Intel Arc B390 vs Intel Arc Pro A60M Comparison

Head-to-Head Benchmarks

The recorded data contains a single benchmark result for the Intel Arc B390: a 3DMark Steel Nomad DX12 score of 1482. The Intel Arc Pro A60M has no benchmark entries in the database, meaning a direct numerical comparison between the two parts cannot be established from the available measurements.

The Arc B390's score places it at the 9th percentile among all GPUs. Its nearest rivals, based on average scores, are all older NVIDIA parts. The B390 is 1.3% ahead of the GeForce GT 520MX (1463), 1.5% ahead of the GeForce 800M (1460), 2.5% ahead of the GeForce GT 625 OEM (1446), and 2.7% ahead of the GeForce GT 710 (1443). These deltas are narrow, indicating that in the Steel Nomad workload, the B390 operates in a performance tier populated by entry-level discrete parts from a previous generation.

The Arc Pro A60M, by contrast, sits at the 50th percentile across all GPUs in the database, with an average benchmark score of zero because no individual benchmark records exist. The percentile figure suggests that the A60M occupies a substantially higher position in the overall performance distribution than the B390, even though the absence of a direct test score prevents a precise percentile-to-score translation. The B390's 9th percentile placement against the A60M's 50th percentile is the only head-to-head signal available, and it indicates a wide gulf in expected performance class.

Because the head-to-head benchmark array is empty, the analysis relies on the percentile fields and the rival comparisons for the B390. The data shows the B390 clustering with GPUs that score in the low-to-mid 1400s, while the A60M's percentile implies it ranks near the middle of all recorded GPUs. No wins are recorded for either part in direct comparison, as no such tests exist in the database.

FAQ

Q: Which GPU has the higher recorded benchmark score?

A: The Intel Arc B390 has a recorded 3DMark Steel Nomad DX12 score of 1482. The Intel Arc Pro A60M has no benchmark scores recorded, so no direct score comparison is possible.

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

A: The B390 leads the 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% in average benchmark scores.

Q: What percentile does each GPU occupy?

A: The Arc B390 sits at the 9th percentile among all GPUs. The Arc Pro A60M sits at the 50th percentile.

Q: Does the Arc Pro A60M have any benchmark entries?

A: No, the database lists no benchmark results for the Intel Arc Pro A60M, and its average benchmark score is recorded as zero.

Q: Which GPU has more shading units?

A: The Arc Pro A60M has 2048 shading units, while the Arc B390 has 1536 shading units.

Q: What is the process node for each chip?

A: The Arc B390 uses a 3 nm process from Intel, while the Arc Pro A60M uses a 6 nm process from TSMC.

Architecture Differences

The two GPUs derive from different Intel architectures and chips. The Arc B390 uses the Panther Lake chip with the Xe3-LPG architecture, part of the Arc Graphics-M (Panther Lake) generation. The Arc Pro A60M uses the DG2-256 chip with the Xe-HPG architecture, part of the Alchemist (Pro-Series Mobile) generation.

The B390 is built on a 3 nm process at Intel's foundry. The A60M uses a 6 nm process at TSMC. The A60M has a documented transistor count of 11,500 million, a die size of 269 mm², and a transistor density of 42.8 million per mm². The B390's transistor count and die size are listed as unknown.

The A60M has a larger execution resource configuration: 2048 shading units, 128 texture mapping units, 64 render output units, and 16 ray tracing cores. The B390 has 1536 shading units, 48 TMUs, 24 ROPs, and 12 ray tracing cores. Despite the A60M's higher unit counts, its FP32 throughput is lower at 5.325 TFLOPS compared to the B390's 7.680 TFLOPS. The same pattern holds for FP16: the A60M delivers 10.65 TFLOPS (2:1) while the B390 delivers 15.36 TFLOPS (2:1).

Pixel and texture rates also differ. The A60M reaches 83.20 GPixel/s and 166.4 GTexel/s. The B390 reaches 60.00 GPixel/s and 120.0 GTexel/s. The A60M's higher ROP and TMU counts explain its advantage in these fill-rate metrics despite the B390's higher compute throughput.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Neither lists tensor cores. The B390's memory subsystem is entirely system-shared, with bandwidth described as system dependent. The A60M uses dedicated GDDR6 memory with a 128-bit bus and 256.0 GB/s bandwidth.

Specification Differences

The Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The Arc Pro A60M has a base clock of 900 MHz and a boost clock of 1300 MHz. The A60M's memory clock is 2000 MHz with 16 Gbps effective transfer rate; the B390's memory clock is listed as system shared.

Memory configuration differs sharply. The B390 uses system-shared memory with system-shared size, bus width, and system-dependent bandwidth. The A60M has 8 GB of GDDR6 on a 128-bit bus with 256.0 GB/s bandwidth.

Power draw: the B390 has a TDP of 80 W, the A60M has a TDP of 95 W. Both are integrated form factors (IGP) with portable-device-dependent display outputs. The B390 has no power connectors; the A60M's power connector field is null. The B390's bus interface is IGP, while the A60M uses PCIe 4.0 x16.

Release dates differ: the B390 was released on 2026-01-26, and the A60M on 2023-06-05. Both are active production parts. Neither has a launch MSRP listed. Neither lists dimensions. The B390's predecessor and successor fields are null, as are the A60M's.

The Verdict

The data presents a split picture. In raw compute throughput, the Arc B390 leads with 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16, versus the A60M's 5.325 TFLOPS and 10.65 TFLOPS. In fill-rate and memory bandwidth, the A60M leads with 83.20 GPixel/s, 166.4 GTexel/s, and 256.0 GB/s of dedicated bandwidth, versus the B390's 60.00 GPixel/s, 120.0 GTexel/s, and system-dependent shared memory.

The percentile data complicates a simple verdict. The B390's sole benchmark score of 1482 places it at the 9th percentile, near older NVIDIA parts like the GT 710 and GT 625 OEM. The A60M has no benchmark scores but sits at the 50th percentile. If the percentile fields reflect real-world standing, the A60M is expected to perform in a much higher tier than the B390's only recorded result suggests.

The A60M also carries more shading units, TMUs, ROPs, and ray tracing cores, plus a dedicated memory interface. The B390 counters with a smaller process node, higher clocks, and higher compute figures. The verdict depends on which metric is weighted more: the B390 wins on paper compute rates and clock speed, while the A60M wins on resource counts, memory, and overall percentile ranking.

Where Each One Wins

The Arc B390 wins in compute-heavy applications that scale with FP32 or FP16 throughput. Its 7.680 TFLOPS FP32 and 15.36 TFLOPS FP16 exceed the A60M's respective 5.325 TFLOPS and 10.65 TFLOPS. Its boost clock of 2500 MHz is nearly double the A60M's 1300 MHz. For workloads that rely on shader math rather than memory bandwidth, the B390's architecture appears better suited.

The Arc Pro A60M wins in bandwidth-sensitive and fill-rate-bound scenarios. Its 256.0 GB/s dedicated GDDR6 bandwidth removes dependence on system memory, which the B390 relies on with system-dependent bandwidth. The A60M's 83.20 GPixel/s pixel rate and 166.4 GTexel/s texture rate exceed the B390's 60.00 GPixel/s and 120.0 GTexel/s. Its 16 ray tracing cores and 2048 shading units provide more parallel resources for geometry and ray traversal work.

The B390's 80 W TDP is lower than the A60M's 95 W, making it the more power-efficient part on paper. The A60M's PCIe 4.0 x16 interface gives it a conventional external bus, while the B390 uses an integrated interface. For systems where the GPU must handle high-resolution textures or large frame buffers, the A60M's 8 GB GDDR6 is the clear choice versus the B390's shared memory. For compute-centric tasks where memory latency is less critical, the B390's higher clock and compute rates provide the advantage.

The percentile gap remains the strongest single indicator: the B390 at the 9th percentile and the A60M at the 50th. The recorded benchmark for the B390 places it near the GT 710 tier, while the A60M's percentile implies a far higher standing. Any selection between the two should weigh the B390's compute and efficiency figures against the A60M's memory, fill-rate, and overall percentile position.