AMD Radeon RX 7400 vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark in the database is 3DMark Steel Nomad DX12, and it produces a decisive result. The Intel Arc B390 scores 1482, while the AMD Radeon RX 7400 scores 1103. That places the Arc B390 25.6% ahead, a substantial margin in a single synthetic workload. The delta is large enough to indicate a clear performance tier separation, not merely a run-to-run variance or driver-level quirk.

The RX 7400 does not win any recorded head-to-head benchmark. Its sole data point in the direct comparison is the Steel Nomad loss. However, the RX 7400 has a much broader benchmark history, which provides context. Its average benchmark score across all recorded tests is 2467, versus 1482 for the Arc B390. That average includes legacy DirectX workloads, compute tests, and 2D graphics, where the RX 7400 shows strengths that the single Steel Nomad run does not capture.

The RX 7400 posts a PassMark G3D score of 11897, a PassMark G2D score of 1209, and a GPU compute score of 5152. The Arc B390 has no recorded scores in those specific tests, so a direct comparison is impossible. The RX 7400 also records legacy API results: 176 in PassMark DirectX 9, 97 in DirectX 11, 59 in DirectX 10, and 44 in DirectX 12. Those figures indicate that the RX 7400 is a functional general-purpose GPU across multiple API generations, whereas the Arc B390's database footprint is limited to the single modern DirectX 12 test.

The percentile rankings further separate the two. The RX 7400 sits at the 17th percentile of all GPUs in the database, while the Arc B390 sits at the 9th percentile. That is a meaningful gap in overall standing, even though the Arc B390 wins the one shared modern benchmark. The RX 7400's nearest rivals include the AMD Radeon 8040S at an average score of 2440 (1.1% behind), the NVIDIA GeForce 710M at 2433 (1.4% behind), the Intel HD Graphics 610 at 2425 (1.8% behind), and the NVIDIA GeForce GT 710M at 2422 (1.9% behind). The Arc B390's nearest rivals are all older NVIDIA parts: the GeForce GT 520MX at 1463 (1.3% behind), the GeForce 800M at 1460 (1.5% behind), the GeForce GT 625 OEM at 1446 (2.5% behind), and the GeForce GT 710 at 1443 (2.7% behind). The RX 7400 competes against a slightly more modern set of integrated and low-end discrete parts, while the Arc B390's peer group is dominated by legacy mobile GPUs.

FAQ

Q: Which GPU wins the only shared benchmark?

A: The Intel Arc B390 wins 3DMark Steel Nomad DX12 with a score of 1482, 25.6% ahead of the AMD Radeon RX 7400's 1103.

Q: Does the RX 7400 have any benchmark advantage?

A: Yes, the RX 7400 has a much higher average benchmark score of 2467 across all recorded tests, versus 1482 for the Arc B390. It also has a higher percentile rank at 17% versus 9%.

Q: What memory configuration does each GPU use?

A: The RX 7400 uses 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth. The Arc B390 uses system shared memory with system dependent bandwidth.

Q: How do the shader counts compare?

A: The RX 7400 has 1792 shading units, 112 texture mapping units, and 64 ROPs. The Arc B390 has 1536 shading units, 48 TMUs, and 24 ROPs.

Q: What process nodes are used?

A: The RX 7400 uses TSMC's 6 nm process with 13,300 million transistors on a 204 mm² die. The Arc B390 uses Intel's 3 nm process; transistor count and die size are listed as unknown in the database.

Q: Which GPU has a higher boost clock?

A: The Arc B390 boosts to 2500 MHz, while the RX 7400 boosts to 2300 MHz. The RX 7400 has a higher base clock at 1452 MHz versus 300 MHz for the Arc B390.

Architecture Differences

The architectural split is fundamental. The RX 7400 is built on RDNA 3.0 with the Navi 33 chip, codenamed Hotpink Bonefish, part of the Navi III (RX 7000) generation. The Arc B390 uses Xe3-LPG architecture with the Panther Lake chip, part of the Arc Graphics-M (Panther Lake) generation. These are entirely different design philosophies: one is a discrete GPU, the other is an integrated graphics processor.

The process technology differs sharply. The RX 7400 uses TSMC's 6 nm node with 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2 million per mm². The Arc B390 uses Intel's 3 nm node, with transistor count and die size listed as unknown. The 3 nm node is smaller, but without transistor or die data, the density comparison cannot be quantified. The foundry difference is also notable: TSMC for AMD, Intel for its own part.

Ray tracing hardware differs in count. The RX 7400 has 28 RT cores, while the Arc B390 has 12. The RX 7400 also has more texture units (112 versus 48) and ROPs (64 versus 24). The shading unit count favors the RX 7400 as well: 1792 versus 1536. Neither GPU lists tensor cores in the database.

Compute throughput reflects the hardware counts. The RX 7400 delivers 16.49 TFLOPS FP32 and 32.97 TFLOPS FP16 (2:1). The Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1). The RX 7400's FP32 figure is more than double the Arc B390's, which is consistent with its larger shader array and higher clock profile. Pixel rate also favors AMD: 147.2 GPixel/s versus 60.00 GPixel/s. Texture rate follows: 257.6 GTexel/s versus 120.0 GTexel/s.

The memory architecture is entirely different. The RX 7400 has dedicated 8 GB GDDR6 with a 128-bit bus and 288.0 GB/s bandwidth. The Arc B390 uses system shared memory, with type, bus width, and bandwidth all listed as system dependent. This has profound implications for performance consistency, as the Arc B390's memory performance depends on the host platform's RAM configuration, which is not fixed in the database.

Power and physical design differ completely. The RX 7400 is a dual-slot discrete card with a 43 W TDP and a single 6-pin power connector, requiring a 200 W suggested PSU. The Arc B390 is an IGP with an 80 W TDP, no power connectors, and no suggested PSU, since it draws from the host system. The Arc B390 is not a card at all; it is integrated into a processor package, with display outputs listed as portable device dependent.

API support is identical on paper: both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs, with the RX 7400 using PCIe 4.0 x8 and the Arc B390 using IGP, meaning no separate bus connection. The RX 7400 offers 1x HDMI 2.1a and 3x DisplayPort 2.1 outputs, while the Arc B390's outputs depend on the portable device it is integrated into.

Specification Differences

The clock speeds show a notable inversion. The RX 7400 has a base clock of 1452 MHz and a boost clock of 2300 MHz, with a game clock of 2200 MHz. The Arc B390 has a much lower base clock of 300 MHz but a higher boost clock of 2500 MHz. The RX 7400's memory clock is 2250 MHz (18 Gbps effective), while the Arc B390's memory clock is listed as system shared.

The memory subsystem is the largest differentiator. The RX 7400 has 8 GB GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth. The Arc B390 has system shared memory, system shared type, system shared bus width, and system dependent bandwidth. No fixed numbers exist for the Intel part's memory.

The compute unit counts differ across the board. The RX 7400 has 1792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores. The Arc B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 RT cores. The RX 7400 leads in every count. Pixel rate is 147.2 GPixel/s versus 60.00 GPixel/s, and texture rate is 257.6 GTexel/s versus 120.0 GTexel/s. FP32 is 16.49 TFLOPS versus 7.680 TFLOPS, and FP16 is 32.97 TFLOPS versus 15.36 TFLOPS.

Power figures diverge. The RX 7400 has a 43 W TDP, while the Arc B390 has an 80 W TDP. The RX 7400 uses a 1x 6-pin power connector and a 200 W suggested PSU. The Arc B390 uses no power connectors and has no suggested PSU. Slot width is dual-slot for the RX 7400 and IGP for the Arc B390. The RX 7400 uses PCIe 4.0 x8; the Arc B390 uses IGP. Display outputs are 1x HDMI 2.1a plus 3x DisplayPort 2.1 for AMD, and portable device dependent for Intel.

Process node and foundry differ. The RX 7400 is on TSMC's 6 nm with 13,300 million transistors and a 204 mm² die. The Arc B390 is on Intel's 3 nm with unknown transistor count and die size. Release dates also differ: the RX 7400 was released on 2025-08-07, and the Arc B390 on 2026-01-26. The RX 7400 has a predecessor (Navi II) and successor (Navi IV) listed, while the Arc B390 has neither. The Arc B390 is marked as active in production, while the RX 7400's production status is not recorded.

The Verdict

The data presents a split verdict. For modern DirectX 12 gaming workloads, the Intel Arc B390 is clearly faster, winning the only shared benchmark by 25.6%. That is a substantial margin, and it places the Arc B390 ahead of its nearest rivals (GeForce GT 520MX at 1.3% behind, GeForce 800M at 1.5%, GeForce GT 625 OEM at 2.5%, GeForce GT 710 at 2.7%) by a much wider gap than the RX 7400 holds over its own peers.

However, the RX 7400 has a far richer benchmark profile. Its average score of 2467 is 66% higher than the Arc B390's 1482, and its 17th percentile rank versus 9th indicates broader competence across multiple workload types. The RX 7400's nearest rivals are within 1.1% to 1.9% of its average score, meaning it sits in a tightly contested cluster of low-end parts. The Arc B390's nearest rivals are all within 1.3% to 2.7%, a similarly tight cluster but at a lower absolute level.

The architectural data further complicates the picture. The RX 7400 has more shading units, more TMUs, more ROPs, more RT cores, more than double the FP32 throughput, and a dedicated 8 GB GDDR6 memory subsystem with 288.0 GB/s bandwidth. The Arc B390 relies on system shared memory, making its performance dependent on the host platform. The RX 7400 is a discrete GPU with its own memory and cooling, while the Arc B390 is an integrated part with an 80 W TDP, higher than the RX 7400's 43 W despite being integrated.

The choice depends on the use case. For users who need a self-contained GPU with predictable memory performance, the RX 7400 is the only option with fixed specifications. For users who prioritize the single recorded modern DirectX 12 benchmark, the Arc B390 delivers a 25.6% advantage. The RX 7400's higher average score and percentile rank suggest it handles a wider range of workloads more consistently, while the Arc B390's advantage is concentrated in the one test where both were measured. Neither part has a launch MSRP recorded in the database, so price cannot factor into the analysis. The recorded data shows a modern synthetic benchmark win for Intel, but a broader performance profile for AMD.