triple-slot PCIe 4.0 x16 part.

The Intel Arc B390's memory is entirely system-shared, meaning its bandwidth depends on the host system. The NVIDIA card uses dedicated GDDR6X memory at 1438 MHz with 23 Gbps effective speed, delivering 736.3 GB/s over a 256-bit bus. This dedicated memory architecture is a fundamental difference in how each GPU accesses data.

Specification Differences

The two GPUs differ in nearly every measurable specification. The Intel Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The NVIDIA card has a base clock of 2295 MHz and a boost clock of 2550 MHz. The Intel part has no dedicated memory clock, using system-shared memory, while the NVIDIA card runs its memory at 1438 MHz with 23 Gbps effective.

Pixel rate: Intel at 60.00 GPixel/s versus NVIDIA at 285.6 GPixel/s. Texture rate: Intel at 120.0 GTexel/s versus NVIDIA at 816.0 GTexel/s. FP32 performance: Intel at 7.680 TFLOPS versus NVIDIA at 52.22 TFLOPS. FP16 performance: Intel at 15.36 TFLOPS versus NVIDIA at 52.22 TFLOPS.

Power: Intel at 80 W TDP versus NVIDIA at 320 W TDP. The Intel part has no power connectors and is an IGP, while the NVIDIA card uses a single 16-pin connector and is triple-slot. The suggested PSU for the NVIDIA card is 700 W; the Intel part has no suggested PSU listed. The RTX 4080 SUPER measures 310 mm in length, 140 mm in height, and 61 mm in width. The Intel part has no dimensions listed.

Memory: Intel uses system-shared memory with system-dependent bandwidth. NVIDIA uses 16 GB GDDR6X with a 256-bit bus and 736.3 GB/s bandwidth. Display outputs: the Intel part is portable-device dependent, while the NVIDIA card has 1x HDMI 2.1 and 3x DisplayPort 1.4a.

Production status: Intel is active, NVIDIA is end-of-life. Release dates: Intel on 2026-01-26, NVIDIA on 2024-01-30. The NVIDIA card's predecessor is GeForce 30 and successor is GeForce 50. The Intel part has no predecessor or successor listed. The NVIDIA card has a launch MSRP of 999 USD.

Where Each One Wins

The NVIDIA GeForce RTX 4080 SUPER wins the only direct benchmark comparison, and it wins all of its recorded tests in absolute terms. The 3DMark Steel Nomad DX12 score of 6600 places it far above the Intel Arc B390's 1482. The NVIDIA card also has strong compute results: Geekbench OpenCL at 219065, Geekbench Vulkan at 260075, and Passmark GPU Compute at 19822. These indicate a GPU suited for compute-heavy workloads, ray tracing, and high-resolution gaming.

The Intel Arc B390's recorded data shows it clustered with low-end NVIDIA parts. Its average score of 1482 is within 2.7 percent of the GeForce GT 710 and within 1.3 percent of the GeForce GT 520MX. The Intel chip is an integrated GPU with 80 W TDP, which makes it appropriate for portable devices or basic graphics tasks. Its 12 ray tracing cores and DirectX 12 Ultimate support suggest it can handle modern APIs, but its raw performance is far below the discrete NVIDIA card.

The NVIDIA card has 80 ray tracing cores versus 12, and 320 tensor cores versus none listed for Intel. The RTX 4080 SUPER has 10240 shading units, which is 6.7 times the Intel count. The memory bandwidth difference is enormous: 736.3 GB/s versus system-dependent shared memory. For any workload that depends on dedicated VRAM, high throughput, or compute density, the NVIDIA card is the clear choice.

The Intel Arc B390's advantage lies in its low power draw and integrated form factor. At 80 W with no external power connectors, it fits into systems where the NVIDIA card cannot operate. The NVIDIA card requires a 700 W PSU and a triple-slot chassis space. The Intel part's 3 nm process at Intel's foundry is a newer node than the NVIDIA card's 5 nm TSMC process, but this does not translate into performance advantages in the recorded benchmarks.

The Verdict

The data points to two completely different product categories. The NVIDIA GeForce RTX 4080 SUPER is a high-end discrete GPU with dedicated 16 GB GDDR6X memory, 10240 shading units, 80 ray tracing cores, and 52.22 TFLOPS of FP32 compute. It performs at the 86th percentile of all GPUs and scores 6600 in 3DMark Steel Nomad DX12. Its nearest rivals are other high-end cards like the RTX 4080 and AMD Radeon Pro W5700X, all within a few percentage points of each other.

The Intel Arc B390 is an integrated graphics processor with 1536 shading units, 12 ray tracing cores, and 7.680 TFLOPS of FP32 compute. It performs at the 9th percentile and scores 1482 in the same 3DMark test. Its nearest rivals are entry-level discrete parts from a decade ago, such as the GeForce GT 710 and GT 625 OEM. The Intel chip's 80 W TDP and system-shared memory make it a low-power solution for basic graphics output.

For a builder choosing between these two, the decision is straightforward. The RTX 4080 SUPER delivers 77.5 percent more performance in the head-to-head test, has dedicated high-bandwidth memory, and offers far more compute resources. It is an end-of-life product with a 999 USD launch MSRP, but its recorded performance remains strong. The Intel Arc B390 is an active product with a newer process node, but its benchmark results place it in a completely different performance tier. The database shows no scenario where the Intel part beats the NVIDIA card in any measured metric. The RTX 4080 SUPER is the choice for demanding workloads, while the Arc B390 is suited only for the most constrained power and form-factor environments.