Intel Arc Pro B60 Dual vs NVIDIA RTX PRO 4000 Blackwell Comparison

Where Each One Wins

The recorded data splits these two workstation GPUs into clearly different territories. The NVIDIA RTX PRO 4000 Blackwell holds every benchmark win in the database, with nine recorded test scores covering DirectX 9 through 12, Vulkan, compute, and 2D/3D graphics. The Intel Arc Pro B60 Dual has no recorded benchmark scores, which places it at the 50th percentile of all GPUs in the database, while the NVIDIA card sits at the 72nd percentile. This percentile gap indicates that the Intel card, based on the available data, lands in the middle of the pack, whereas the NVIDIA card outperforms the majority of tracked GPUs.

The use-case split is defined by what each card can physically deliver. The NVIDIA RTX PRO 4000 Blackwell offers 8,960 shading units, 280 tensor cores, and 70 RT cores, making it the choice for workloads that leverage CUDA-like parallel processing, ray tracing, and AI acceleration. Its FP32 throughput of 36.83 TFLOPS and FP16 throughput of 36.83 TFLOPS at a 1:1 ratio means compute-heavy tasks see no penalty when switching precision. The Intel Arc Pro B60 Dual, with 2,560 shading units and 20 RT cores, delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 at a 2:1 ratio, which positions it as a capable entry for graphics and light compute, but the data shows it is outmatched in raw throughput.

Memory bandwidth also splits the field. The NVIDIA card uses 24 GB of GDDR7 on a 192-bit bus, achieving 672.0 GB/s, while the Intel card uses 24 GB of GDDR6 on the same bus width, achieving 456.0 GB/s. For workloads that stream large datasets, such as 3D rendering or video processing, the NVIDIA card has a 47% bandwidth advantage. The Intel card does hold one structural advantage: its PCIe 5.0 x8 interface, while narrower than the NVIDIA card’s PCIe 5.0 x16, still supports modern transfer rates, but the x16 width on the NVIDIA card provides more headroom for data-intensive tasks.

Architecture Differences

The two GPUs come from different architectural generations and design philosophies. The Intel Arc Pro B60 Dual uses the BMG-G21 chip based on Xe2-HPG architecture, belonging to the Battlemage (Pro Series) generation. The NVIDIA RTX PRO 4000 Blackwell uses the GB203 chip based on Blackwell 2.0 architecture, belonging to the Blackwell PRO W (x000) generation. Both are fabricated on a 5 nm process at TSMC, but the transistor counts diverge sharply: the NVIDIA chip packs 45,600 million transistors on a 378 mm² die, yielding a density of 120.6M per mm², while the Intel chip contains 19,600 million transistors on a 272 mm² die, yielding 72.1M per mm². This 2.3x transistor advantage on the NVIDIA side explains its higher shading unit count and tensor core availability.

Clock behavior differs as well. The Intel card has a higher base clock of 2000 MHz and a boost clock of 2400 MHz, compared to the NVIDIA card’s 1230 MHz base and 2055 MHz boost. Despite the lower clocks, the NVIDIA card achieves higher throughput because it has 3.5x more shading units. The Intel card compensates with a higher pixel rate of 192.0 GPixel/s versus 197.3 GPixel/s on the NVIDIA card, a narrow margin, while the NVIDIA card leads in texture rate at 575.4 GTexel/s versus 384.0 GTexel/s. Memory type and speed also differ: the Intel card uses GDDR6 at 2375 MHz (19 Gbps effective), while the NVIDIA card uses GDDR7 at 1750 MHz (28 Gbps effective), which explains the bandwidth delta.

Power and physical design present a stark contrast. The Intel Arc Pro B60 Dual draws 400 W TDP, requires an 800 W suggested PSU, spans 300 mm in length, and occupies a dual-slot width. The NVIDIA RTX PRO 4000 Blackwell draws 140 W TDP, requires a 300 W suggested PSU, measures 241 mm in length, and fits a single-slot width. Both use a single 16-pin power connector, but the NVIDIA card’s efficiency is evident: it delivers nearly 3x the FP32 throughput at 35% of the power draw. Display outputs differ: the Intel card provides 4x mini-DisplayPort 2.1, while the NVIDIA card provides 4x DisplayPort 2.1b. The NVIDIA card also supports a wider bus interface at PCIe 5.0 x16 versus the Intel card’s x8.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two cards, so the comparison relies on the NVIDIA card’s recorded scores and the Intel card’s absence of scores. The NVIDIA RTX PRO 4000 Blackwell achieves a 3DMark Steel Nomad DX12 score of 4,648, a Geekbench Vulkan score of 194,168, and a Passmark G3D score of 28,427. Its Passmark GPU Compute score is 14,805. These numbers place it in the 72nd percentile of all GPUs, with an average benchmark score of 27,135.

The nearest rivals for the NVIDIA card, based on the database, include the AMD Radeon RX 6700 XT with an average score of 27,425 and a delta of -1.1%, the NVIDIA GeForce RTX 4070 Mobile at 27,435 with a delta of -1.1%, the NVIDIA GeForce RTX 3090 at 27,565 with a delta of -1.6%, and the NVIDIA RTX A4000 at 26,683 with a delta of +1.7%. This means the RTX PRO 4000 Blackwell trails the RTX 3090 by 1.6% but leads the RTX A4000 by 1.7%. The Intel Arc Pro B60 Dual has no such rival data, so its standing can only be inferred from its 50th percentile placement, which is well below the NVIDIA card’s 72nd percentile.

The biggest wins for the NVIDIA card are not direct comparisons but structural. Its FP32 throughput of 36.83 TFLOPS is 3x the Intel card’s 12.29 TFLOPS. Its memory bandwidth of 672.0 GB/s is 47% higher than the Intel card’s 456.0 GB/s. Its tensor core count of 280 versus none listed on the Intel card means AI and machine learning workloads have no equivalent on the Intel side. The Intel card does win on clock speed, with a 2400 MHz boost versus 2055 MHz on the NVIDIA card, and on FP16 efficiency, achieving 24.58 TFLOPS at half the FP32 rate, which indicates a 2:1 ratio that can benefit certain mixed-precision workloads where the NVIDIA card runs at a 1:1 ratio.

FAQ

Q: Which card has higher raw compute performance?

A: The NVIDIA RTX PRO 4000 Blackwell delivers 36.83 TFLOPS FP32, which is 3x the Intel Arc Pro B60 Dual’s 12.29 TFLOPS. The NVIDIA card also achieves 36.83 TFLOPS FP16 at a 1:1 ratio, while the Intel card reaches 24.58 TFLOPS FP16 at a 2:1 ratio.

Q: How do the memory subsystems compare?

A: Both cards have 24 GB of memory on a 192-bit bus, but the NVIDIA card uses GDDR7 at 28 Gbps effective for 672.0 GB/s bandwidth, while the Intel card uses GDDR6 at 19 Gbps effective for 456.0 GB/s. The NVIDIA card provides 47% more bandwidth.

Q: What are the power requirements?

A: The Intel Arc Pro B60 Dual has a 400 W TDP and requires an 800 W suggested PSU, while the NVIDIA RTX PRO 4000 Blackwell has a 140 W TDP and requires a 300 W suggested PSU. Both use a single 16-pin power connector.

Q: Which card supports ray tracing and AI workloads?

A: The NVIDIA card has 70 RT cores and 280 tensor cores, while the Intel card has 20 RT cores and no listed tensor cores. The NVIDIA card’s tensor cores enable AI acceleration that the Intel card lacks.

Q: How do the physical dimensions differ?

A: The Intel card measures 300 mm in length, 110 mm in height, and 40 mm in width, occupying a dual-slot width. The NVIDIA card measures 241 mm in length, 111 mm in height, and 20 mm in width, fitting a single-slot width.

Q: What is the performance percentile ranking?

A: The NVIDIA RTX PRO 4000 Blackwell ranks in the 72nd percentile of all GPUs with an average benchmark score of 27,135. The Intel Arc Pro B60 Dual ranks in the 50th percentile with no recorded average benchmark score.

Specification Differences

The two cards differ in nearly every measurable specification. The chip and architecture differ: Intel uses BMG-G21 with Xe2-HPG, while NVIDIA uses GB203 with Blackwell 2.0. Transistor count is 19,600 million on Intel versus 45,600 million on NVIDIA, with die sizes of 272 mm² and 378 mm² respectively. Transistor density is 72.1M per mm² on Intel versus 120.6M per mm² on NVIDIA. Base clocks are 2000 MHz on Intel versus 1230 MHz on NVIDIA, and boost clocks are 2400 MHz versus 2055 MHz. Memory clocks are 2375 MHz (19 Gbps effective) on Intel versus 1750 MHz (28 Gbps effective) on NVIDIA.

Memory type differs: GDDR6 on Intel versus GDDR7 on NVIDIA. Bandwidth is 456.0 GB/s versus 672.0 GB/s. Shading units are 2,560 versus 8,960, TMUs are 160 versus 280, ROPs are 80 versus 96, and RT cores are 20 versus 70. Tensor cores are not listed for Intel but are 280 on NVIDIA. Pixel rates are 192.0 GPixel/s versus 197.3 GPixel/s, and texture rates are 384.0 GTexel/s versus 575.4 GTexel/s. FP32 is 12.29 TFLOPS versus 36.83 TFLOPS, and FP16 is 24.58 TFLOPS (2:1) versus 36.83 TFLOPS (1:1). TDP is 400 W versus 140 W, slot width is dual-slot versus single-slot, suggested PSU is 800 W versus 300 W, and bus interface is PCIe 5.0 x8 versus PCIe 5.0 x16. Display outputs are 4x mini-DisplayPort 2.1 versus 4x DisplayPort 2.1b. Dimensions are 300 mm x 110 mm x 40 mm versus 241 mm x 111 mm x 20 mm. Release dates are September 2025 for Intel and March 2025 for NVIDIA.

The Verdict

The data points to the NVIDIA RTX PRO 4000 Blackwell as the superior workstation GPU for compute, AI, and memory-intensive tasks. It holds a 3x FP32 advantage, a 47% memory bandwidth advantage, dedicated tensor cores, and a 72nd percentile ranking versus the Intel card’s 50th percentile. Its 140 W TDP and single-slot design make it far easier to integrate into dense systems, and its 280 tensor cores provide capabilities the Intel card cannot match. The Intel Arc Pro B60 Dual, with its 400 W TDP and dual-slot footprint, offers a higher base clock and a 2:1 FP16 ratio, which may benefit specific mixed-precision graphics workloads, but the lack of recorded benchmark scores and the absence of tensor cores limit its appeal in AI-heavy environments.

For users prioritizing raw compute, AI inference, or high-bandwidth data streaming, the NVIDIA card is the clear choice based on the recorded data. For users who need a dual-slot card with a higher boost clock and are working primarily in standard graphics pipelines, the Intel card remains an option, but the performance gap is substantial. The NVIDIA card also leads in efficiency, delivering more than 3x the FP32 throughput at 35% of the power draw. The Intel card’s only recorded advantages are its higher clocks and its FP16 2:1 ratio, which does not compensate for the overall throughput deficit. The verdict from the data is unambiguous: the NVIDIA RTX PRO 4000 Blackwell dominates this comparison across every measured category.