AMD Radeon 740M vs Intel Arc B390 Comparison

Where Each One Wins

The recorded benchmark data splits these two integrated GPUs into entirely different performance classes. The AMD Radeon 740M holds the clear advantage in general-purpose and graphics compute workloads. Its Geekbench OpenCL score of 10,172 and Vulkan score of 15,568 place it in the 53rd percentile of all GPUs in the database. The Intel Arc B390, by contrast, has a single recorded 3DMark Steel Nomad DX12 score of 1,482, which puts it in the 9th percentile. That is a massive gap in raw measured performance.

The Radeon 740M wins every direct comparison available in the database. Its average benchmark score of 12,870 is roughly 8.7 times higher than the Arc B390's average of 1,482. In OpenCL compute, the Radeon 740M delivers 10,172 points, a figure that places it alongside discrete graphics cards from several generations ago. Its nearest rivals include the AMD Radeon RX 580 with an average score of 12,928 (the 740M trails by 0.4%) and the NVIDIA GeForce GTX 590 at 12,830 (the 740M leads by 0.3%). These are desktop-class discrete GPUs, and the integrated Radeon 740M trades blows with them within a fraction of a percent.

The Arc B390's single benchmark result of 1,482 sits near the NVIDIA GeForce GT 520MX (1,463, Intel leads by 1.3%) and the NVIDIA GeForce GT 710 (1,443, Intel leads by 2.7%). Those are entry-level discrete cards from over a decade ago. The data indicates the Arc B390 is positioned at the very low end of the performance spectrum, while the Radeon 740M is a mid-range performer by comparison.

For use cases, the Radeon 740M is the pick for any workload that stresses compute throughput, shader execution, or Vulkan-based rendering. The Arc B390 does not have a single benchmark category where it posts a higher score. Its only measured result is in DX12 via 3DMark Steel Nomad, and that score is far below the Radeon's OpenCL and Vulkan results. The Radeon 740M wins on every axis the database measures.

Architecture Differences

The two chips come from different foundries and process nodes. The AMD Radeon 740M uses the Phoenix2 chip built on TSMC's 4 nm process with RDNA 3.0 architecture. It packs 20,900 million transistors onto a 137 mm² die, giving a transistor density of 152.6 million transistors per square millimeter. The Intel Arc B390 uses the Panther Lake chip built on Intel's own 3 nm process with Xe3-LPG architecture. Intel's transistor count and die size are not recorded in the database.

The compute resources differ dramatically. The Radeon 740M has 256 shading units, 16 texture mapping units, 8 render output units, and 4 ray tracing cores. The Arc B390 has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. That is a 6x advantage in shader count, 3x in TMUs, 3x in ROPs, and 3x in ray tracing cores for Intel. Yet the actual benchmark results show AMD far ahead, which indicates the architectural efficiency differences are substantial.

Clock speeds tell part of the story. The Radeon 740M runs at an 800 MHz base clock and boosts to 2,800 MHz. The Arc B390 has a 300 MHz base clock and a 2,500 MHz boost. AMD's higher boost clock helps, but the raw throughput figures reveal the real gap. The Radeon 740M delivers 2.867 TFLOPS of FP32 compute and the same 2.867 TFLOPS for FP16 (at a 1:1 ratio). The Arc B390 delivers 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (at a 2:1 ratio). Intel's theoretical FP32 throughput is 2.7x higher, yet its measured DX12 score is a fraction of AMD's measured Vulkan and OpenCL scores.

Pixel and texture rates follow the same pattern. The Radeon 740M produces 22.40 GPixel/s and 44.80 GTexel/s. The Arc B390 produces 60.00 GPixel/s and 120.0 GTexel/s. Again, Intel's theoretical numbers are roughly 2.7x higher. The database's benchmark results contradict those theoretical advantages, suggesting the Arc B390's real-world execution does not match its specification sheet.

Both GPUs share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use system-shared memory with system-dependent bandwidth. The Radeon 740M connects via PCIe 4.0 x8, while the Arc B390's bus interface is listed simply as IGP. Both are integrated parts with no power connectors and no dedicated slot width beyond the IGP designation. The Radeon 740M has a 45 W TDP, while the Arc B390 has an 80 W TDP.

The Verdict

The database shows a one-sided comparison. The AMD Radeon 740M is the superior part by every measured metric. Its average benchmark score of 12,870 versus the Arc B390's 1,482 means the Radeon is roughly 8.7x faster on average. The Radeon's percentile ranking of 53rd versus the Arc's 9th percentile confirms this is not a close contest.

The Radeon 740M's nearest rivals are all discrete desktop GPUs: the AMD Radeon RX 580 (0.4% ahead), the AMD FirePro W5100 (0.2% behind), the AMD Radeon Pro 455 (0.3% behind), and the NVIDIA GeForce GTX 590 (0.3% behind). This positions the integrated Radeon 740M in the same performance class as those older discrete cards. The Arc B390's nearest rivals are the NVIDIA GeForce GT 520MX (1.3% behind), GeForce 800M (1.5% behind), GT 625 OEM (2.5% behind), and GT 710 (2.7% behind). Those are all low-end parts from a much earlier era.

For a builder choosing between these two integrated options, the data points firmly to the Radeon 740M. It delivers higher scores in both OpenCL and Vulkan, while the Arc B390's single DX12 score cannot compete. The Arc B390 does have more shading units, more TMUs, more ROPs, more ray tracing cores, and higher theoretical FP32 throughput, but the recorded benchmark results do not reflect those advantages. The Radeon 740M is the practical choice for anyone who needs usable integrated graphics performance today.

FAQ

Q: How does the AMD Radeon 740M compare to the Intel Arc B390 in average benchmark scores?

A: The Radeon 740M has an average benchmark score of 12,870, while the Arc B390 averages 1,482. That puts the Radeon roughly 8.7 times higher.

Q: Which GPU has the higher percentile ranking in the database?

A: The Radeon 740M ranks in the 53rd percentile of all GPUs, while the Arc B390 ranks in the 9th percentile.

Q: What are the closest rivals to the Radeon 740M?

A: The nearest rivals are the AMD Radeon RX 580 (12,928, 0.4% ahead), the AMD FirePro W5100 (12,847, 0.2% behind), the AMD Radeon Pro 455 (12,831, 0.3% behind), and the NVIDIA GeForce GTX 590 (12,830, 0.3% behind).

Q: What are the closest rivals to the Arc B390?

A: The nearest rivals are the NVIDIA GeForce GT 520MX (1,463, 1.3% behind), the NVIDIA GeForce 800M (1,460, 1.5% behind), the NVIDIA GeForce GT 625 OEM (1,446, 2.5% behind), and the NVIDIA GeForce GT 710 (1,443, 2.7% behind).

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What are the TDP ratings for each GPU?

A: The Radeon 740M is rated at 45 W, while the Arc B390 is rated at 80 W.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries between these two GPUs. However, the individual recorded scores provide a clear comparison. The Radeon 740M's Geekbench OpenCL score is 10,172. The Arc B390 has no OpenCL result recorded. The Radeon 740M's Geekbench Vulkan score is 15,568. The Arc B390 has no Vulkan result recorded. The Arc B390's only result is a 3DMark Steel Nomad DX12 score of 1,482. The Radeon 740M has no 3DMark Steel Nomad result recorded.

The closest available comparison comes through the average benchmark scores. The Radeon 740M averages 12,870 across its two recorded tests. The Arc B390 averages 1,482 across its single test. That is a difference of 11,388 points in favor of AMD. Even if the Radeon's lowest single score (10,172 in OpenCL) is compared to the Arc's only score (1,482), the Radeon still leads by roughly 6.9x.

The nearest-rival data reinforces the gap. The Radeon 740M competes with the Radeon RX 580, a desktop discrete GPU that scores 12,928. The Arc B390 competes with the GeForce GT 710, a card that scores 1,443. The performance class difference between those two rival groups is enormous, and the two integrated GPUs sit squarely within their respective groups.

The Radeon 740M's Vulkan score of 15,568 is particularly strong. It exceeds the average scores of all four of its nearest rivals, which range from 12,830 to 12,928. That means the Radeon 740M's Vulkan performance is roughly 20% to 21% above its own average, and well above the discrete cards it otherwise trades blows with. The OpenCL score of 10,172 is below the average of the Radeon RX 580 (12,928) by about 21%, but it is still far above the Arc B390's entire performance envelope.

The Arc B390's single score of 1,482 does not come close to any Radeon 740M result. The Radeon 740M's lowest recorded score is 10,172, which is 6.9x higher than the Arc B390's best. The Radeon 740M's highest score is 15,568, which is 10.5x higher. No benchmark category in the database shows the Arc B390 winning.

Specification Differences

The two GPUs differ across nearly every recorded specification. The Radeon 740M uses the Phoenix2 chip on TSMC's 4 nm process with RDNA 3.0 architecture. The Arc B390 uses the Panther Lake chip on Intel's 3 nm process with Xe3-LPG architecture. The Radeon packs 20,900 million transistors onto a 137 mm² die with a density of 152.6M per mm². The Arc B390's transistor count and die size are unknown.

Clock speeds differ: the Radeon 740M has an 800 MHz base and 2,800 MHz boost, while the Arc B390 has a 300 MHz base and 2,500 MHz boost. Both use system-shared memory with system-dependent bandwidth.

The compute unit counts favor Intel on paper. The Radeon 740M has 256 shading units, 16 TMUs, 8 ROPs, and 4 ray tracing cores. The Arc B390 has 1,536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. The Arc B390 has 6x the shading units, 3x the TMUs, 3x the ROPs, and 3x the ray tracing cores.

Theoretical throughput favors Intel as well. The Radeon 740M produces 2.867 TFLOPS FP32 and 2.867 TFLOPS FP16 (1:1 ratio). The Arc B390 produces 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 (2:1 ratio). Pixel rates are 22.40 GPixel/s for AMD versus 60.00 GPixel/s for Intel. Texture rates are 44.80 GTexel/s for AMD versus 120.0 GTexel/s for Intel.

Power draw differs: the Radeon 740M is rated at 45 W TDP, the Arc B390 at 80 W TDP. Neither has power connectors. The Radeon 740M uses a PCIe 4.0 x8 bus interface, while the Arc B390's interface is listed as IGP. Display outputs are motherboard dependent for AMD and portable device dependent for Intel.

Release dates differ by two years: the Radeon 740M launched on January 30, 2024, and the Arc B390 on January 26, 2026. Both are listed as Active in production status. The Radeon 740M's predecessor is listed as Navi II IGP and successor as Navi III IGP, while the Arc B390 has no predecessor or successor recorded. Neither has a launch MSRP in the database.