AMD Radeon RX 7600 vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The database contains one direct benchmark comparison between the AMD Radeon RX 7600 and the Intel Arc B390: the 3DMark Steel Nomad DX12 test. In this test, the AMD card scores 2310, while the Intel Arc B390 scores 1482. The RX 7600 wins by a decisive 55.9% margin, which is a massive lead in raw graphics performance.

This single result defines the overall head-to-head record: one win for AMD, zero for Intel. The RX 7600's average benchmark score across all recorded tests is 15171, placing it in the 57th percentile of all GPUs. The Arc B390, with only the Steel Nomad result recorded, has an average score of 1482 and sits in the 9th percentile. That percentile gap is stark: the AMD part is in the upper half of all GPUs, while the Intel part is near the bottom of the database's rankings.

Looking at the nearest rivals for each card puts the delta into perspective. The RX 7600's closest competitors are the NVIDIA GeForce RTX 3050 OEM (average score 15199, a 0.2% difference), the AMD Radeon 680M (15270, 0.7% difference), the AMD Radeon Pro 560X (15082, 0.6% difference), and the NVIDIA GeForce GTX 660 Ti (15063, 0.7% difference). These deltas are all within 1%, meaning the RX 7600 trades blows with these parts; it is not universally faster, but it is in their performance class. The Arc B390, by contrast, has nearest rivals that are far older or weaker. The NVIDIA GeForce GT 520MX (1463, 1.3% difference), NVIDIA GeForce 800M (1460, 1.5%), NVIDIA GeForce GT 625 OEM (1446, 2.5%), and NVIDIA GeForce GT 710 (1443, 2.7%) are all within a few percent of the Intel part. This places the B390 in a completely different competitive tier, alongside entry-level cards from over a decade ago.

The RX 7600 also shows a much richer benchmark profile. It has scores for Geekbench OpenCL (88051) and Vulkan (34401), plus a full set of Passmark tests. The B390 has no recorded scores in any of those tests, so the only common ground is the single 3DMark result. This lack of data for the Intel part is itself a limitation: the database cannot show how it behaves in compute workloads or older DirectX versions. What the data does show is that in the one test where both have numbers, the AMD card is far ahead.

Architecture Differences

The two parts come from completely different design philosophies. The AMD Radeon RX 7600 uses the Navi 33 chip on the RDNA 3.0 architecture, built on a 6 nm process at TSMC. It has 13,300 million transistors on a 204 mm² die, giving a transistor density of 65.2M per mm². The Intel Arc B390 uses the Panther Lake chip with Xe3-LPG architecture, built on a 3 nm process at Intel's own foundry. Its transistor count and die size are listed as unknown in the database, so the density cannot be calculated.

The compute resources differ substantially. The RX 7600 has 2048 shading units, 128 texture mapping units, 64 ROPs, and 32 ray tracing cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The AMD card has 33% more shading units, 167% more TMUs, 167% more ROPs, and 167% more RT cores. This explains the large performance gap in the 3DMark test.

Clock speeds tell a similar story. The RX 7600 has a base clock of 1720 MHz, a game clock of 2250 MHz, and a boost clock of 2655 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. While the boost clocks are close, the base clock difference is enormous: the AMD part runs at nearly six times the base frequency of the Intel part. The Arc B390's very low base clock suggests it is designed to idle aggressively, ramping up only when needed, but the sustained performance profile is clearly weaker.

Memory is another fundamental divergence. The RX 7600 has 8 GB of dedicated GDDR6 memory on a 128-bit bus, with 2250 MHz memory clock (18 Gbps effective) and 288.0 GB/s of bandwidth. The Arc B390 uses System Shared memory, meaning it has no dedicated VRAM and relies on the system's main memory. Its memory type, bus width, and bandwidth are all listed as "System Shared" or "System Dependent", so the database cannot give a fixed bandwidth figure. For a discrete GPU like the RX 7600, dedicated VRAM is a major advantage, especially in games that need more than integrated-style memory access.

The FP32 compute throughput reflects the architectural split. The RX 7600 delivers 21.75 TFLOPS of FP32 and the same 21.75 TFLOPS of FP16 (1:1 ratio). The Arc B390 delivers 7.680 TFLOPS FP32 but doubles that to 15.36 TFLOPS FP16 (2:1 ratio). This means the Intel part is relatively stronger at FP16 workloads, but far weaker at standard FP32 rendering. Pixel rate and texture rate follow the same trend: the RX 7600 has 169.9 GPixel/s and 339.8 GTexel/s, while the Arc B390 has 60.00 GPixel/s and 120.0 GTexel/s. The AMD card is about 2.8 times faster in both fill rates.

The power envelope is equally different. The RX 7600 has a TDP of 165 W, requires a single 8-pin power connector, and comes in a dual-slot form factor. It needs a 450 W suggested PSU. The Arc B390 has an 80 W TDP, requires no power connectors, and is an IGP (integrated graphics processor). It has no suggested PSU because it does not need one. This makes the comparison one of a full discrete GPU against an integrated solution, which is a core architectural distinction.

Both parts support the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 7600 uses PCIe 4.0 x8, while the Arc B390 uses IGP as its bus interface. Display outputs differ too: the RX 7600 has 1x HDMI 2.1a and 3x DisplayPort 2.1, while the Arc B390's outputs are listed as "Portable Device Dependent", which means it uses whatever display connections the host device provides.

The Verdict

The data is unambiguous. The AMD Radeon RX 7600 is the faster GPU by a wide margin, with a 55.9% lead in the only shared benchmark. It also has far more compute resources, dedicated memory, and a higher performance percentile. The Intel Arc B390 is an integrated part with an 80 W TDP and no dedicated VRAM, so it cannot compete with a discrete card that was designed to fill a full dual-slot 165 W envelope.

Who should pick the RX 7600: anyone building a desktop PC with a dedicated graphics card slot and a PSU that can handle 450 W. The data shows it performs in the 57th percentile of all GPUs, trading blows with parts like the RTX 3050 OEM and the Radeon 680M. Its 8 GB of GDDR6 and 288 GB/s bandwidth make it suitable for modern gaming and compute tasks.

Who should pick the Arc B390: anyone who needs an integrated GPU for a portable device or a low-power system. The 80 W TDP and no power connectors mean it can run in a laptop or a compact device without additional power delivery. Its 9th percentile ranking shows that it is not meant for heavy gaming, but for basic graphics output and possibly FP16 workloads where its 15.36 TFLOPS could be useful. The 3 nm process gives it an efficiency advantage, but that does not translate into competitive raw performance against the RX 7600.

The verdict is simple: for raw graphics performance, the RX 7600 is the clear choice. For integrated, low-power use, the Arc B390 is the only option of the two, but it is not a substitute for a discrete GPU.

FAQ

Q: Which GPU is faster in the 3DMark Steel Nomad DX12 test?

A: The AMD Radeon RX 7600 scores 2310, which is 55.9% higher than the Intel Arc B390's 1482.

Q: How much memory does each GPU have?

A: The RX 7600 has 8 GB of dedicated GDDR6 memory. The Arc B390 uses System Shared memory, meaning it has no dedicated VRAM and depends on the system's main memory.

Q: What is the power consumption difference?

A: The RX 7600 has a TDP of 165 W and requires a 1x 8-pin power connector. The Arc B390 has a TDP of 80 W and requires no power connectors.

Q: Are they in the same performance tier?

A: No. The RX 7600 sits in the 57th percentile of all GPUs with an average score of 15171, while the Arc B390 sits in the 9th percentile with an average score of 1482.

Q: Which GPU has more shading units?

A: The RX 7600 has 2048 shading units, while the Arc B390 has 1536. The RX 7600 also has more TMUs (128 vs 48), ROPs (64 vs 24), and ray tracing cores (32 vs 12).

Q: What process nodes do the two GPUs use?

A: The RX 7600 uses a 6 nm process at TSMC. The Arc B390 uses a 3 nm process at Intel.

Where Each One Wins

The AMD Radeon RX 7600 wins in every measurable graphics benchmark shared between the two. It has a 55.9% lead in 3DMark Steel Nomad, a 2.8 times higher pixel rate, and a 2.8 times higher texture rate. It also has 2.8 times the FP32 compute power (21.75 TFLOPS vs 7.680 TFLOPS). For any task that relies on raw rasterization, fill rate, or standard FP32 shader work, the RX 7600 is the winner. Its 8 GB of dedicated GDDR6 memory with 288.0 GB/s bandwidth also gives it a clear advantage in bandwidth-sensitive workloads, since the Arc B390's bandwidth is system-dependent and cannot be fixed at a comparable figure.

The Intel Arc B390 wins in a few specific areas, mostly related to efficiency and integration. Its 80 W TDP is less than half of the RX 7600's 165 W, and it requires no power connectors, so it fits into systems where the RX 7600 cannot go. Its FP16 throughput of 15.36 TFLOPS is higher than its own FP32 figure, and while it is still lower than the RX 7600's FP16 (21.75 TFLOPS), the 2:1 ratio suggests the architecture is more optimized for FP16 workloads relative to its own FP32. The 3 nm process also gives it a manufacturing advantage in density, though transistor count and die size are unknown, so the database cannot quantify that. The Arc B390 is also the only option for portable devices, as its display outputs are listed as "Portable Device Dependent", meaning it is designed to be built into laptops or similar hardware.

For a use-case split: the RX 7600 is for desktop gaming, 3D rendering, and compute tasks that need dedicated VRAM and high fill rates. The Arc B390 is for low-power integrated graphics in portable devices, basic 2D/3D output, and workloads that can leverage its FP16 throughput without needing high FP32 performance.

Specification Differences

The two GPUs differ in nearly every specification field. The RX 7600 uses the Navi 33 chip on RDNA 3.0, while the Arc B390 uses Panther Lake on Xe3-LPG. The process node is 6 nm (TSMC) for AMD and 3 nm (Intel) for Intel. Transistor count is 13,300 million for the RX 7600 and unknown for the Arc B390; die size is 204 mm² vs unknown.

Clocks: the RX 7600 has a base clock of 1720 MHz, a boost of 2655 MHz, and a game clock of 2250 MHz. The Arc B390 has a base of 300 MHz and a boost of 2500 MHz, with no game clock listed. Memory clocks are 2250 MHz (18 Gbps effective) for the RX 7600 and "System Shared" for the Arc B390.

Memory: 8 GB GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth for the RX 7600; System Shared type, bus width, and bandwidth for the Arc B390.

Compute units: 2048 shading units, 128 TMUs, 64 ROPs, and 32 RT cores for the RX 7600; 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores for the Arc B390. Pixel rate is 169.9 GPixel/s vs 60.00 GPixel/s, and texture rate is 339.8 GTexel/s vs 120.0 GTexel/s. FP32 is 21.75 TFLOPS vs 7.680 TFLOPS, and FP16 is 21.75 TFLOPS (1:1) vs 15.36 TFLOPS (2:1).

Power and form factor: 165 W TDP, dual-slot, 1x 8-pin connector, 450 W suggested PSU for the RX 7600; 80 W TDP, IGP slot width, no power connectors, and no suggested PSU for the Arc B390.

Bus interface: PCIe 4.0 x8 for the RX 7600, IGP for the Arc B390. Display outputs: 1x HDMI 2.1a and 3x DisplayPort 2.1 for AMD, "Portable Device Dependent" for Intel. Dimensions: 204 mm x 115 mm for the RX 7600, no dimensions listed for the Arc B390. Release dates: May 24, 2023 for the RX 7600 and January 26, 2026 for the Arc B390. The RX 7600 has a launch MSRP of 269 USD; the Arc B390 has no listed MSRP. The RX 7600 also lists a predecessor (Navi II) and successor (Navi IV), while the Arc B390 has neither.