AMD Radeon RX 9070 vs Intel Arc B390 Comparison

# Head-to-Head Benchmarks

The recorded database contains a single shared benchmark between the AMD Radeon RX 9070 and the Intel Arc B390: the 3DMark Steel Nomad DX12 test. In this workload, the AMD Radeon RX 9070 scores 6290 points, while the Intel Arc B390 scores 1482 points. This represents a 324.4% advantage for the AMD part, meaning the Radeon RX 9070 delivers more than four times the performance of the Arc B390 in this specific DirectX 12 test. The result is unambiguous: AMD wins the only directly comparable benchmark, and the margin is substantial.

Looking at broader performance context, the AMD Radeon RX 9070 holds an average benchmark score of 23877 across all recorded tests, with a percentile ranking of 69 among all GPUs in the database. Its nearest rivals include the NVIDIA GeForce RTX 2080 SUPER, which averages 24170 (the AMD card trails by 1.2%), and the AMD Radeon RX 6800S, which averages 24063 (the RX 9070 trails by 0.8%). Conversely, the RX 9070 leads the NVIDIA GeForce RTX 3080 Mobile by 1.1% (23628 average) and the NVIDIA GeForce GTX TITAN Z by 0.6% (23736 average). These figures place the RX 9070 in a competitive position relative to high-end discrete GPUs from previous generations.

The Intel Arc B390, by contrast, averages 1482 points and ranks at the 9th percentile among all GPUs. Its nearest rivals are much older and lower-powered parts: the NVIDIA GeForce GT 520MX (1463 average, with the Arc B390 leading by 1.3%), the NVIDIA GeForce 800M (1460, leading by 1.5%), the NVIDIA GeForce GT 625 OEM (1446, leading by 2.5%), and the NVIDIA GeForce GT 710 (1443, leading by 2.7%). These deltas are small, indicating that the Arc B390 sits in a very different performance tier, roughly comparable to entry-level discrete GPUs from roughly a decade earlier.

The head-to-head delta of 324.4% dwarfs any of the nearest-rival margins for either card. For the RX 9070, its largest nearest-rival gap is a 1.2% deficit, while for the Arc B390, its largest nearest-rival gap is a 2.7% lead. The gap between the two products in this comparison is therefore not a marginal difference but a fundamental separation in performance class.

# FAQ

Q: Which GPU wins the only shared benchmark in the database?

A: The AMD Radeon RX 9070 wins the 3DMark Steel Nomad DX12 test with a score of 6290, compared to the Intel Arc B390's 1482, a lead of 324.4%.

Q: How does the AMD Radeon RX 9070 compare to its nearest rivals?

A: The RX 9070's average benchmark score of 23877 is 1.2% below the NVIDIA GeForce RTX 2080 SUPER (24170) and 0.8% below the AMD Radeon RX 6800S (24063). It is 1.1% above the NVIDIA GeForce RTX 3080 Mobile (23628) and 0.6% above the NVIDIA GeForce GTX TITAN Z (23736).

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

A: The Arc B390's average benchmark score of 1482 is 1.3% above the NVIDIA GeForce GT 520MX (1463), 1.5% above the NVIDIA GeForce 800M (1460), 2.5% above the NVIDIA GeForce GT 625 OEM (1446), and 2.7% above the NVIDIA GeForce GT 710 (1443).

Q: What is the percentile ranking for each GPU?

A: The AMD Radeon RX 9070 ranks at the 69th percentile among all GPUs in the database, while the Intel Arc B390 ranks at the 9th percentile.

Q: How many benchmark wins does each GPU have in the head-to-head comparison?

A: The AMD Radeon RX 9070 has 1 win, and the Intel Arc B390 has 0 wins.

Q: What is the average benchmark score for each GPU?

A: The AMD Radeon RX 9070 has an average benchmark score of 23877, while the Intel Arc B390 has an average benchmark score of 1482.

# Architecture Differences

The two GPUs come from different manufacturers and are built on different architectural foundations. The AMD Radeon RX 9070 uses the Navi 48 chip based on RDNA 4.0 architecture, part of the Navi IV (RX 9000) generation. It is fabricated on a 4 nm process at TSMC, with 53,900 million transistors on a 357 mm² die, yielding a transistor density of 151.0 million transistors per square millimeter. The Intel Arc B390 uses the Panther Lake chip based on Xe3-LPG architecture, part of the Arc Graphics-M (Panther Lake) generation. It is fabricated on a 3 nm process at Intel, though its transistor count, die size, and transistor density are recorded as unknown or null.

The RX 9070 is a discrete add-in board with a dual-slot cooler and two 8-pin power connectors. The Arc B390 is an integrated graphics processor (IGP) with no slot width beyond the IGP designation and no power connectors. This fundamental difference in form factor shapes many of the architectural trade-offs between the two.

The RX 9070 features 3584 shading units, 224 texture mapping units, 128 raster output units, and 56 ray tracing cores. The Arc B390 features 1536 shading units, 48 texture mapping units, 24 raster output units, and 12 ray tracing cores. The AMD part has more than double the shading units, nearly five times the TMUs, more than five times the ROPs, and more than four times the ray tracing cores.

Memory architecture also differs sharply. The RX 9070 has 16 GB of GDDR6 memory on a 256-bit bus, with a bandwidth of 644.6 GB/s and a memory clock of 2518 MHz (20.1 Gbps effective). The Arc B390 uses system shared memory, meaning its memory size, type, and bus width are all listed as system shared, and bandwidth is system dependent. This reflects the integrated nature of the Intel part, which relies on the host system's memory rather than dedicated VRAM.

The RX 9070 delivers a pixel rate of 322.6 GPixel/s and a texture rate of 564.5 GTexel/s. The Arc B390 delivers 60.00 GPixel/s and 120.0 GTexel/s. In floating-point throughput, the RX 9070 achieves 36.13 TFLOPS for FP32 and the same 36.13 TFLOPS for FP16 at a 1:1 ratio. The Arc B390 achieves 7.680 TFLOPS for FP32 and 15.36 TFLOPS for FP16 at a 2:1 ratio. The RX 9070's FP32 throughput is roughly 4.7 times higher, consistent with the observed benchmark delta.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 9070 connects via PCIe 5.0 x16, while the Arc B390 uses an IGP bus interface. Display outputs for the RX 9070 consist of 1x HDMI 2.1b and 3x DisplayPort 2.1a; the Arc B390's display outputs are portable device dependent.

# Specification Differences

The AMD Radeon RX 9070 and Intel Arc B390 differ across nearly every recorded specification field. The RX 9070 has a base clock of 1330 MHz and a boost clock of 2520 MHz, with a game clock of 2070 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, with no recorded game clock. The RX 9070's memory clock is 2518 MHz (20.1 Gbps effective), while the Arc B390's memory clock is listed as system shared.

Power draw and cooling requirements differ substantially. The RX 9070 has a TDP of 220 W and a suggested PSU of 550 W. The Arc B390 has a TDP of 80 W and no suggested PSU, consistent with its integrated nature. The RX 9070 is dual-slot with 2x 8-pin power connectors; the Arc B390 is an IGP with no power connectors.

The RX 9070 uses 16 GB of GDDR6 memory on a 256-bit bus with 644.6 GB/s bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth. The RX 9070 has 3584 shading units, 224 TMUs, 128 ROPs, and 56 RT cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores.

Pixel and texture rates also differ: the RX 9070 achieves 322.6 GPixel/s and 564.5 GTexel/s, while the Arc B390 achieves 60.00 GPixel/s and 120.0 GTexel/s. Floating-point performance shows the RX 9070 at 36.13 TFLOPS for both FP32 and FP16, while the Arc B390 is at 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16. The RX 9070 is fabricated on a 4 nm TSMC process with 53,900 million transistors and a 357 mm² die; the Arc B390 is on a 3 nm Intel process with unknown transistor count and die size.

The RX 9070 was released on 2025-03-05 with a launch MSRP of 549 USD and a production status of Active. The Arc B390 was released on 2026-01-26 with no launch MSRP and a production status of Active. The RX 9070's predecessor is listed as Navi III, while the Arc B390 has no recorded predecessor. The RX 9070 is part of the Radeon RX 9000 series; the Arc B390 has no series designation. The RX 9070's PCIe interface is 5.0 x16, while the Arc B390's is IGP.

# Where Each One Wins

The AMD Radeon RX 9070 wins the only directly comparable benchmark, the 3DMark Steel Nomad DX12 test, with a 324.4% lead. More broadly, its average benchmark score of 23877 places it at the 69th percentile among all GPUs, and it trades closely with high-end discrete GPUs such as the NVIDIA GeForce RTX 2080 SUPER, the NVIDIA GeForce RTX 3080 Mobile, the AMD Radeon RX 6800S, and the NVIDIA GeForce GTX TITAN Z. The RX 9070's dedicated 16 GB GDDR6 memory, 256-bit bus, and 644.6 GB/s bandwidth make it suitable for memory-intensive workloads. Its 36.13 TFLOPS FP32 throughput and 36.13 TFLOPS FP16 throughput indicate strong compute capability. Its 56 ray tracing cores and 128 ROPs provide substantial geometry and pixel processing resources. The RX 9070's 220 W TDP and dual-slot cooler with 2x 8-pin power connectors reflect a design intended for full-power desktop operation.

The Intel Arc B390 wins no head-to-head benchmarks in the database. Its average benchmark score of 1482 places it at the 9th percentile, and its nearest rivals are all NVIDIA parts from a much older era: the GT 520MX, the GeForce 800M, the GT 625 OEM, and the GT 710. Its advantages are not in raw performance but in form factor and power draw. As an IGP with no power connectors and an 80 W TDP, it requires no separate graphics card slot and no dedicated power supply recommendation. Its system shared memory design means it draws on host memory rather than requiring dedicated VRAM. Its 3 nm Intel process node is smaller than the RX 9070's 4 nm TSMC node, and its FP16 throughput of 15.36 TFLOPS is higher than its FP32 throughput of 7.680 TFLOPS, reflecting a 2:1 ratio that may benefit certain compute tasks. The Arc B390's 12 ray tracing cores and 24 ROPs, while far fewer than the RX 9070's, still provide baseline support for modern graphics features.

The use cases naturally diverge. The RX 9070 is positioned for scenarios demanding high frame rates, high resolutions, and heavy geometry or compute loads, where its 4.7 times FP32 throughput advantage and 5.4 times pixel rate advantage can be fully utilized. The Arc B390 is positioned for systems where a discrete GPU is not feasible, where power draw must remain minimal, and where the workload is light enough to be served by an integrated solution. The benchmark data does not show any workload where the Arc B390 outperforms the RX 9070; it shows only that the Arc B390 operates in a far lower performance envelope.

# The Verdict

The recorded data presents a clear separation in performance tier. The AMD Radeon RX 9070 wins the only shared benchmark by 324.4%, holds a 69th percentile ranking, and averages 23877 points across its recorded tests. The Intel Arc B390 averages 1482 points, ranks at the 9th percentile, and its nearest rivals are entry-level GPUs from an older generation. No benchmark in the database shows the Arc B390 ahead.

The RX 9070 is the appropriate choice for users who need discrete-level graphics performance, with 16 GB of dedicated GDDR6 memory, 644.6 GB/s bandwidth, 3584 shading units, and 36.13 TFLOPS of FP32 throughput. Its nearest rivals in the database are high-end NVIDIA and AMD parts from recent generations, and it sits within roughly 1% of all four of them. The Arc B390, by contrast, is an integrated GPU with 1536 shading units, 7.680 TFLOPS FP32, and system shared memory, placing it in a fundamentally different performance class.

Based on the database measurements, the RX 9070 is the faster product in every recorded comparison. The Arc B390 offers a lower power envelope at 80 W TDP and requires no external power connectors, but the performance data does not indicate any scenario where it matches or exceeds the RX 9070. The verdict follows directly from the numbers: the AMD Radeon RX 9070 is the higher-performing GPU, and the Intel Arc B390 is a lower-power integrated alternative with substantially lower benchmark scores.