Intel Arc Pro B60 Dual vs NVIDIA RTX PRO 6000 Blackwell Comparison

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between the Intel Arc Pro B60 Dual and the NVIDIA RTX PRO 6000 Blackwell. The Intel Arc Pro B60 Dual has no recorded benchmark entries, resulting in an average benchmark score of 0 and a percentile rank of 50 among all GPUs. The NVIDIA RTX PRO 6000 Blackwell, by contrast, has one recorded benchmark result: a 3DMark Steel Nomad DX12 score of 16,408, placing it in the 59th percentile of all GPUs.

The NVIDIA card's single benchmark score positions it in a tight competitive cluster. It sits within 0.6% of the AMD Radeon PRO W7500, which scored 16,415, and within 0.3% of the AMD Radeon RX 5700 XT, which scored 16,361. The AMD Radeon Pro 5600M trails by 0.4% with a score of 16,351. The closest rival from NVIDIA's own lineup, the GeForce RTX 5090 D V2, leads by 0.6% with a score of 16,504. These deltas are marginal, indicating that the RTX PRO 6000 Blackwell's measured performance in this particular DX12 workload is essentially on par with a group of cards spanning multiple vendors and generations.

Without any benchmark data for the Intel Arc Pro B60 Dual, a direct numerical comparison of performance is impossible. The recorded data only allows for a comparison of architectural specifications and theoretical throughput figures. The Intel card's absence from the benchmark database means its real-world performance in standard workloads remains unquantified, while the NVIDIA card's single result provides a reference point for one specific test scenario.

Architecture Differences

The two cards diverge sharply at the architectural level. The Intel Arc Pro B60 Dual uses the BMG-G21 chip based on the Xe2-HPG architecture, part of the Battlemage Pro Series generation. It is fabricated on a 5 nm process at TSMC, with 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1 million transistors per square millimeter. The NVIDIA RTX PRO 6000 Blackwell uses the GB202 chip based on the Blackwell 2.0 architecture, from the Blackwell PRO W (x000) generation. It also uses a 5 nm TSMC process, but packs 92,200 million transistors onto a 750 mm² die, achieving a density of 122.9 million transistors per square millimeter. The NVIDIA die is nearly three times larger physically and contains roughly 4.7 times more transistors.

Memory configurations differ substantially. The Intel card carries 24 GB of GDDR6 memory on a 192-bit bus, with a memory clock of 2375 MHz (19 Gbps effective) and a bandwidth of 456.0 GB/s. The NVIDIA card carries 96 GB of GDDR7 memory on a 512-bit bus, with a memory clock of 1750 MHz (28 Gbps effective) and a bandwidth of 1.79 TB/s. The NVIDIA card offers four times the capacity and roughly four times the bandwidth, reflecting a much wider memory subsystem.

Compute resources show a similar scale of difference. The Intel card has 2,560 shading units, 160 texture mapping units, 80 render output units, and 20 ray tracing cores. The NVIDIA card has 24,064 shading units, 752 texture mapping units, 192 render output units, 188 ray tracing cores, and 752 tensor cores. The Intel card has no tensor core count listed. Pixel rate for the Intel card is 192.0 GPixel/s, while the NVIDIA card reaches 502.5 GPixel/s. Texture rate for Intel is 384.0 GTexel/s, while NVIDIA reaches 1,968.0 GTexel/s.

Clock behavior differs as well. The Intel card has a base clock of 2000 MHz and a boost clock of 2400 MHz. The NVIDIA card has a lower base clock of 1590 MHz but a higher boost clock of 2617 MHz. Floating point throughput is dramatically different: the Intel card delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1 ratio), while the NVIDIA card delivers 126.0 TFLOPS FP32 and 126.0 TFLOPS FP16 (1:1 ratio). The NVIDIA card offers roughly 10 times the FP32 throughput and over 5 times the FP16 throughput.

Power and interface specifications also diverge. The Intel card has a TDP of 400 W with a suggested power supply of 800 W, while the NVIDIA card has a TDP of 600 W with a suggested power supply of 1000 W. Both use a single 16-pin power connector and a dual-slot form factor. The Intel card uses a PCIe 5.0 x8 interface, while the NVIDIA card uses a PCIe 5.0 x16 interface. Display outputs are four mini-DisplayPort 2.1 connectors on the Intel card, versus four DisplayPort 2.1b connectors on the NVIDIA card.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Physical dimensions are similar in length, with the Intel card at 300 mm (11.8 inches) and the NVIDIA card at 304 mm (12 inches). Height differs: the Intel card is 110 mm (4.3 inches), while the NVIDIA card is 137 mm (5.4 inches). Both are 40 mm (1.6 inches) wide.

Where Each One Wins

Based on the recorded data, the NVIDIA RTX PRO 6000 Blackwell wins in nearly every measurable category. It has a higher benchmark score, a higher percentile rank among all GPUs, more memory, higher bandwidth, more shading units, more ray tracing cores, more tensor cores, higher pixel rate, higher texture rate, and higher FP32 and FP16 throughput. It also has a higher boost clock and a wider PCIe interface.

The Intel Arc Pro B60 Dual holds advantages in a few specific areas. Its base clock of 2000 MHz is higher than the NVIDIA base clock of 1590 MHz. Its memory clock of 2375 MHz is higher than the NVIDIA memory clock of 1750 MHz, though the effective data rate is lower (19 Gbps versus 28 Gbps). The Intel card is smaller in physical height at 110 mm versus 137 mm, and it has a lower TDP of 400 W versus 600 W, which may simplify cooling requirements in constrained chassis. It also has a lower suggested power supply rating of 800 W versus 1000 W.

The Intel card was released on 2025-09-04, while the NVIDIA card was released earlier on 2025-03-17. The NVIDIA card lists a predecessor, Workstation Ada, while the Intel card lists no predecessor or successor. The NVIDIA card's launch MSRP is 8,565 USD, while the Intel card's launch MSRP is 1,199 USD.

In terms of raw compute, the NVIDIA card's FP32 throughput of 126.0 TFLOPS is approximately 10.25 times the Intel card's 12.29 TFLOPS. The NVIDIA card's FP16 throughput of 126.0 TFLOPS is approximately 5.13 times the Intel card's 24.58 TFLOPS. The NVIDIA card's texture rate of 1,968.0 GTexel/s is approximately 5.13 times the Intel card's 384.0 GTexel/s. The NVIDIA card's pixel rate of 502.5 GPixel/s is approximately 2.62 times the Intel card's 192.0 GPixel/s.

The NVIDIA card's memory bandwidth of 1.79 TB/s is approximately 3.92 times the Intel card's 456.0 GB/s. The NVIDIA card also has 4 times the memory capacity, 9.4 times the shading units, 4.7 times the texture mapping units, 2.4 times the render output units, and 9.4 times the ray tracing cores.

FAQ

Q: How much memory does each card have?

A: The Intel Arc Pro B60 Dual has 24 GB of GDDR6 memory, while the NVIDIA RTX PRO 6000 Blackwell has 96 GB of GDDR7 memory.

Q: What is the memory bandwidth difference?

A: The Intel card provides 456.0 GB/s of bandwidth, while the NVIDIA card provides 1.79 TB/s, approximately 3.92 times higher.

Q: What are the FP32 throughput figures?

A: The Intel card delivers 12.29 TFLOPS FP32, while the NVIDIA card delivers 126.0 TFLOPS FP32, approximately 10.25 times higher.

Q: Which card has a higher boost clock?

A: The NVIDIA RTX PRO 6000 Blackwell has a boost clock of 2617 MHz, while the Intel Arc Pro B60 Dual has a boost clock of 2400 MHz.

Q: What is the transistor count for each?

A: The Intel card has 19,600 million transistors on a 272 mm² die. The NVIDIA card has 92,200 million transistors on a 750 mm² die.

Q: What benchmark results are recorded for the NVIDIA card?

A: The NVIDIA card has one recorded result: a 3DMark Steel Nomad DX12 score of 16,408, which places it in the 59th percentile of all GPUs. The Intel card has no recorded benchmark results.

Specification Differences

The following fields differ between the two cards:

• Chip: BMG-G21 versus GB202
• Architecture: Xe2-HPG versus Blackwell 2.0
• Generation: Battlemage (Pro Series) versus Blackwell PRO W (x000)
• Transistors: 19,600 million versus 92,200 million
• Die Size: 272 mm² versus 750 mm²
• Transistor Density: 72.1M / mm² versus 122.9M / mm²
• Base Clock: 2000 MHz versus 1590 MHz
• Boost Clock: 2400 MHz versus 2617 MHz
• Memory Clock: 2375 MHz (19 Gbps effective) versus 1750 MHz (28 Gbps effective)
• Memory Size: 24 GB versus 96 GB
• Memory Type: GDDR6 versus GDDR7
• Memory Bus Width: 192 bit versus 512 bit
• Memory Bandwidth: 456.0 GB/s versus 1.79 TB/s
• Shading Units: 2560 versus 24064
• TMUs: 160 versus 752
• ROPs: 80 versus 192
• RT Cores: 20 versus 188
• Tensor Cores: not listed versus 752
• Pixel Rate: 192.0 GPixel/s versus 502.5 GPixel/s
• Texture Rate: 384.0 GTexel/s versus 1,968.0 GTexel/s
• FP32: 12.29 TFLOPS versus 126.0 TFLOPS
• FP16: 24.58 TFLOPS (2:1) versus 126.0 TFLOPS (1:1)
• TDP: 400 W versus 600 W
• Suggested PSU: 800 W versus 1000 W
• Bus Interface: PCIe 5.0 x8 versus PCIe 5.0 x16
• Display Outputs: 4x mini-DisplayPort 2.1 versus 4x DisplayPort 2.1b
• Dimensions: 300 mm x 110 mm x 40 mm versus 304 mm x 137 mm x 40 mm
• Release Date: 2025-09-04 versus 2025-03-17
• Predecessor: none listed versus Workstation Ada
• Launch MSRP: 1,199 USD versus 8,565 USD
• Benchmark Score: none recorded versus 16,408
• Percentile vs All GPUs: 50 versus 59

The Verdict

The recorded data indicates a substantial capability gap between these two workstation graphics cards. The NVIDIA RTX PRO 6000 Blackwell delivers over 10 times the FP32 throughput, over 5 times the FP16 throughput, nearly 4 times the memory bandwidth, 4 times the memory capacity, and over 9 times the shading units and ray tracing cores compared to the Intel Arc Pro B60 Dual. It also holds a higher percentile rank among all GPUs and has a confirmed benchmark result in the database, while the Intel card has none.

The Intel Arc Pro B60 Dual offers a higher base clock, higher memory clock in raw MHz terms, a smaller physical footprint in height, lower power consumption, and a lower suggested power supply requirement. Its launch MSRP of 1,199 USD is substantially lower than the NVIDIA card's launch MSRP of 8,565 USD, though pricing considerations are not part of this analysis.

For workloads demanding maximum compute throughput, memory capacity, and bandwidth, the NVIDIA card is the clear choice based on every recorded performance metric. For environments where power draw, physical size, and power supply headroom are constraints, the Intel card presents a more modest specification profile. The absence of any benchmark data for the Intel card means its practical performance cannot be verified from the database, while the NVIDIA card's single 3DMark Steel Nomad DX12 score of 16,408 places it in a competitive band with several other cards within a 0.6% margin.