AMD Radeon RX 9070 vs Intel Arc Pro B390 Comparison

The AMD Radeon RX 9070 and Intel Arc Pro B390 occupy opposite ends of the graphics spectrum, one a discrete add-in board with a 220 W power draw and the other an integrated GPU with an 80 W envelope. The database records no direct head-to-head benchmark results, and the Arc Pro B390 has no individual test scores or rivals listed. What follows is a comparison based strictly on the recorded specifications, the RX 9070’s benchmark results, and the architectural data available for each part.

The Verdict

The data separates these two products into distinct roles. The AMD Radeon RX 9070 delivers measured performance across ten benchmark tests, with an average benchmark score of 23877 points and a percentile rank of 69 among all GPUs in the database. Its nearest rivals include the NVIDIA GeForce RTX 2080 SUPER, which scores 24170 points with a -1.2% delta, and the AMD Radeon RX 6800S at 24063 points with a -0.8% delta. The RX 9070 also sits 0.6% above the NVIDIA GeForce GTX TITAN Z (23736 points) and 1.1% above the NVIDIA GeForce RTX 3080 Mobile (23628 points). This places the RX 9070 in a performance band where it trades positions with those established desktop and mobile parts, all within roughly a one-point percentage spread.

The Intel Arc Pro B390 has no benchmark scores, no average score, and no rival comparisons in the database. Its percentile rank sits at 50, but with zero recorded measurements, that rank carries no empirical weight. The B390 is an integrated GPU built into the Panther Lake chip, using system shared memory with system dependent bandwidth. It targets a different form factor entirely: an IGP with no power connectors, no suggested PSU, and a dual-slot counterpart that requires two 8-pin connectors and a 550 W recommended power supply. The verdict from the recorded data is clear: the RX 9070 is the only part here with verified performance numbers, and it belongs in a desktop system with dedicated power delivery. The Arc Pro B390, by contrast, is a low-power integrated solution whose performance cannot be quantified from the database, so any selection between them depends entirely on whether the user needs a discrete GPU or an integrated one.

Architecture Differences

The RX 9070 uses the Navi 48 chip built on RDNA 4.0 architecture, fabricated on a 4 nm process at TSMC. The die measures 357 mm² and contains 53,900 million transistors, producing a transistor density of 151.0 million per square millimeter. The chip belongs to the Navi IV (RX 9000) generation and succeeds the Navi III predecessor. The Arc Pro B390 uses the Panther Lake chip with Xe3-LPG architecture, fabricated on a 3 nm process at Intel. Its transistor count and die size are listed as unknown, and it has no transistor density figure. The B390 belongs to the Arc Graphics-WM (Panther Lake) generation, succeeding HD Graphics-WM.

The RX 9070 carries 3584 shading units, 224 texture mapping units, and 128 raster output units. It has 56 ray tracing cores. The Arc Pro B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The RX 9070’s shading unit count is more than double the B390’s, and its TMU count is over four times higher. The ROP count is more than five times higher on the RX 9070. Pixel rate for the RX 9070 is 322.6 GPixel/s versus 60.00 GPixel/s for the B390, and texture rate is 564.5 GTexel/s versus 120.0 GTexel/s. FP32 compute is 36.13 TFLOPS for the RX 9070 versus 7.680 TFLOPS for the B390, a factor of roughly 4.7 times. FP16 on the RX 9070 is 36.13 TFLOPS at a 1:1 ratio, while the B390 reaches 15.36 TFLOPS at a 2:1 ratio, so the B390 has a higher FP16-to-FP32 ratio but still lower absolute FP16 throughput.

Memory differs fundamentally. The RX 9070 has 16 GB of GDDR6 on a 256-bit bus, with 644.6 GB/s of bandwidth and a memory clock of 2518 MHz (20.1 Gbps effective). The B390 uses system shared memory, with system shared type, bus width, and system dependent bandwidth. The RX 9070’s base clock is 1330 MHz with a boost of 2520 MHz and a game clock of 2070 MHz. The B390’s base clock is 300 MHz with a boost of 2500 MHz, and no game clock is listed. Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 9070 uses PCIe 5.0 x16, while the B390 uses an IGP bus interface. Display outputs for the RX 9070 are 1x HDMI 2.1b and 3x DisplayPort 2.1a; the B390 lists portable device dependent outputs.

Where Each One Wins

The RX 9070 wins on every measurable compute and rendering metric. Its FP32 throughput is 36.13 TFLOPS, which is 4.7 times the B390’s 7.680 TFLOPS. Pixel fill rate is 322.6 GPixel/s, 5.4 times higher than 60.00 GPixel/s. Texture fill rate is 564.5 GTexel/s, 4.7 times higher than 120.0 GTexel/s. The RX 9070 has 16 GB of dedicated GDDR6 memory versus system shared memory for the B390, and its 644.6 GB/s bandwidth stands against a system dependent figure. The RX 9070 has 3584 shading units versus 1536, 224 TMUs versus 48, and 128 ROPs versus 24.

The B390 wins on power efficiency and integration. Its 80 W TDP is less than half the RX 9070’s 220 W. It requires no power connectors, whereas the RX 9070 needs two 8-pin connectors. The B390 has no suggested PSU, while the RX 9070 recommends a 550 W unit. The B390 is an IGP, meaning it occupies no slot width and needs no separate card, while the RX 9070 is dual-slot. The B390 also uses a 3 nm process at Intel versus the 4 nm TSMC process for the RX 9070, though the transistor count is unknown. The B390 has a lower base clock at 300 MHz versus 1330 MHz, but its boost clock of 2500 MHz is close to the RX 9070’s 2520 MHz. The B390’s FP16 rate of 15.36 TFLOPS is higher relative to its FP32 than the RX 9070’s 1:1 ratio, which may benefit workloads that use FP16 instructions, but the absolute FP16 number is still lower.

In benchmark terms, the RX 9070 records its best scores in Geekbench OpenCL at 131539 points, PassMark G3D at 25381 points, and 3DMark Steel Nomad DX12 at 6290 points. The Arc Pro B390 has no recorded scores, so no win can be attributed to it in any test. The database shows winsA at 0 and winsB at 0, reflecting the absence of head-to-head results.

FAQ

Q: Does the Intel Arc Pro B390 have any benchmark scores in the database?

A: No. The B390 lists an empty benchmarks array, an average benchmark score of 0, and no nearest rivals. Its percentile rank of 50 is recorded, but with no measurements to support it.

Q: What is the average benchmark score for the AMD Radeon RX 9070?

A: The RX 9070 has an average benchmark score of 23877 points across ten tests, placing it at the 69th percentile among all GPUs in the database.

Q: How does the RX 9070 compare to its nearest rival, the NVIDIA GeForce RTX 2080 SUPER?

A: The RTX 2080 SUPER has an average score of 24170 points, which is 1.2% higher than the RX 9070’s 23877 points. The RX 9070 also trails the AMD Radeon RX 6800S by 0.8% (24063 points) and beats the NVIDIA GeForce GTX TITAN Z by 0.6% (23736 points) and the NVIDIA GeForce RTX 3080 Mobile by 1.1% (23628 points).

Q: What memory configuration does each GPU use?

A: The RX 9070 uses 16 GB of GDDR6 on a 256-bit bus with 644.6 GB/s bandwidth. The Arc Pro B390 uses system shared memory with system shared type, bus width, and system dependent bandwidth.

Q: What is the power draw difference between the two?

A: The RX 9070 has a TDP of 220 W and requires two 8-pin power connectors with a suggested 550 W PSU. The Arc Pro B390 has a TDP of 80 W, no power connectors, and no suggested PSU.

Q: Which GPU has more ray tracing cores?

A: The RX 9070 has 56 ray tracing cores, while the Arc Pro B390 has 12.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between the RX 9070 and the Arc Pro B390, and the winsA and winsB counters are both zero. However, the RX 9070’s individual benchmark scores provide a reference for what a discrete GPU in this class achieves. In 3DMark Steel Nomad DX12, the RX 9070 scores 6290 points. In Geekbench OpenCL, it scores 131539 points, and in Geekbench Vulkan, 58705 points. PassMark tests show a G3D score of 25381, a GPU compute score of 14737, a G2D score of 1280, a DirectX 9 score of 343, a DirectX 11 score of 281, a DirectX 10 score of 141, and a DirectX 12 score of 74.

The nearest rival data contextualizes these numbers. The RX 9070’s average of 23877 is within 1.2% of the RTX 2080 SUPER’s 24170 and within 0.8% of the RX 6800S’s 24063. It is 0.6% above the GTX TITAN Z’s 23736 and 1.1% above the RTX 3080 Mobile’s 23628. The narrow deltas, all under 1.2 percentage points, indicate that the RX 9070 sits in a tightly clustered performance tier where no single rival holds a decisive lead. The largest gap in the available data is the 1.1% advantage over the RTX 3080 Mobile, while the smallest is the 0.6% lead over the GTX TITAN Z.

For the Arc Pro B390, the absence of benchmark data means no head-to-head comparison can be constructed. The specifications alone suggest a large compute deficit: the RX 9070’s 36.13 FP32 TFLOPS is 4.7 times the B390’s 7.680 TFLOPS, and the RX 9070’s 644.6 GB/s bandwidth has no equivalent in a system shared memory design. The B390’s boost clock of 2500 MHz nearly matches the RX 9070’s 2520 MHz, but with 1536 shading units versus 3584, the per-clock throughput is far lower.

Specification Differences

The two GPUs differ across nearly every recorded specification field. The RX 9070 uses a 4 nm TSMC process with 53,900 million transistors on a 357 mm² die, while the B390 uses a 3 nm Intel process with unknown transistor count and die size. The RX 9070’s transistor density is 151.0M / mm²; the B390 has no recorded density.

Clock speeds: the RX 9070 has a base clock of 1330 MHz, a boost of 2520 MHz, and a game clock of 2070 MHz. The B390 has a base of 300 MHz and a boost of 2500 MHz, with no game clock. Memory: the RX 9070 uses 16 GB GDDR6 on a 256-bit bus with 644.6 GB/s bandwidth and a memory clock of 2518 MHz (20.1 Gbps effective). The B390 uses system shared memory with system dependent bandwidth.

Compute units: the RX 9070 has 3584 shading units, 224 TMUs, 128 ROPs, and 56 RT cores. The B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores. Pixel rate is 322.6 GPixel/s versus 60.00 GPixel/s, texture rate is 564.5 GTexel/s versus 120.0 GTexel/s, and FP32 is 36.13 TFLOPS versus 7.680 TFLOPS. FP16 is 36.13 TFLOPS (1:1) versus 15.36 TFLOPS (2:1).

Power and physical: the RX 9070 has a TDP of 220 W, dual-slot width, two 8-pin power connectors, and a suggested PSU of 550 W. The B390 has a TDP of 80 W, IGP slot width, no power connectors, and no suggested PSU. Bus interface: PCIe 5.0 x16 for the RX 9070 versus IGP for the B390. Display outputs: 1x HDMI 2.1b and 3x DisplayPort 2.1a for the RX 9070 versus portable device dependent for the B390. The RX 9070 has a launch MSRP of 549 USD; the B390 has no launch MSRP. Release dates are 2025-03-05 for the RX 9070 and 2026-01-26 for the B390. Both list production status as Active, and both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.