AMD Radeon 8065S vs Intel Arc B390 Comparison

Head-to-Head Benchmarks

The recorded data for the AMD Radeon 8065S contains no benchmark entries, while the Intel Arc B390 has a single 3DMark Steel Nomad DX12 score of 1482. This makes direct numerical comparison impossible on a test-by-test basis, so the analysis must rely on architectural specifications and the one recorded score.

The Intel Arc B390's 1482 score places it in the 9th percentile of all GPUs in the database. Its nearest rivals in the recorded data are all NVIDIA parts from older generations. The Arc B390 leads the NVIDIA GeForce GT 520MX by 1.3%, the GeForce 800M by 1.5%, the GeForce GT 625 OEM by 2.5%, and the GeForce GT 710 by 2.7%. These deltas are narrow, indicating that the Arc B390 sits in a performance class populated by entry-level mobile parts.

The AMD Radeon 8065S carries no benchmark score in the database, but its theoretical specifications suggest a substantially higher compute ceiling. The Radeon 8065S delivers 15.36 TFLOPS of FP32 compute, exactly double the 7.680 TFLOPS of the Arc B390. In FP16 workloads, both GPUs reach 15.36 TFLOPS, but the Radeon achieves this at a 1:1 ratio with FP32, while the Arc B390 requires a 2:1 ratio, meaning it halves its FP32 throughput to reach the same FP16 figure.

Pixel throughput shows a similar gap. The Radeon 8065S renders 192.0 GPixel/s versus 60.00 GPixel/s for the Arc B390, a 3.2x advantage. Texture fill rates differ by a factor of four: 480.0 GTexel/s for the AMD part versus 120.0 GTexel/s for the Intel part. These are raw specification comparisons, not measured benchmark results, but they indicate the Radeon 8065S was designed for a much higher workload ceiling.

The Arc B390's nearest rival data confirms its positioning. A 1.3% lead over the GeForce GT 520MX and a 2.7% lead over the GeForce GT 710 represent incremental improvements over decade-old parts, not generational leaps. The Radeon 8065S has no nearest rivals recorded, which means the database has insufficient comparable measurements to place it relative to other GPUs.

The Verdict

The data presents a clear split. The Intel Arc B390 is the only part with a recorded benchmark score, and that score places it at the 9th percentile of all GPUs. Its nearest rivals are all NVIDIA entry-level parts from older generations, and its advantage over them ranges from 1.3% to 2.7%. This indicates a low-end integrated GPU with modest absolute performance.

The AMD Radeon 8065S, by contrast, has no recorded benchmark scores but carries specifications that position it far above the Arc B390's class. The 15.36 TFLOPS FP32 figure, the 192.0 GPixel/s pixel rate, and the 480.0 GTexel/s texture rate all point to a part with several times the theoretical throughput of the Intel chip. The Radeon also uses 2560 shading units, 160 texture mapping units, and 64 raster operation units, versus 1536, 48, and 24 respectively for the Arc B390.

Users seeking a GPU for demanding 3D workloads would select the Radeon 8065S based on its specification advantage. Users seeking a low-power integrated solution for basic graphics tasks would select the Arc B390, which has a recorded benchmark result showing functional performance at the entry level. The Radeon 8065S carries a 55 W TDP, while the Arc B390 consumes 80 W, so the AMD part delivers higher theoretical performance at lower power draw.

The Arc B390's 9th percentile ranking means it outperforms only a small fraction of the database's GPU population. The Radeon 8065S sits at the 50th percentile, indicating the database places it at the median of all GPUs, though this figure likely reflects its specification-based classification rather than measured results.

Architecture Differences

The AMD Radeon 8065S uses the Gorgon Halo chip built on TSMC's 4 nm process, with a die size of 308 mm². The architecture is RDNA 3.5, belonging to the Navi Mobile (RX 8000M) generation. The Intel Arc B390 uses the Panther Lake chip on Intel's 3 nm process, with an unknown die size. Its architecture is Xe3-LPG, belonging to the Arc Graphics-M (Panther Lake) generation.

The Radeon 8065S has a base clock of 1295 MHz and a boost clock of 3000 MHz. The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The AMD part's boost clock exceeds the Intel part's by 500 MHz, contributing to its higher fill rates and compute throughput.

Both GPUs use system shared memory, making bandwidth dependent on the host system. Neither has dedicated VRAM, and both are classified as integrated graphics processors (IGP) with no power connectors required. The Radeon 8065S connects via PCIe 5.0 x16, while the Arc B390 uses an unspecified IGP bus interface.

The Radeon 8065S includes 40 ray tracing cores, while the Arc B390 has 12. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Radeon's FP16 compute runs at a 1:1 ratio with FP32, while the Arc B390's FP16 runs at a 2:1 ratio, meaning the Intel part trades FP32 throughput for FP16 work.

The Radeon 8065S has a release date of December 31, 2025, and lists Polaris Mobile as its predecessor. The Arc B390 has a release date of January 26, 2026, and lists no predecessor. The Radeon was built by TSMC, while Intel fabricated the Arc B390 in-house. The Radeon's 308 mm² die size is known, while the Arc B390's die size is recorded as unknown.

FAQ

Q: Which GPU has a higher FP32 compute throughput?

A: The AMD Radeon 8065S delivers 15.36 TFLOPS of FP32 compute, exactly double the 7.680 TFLOPS of the Intel Arc B390.

Q: What benchmark score does the Intel Arc B390 have?

A: The Arc B390 records a 3DMark Steel Nomad DX12 score of 1482, which places it in the 9th percentile of all GPUs in the database.

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

A: The Arc B390 leads the NVIDIA GeForce GT 520MX by 1.3%, the GeForce 800M by 1.5%, the GeForce GT 625 OEM by 2.5%, and the GeForce GT 710 by 2.7%.

Q: What is the pixel fill rate of each GPU?

A: The AMD Radeon 8065S renders 192.0 GPixel/s, while the Intel Arc B390 renders 60.00 GPixel/s.

Q: Do both GPUs use dedicated video memory?

A: No, both use System Shared memory, with bandwidth recorded as System Dependent.

Q: What is the TDP of each GPU?

A: The AMD Radeon 8065S has a TDP of 55 W, while the Intel Arc B390 has a TDP of 80 W.

Q: Which GPU has more ray tracing cores?

A: The AMD Radeon 8065S includes 40 ray tracing cores, while the Intel Arc B390 has 12.

Where Each One Wins

The AMD Radeon 8065S wins decisively in raw specification categories. Its 15.36 TFLOPS FP32 compute doubles the Arc B390's 7.680 TFLOPS. The pixel rate of 192.0 GPixel/s triples the Arc B390's 60.00 GPixel/s, and the texture rate of 480.0 GTexel/s quadruples the Intel part's 120.0 GTexel/s. The Radeon also carries more shading units (2560 versus 1536), more texture mapping units (160 versus 48), and more raster operation units (64 versus 24). Its boost clock of 3000 MHz exceeds the Arc B390's 2500 MHz, and its 40 ray tracing cores outnumber the Arc B390's 12. The Radeon achieves all of this at a lower TDP of 55 W versus 80 W.

The Intel Arc B390 wins in the only measured benchmark category. Its 3DMark Steel Nomad DX12 score of 1482 is the sole recorded benchmark among the two parts, placing it above its nearest rivals in the database. The Arc B390's nearest rivals, the GeForce GT 520MX, GeForce 800M, GeForce GT 625 OEM, and GeForce GT 710, all score lower, giving the Intel part a measurable if narrow victory in each comparison. The Arc B390 also uses a smaller process node at 3 nm versus 4 nm, though both are integrated GPUs with no power connectors and no dedicated memory.

The Arc B390's FP16 throughput of 15.36 TFLOPS matches the Radeon 8065S, but the Intel part achieves this only through a 2:1 ratio with FP32, whereas the Radeon runs FP16 at 1:1. In workloads that rely heavily on FP16, the Arc B390 can match the Radeon's raw output, but it sacrifices FP32 performance to do so.

The Radeon 8065S's 50th percentile ranking places it at the median of all GPUs in the database, while the Arc B390's 9th percentile places it near the bottom. The Radeon's PCIe 5.0 x16 interface provides a wider connection than the Arc B390's unspecified IGP bus. The Radeon's known die size of 308 mm² suggests a large, capable chip, while the Arc B390's die size remains unrecorded.

For users prioritizing measured performance with a recorded score, the Arc B390 has the only data point. For users prioritizing theoretical compute capability, power efficiency, and architectural resources, the Radeon 8065S dominates every specification category. The Radeon offers higher clocks, more execution units, faster fill rates, and lower power consumption. The Arc B390 offers a verified benchmark result and a smaller manufacturing process. The choice depends on whether a recorded score or raw specification headroom matters more.