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

Intel Arc Pro B60 Dual and NVIDIA RTX PRO 6000 Blackwell Server are both active, dual-slot workstation accelerators, but the benchmark database records a stark contrast in their measured performance profiles. The Intel part is a 5 nm Battlemage generation card with a 50th percentile ranking across all GPUs, while the NVIDIA part, also on a 5 nm node, represents the Server Blackwell generation. The most significant data point for the NVIDIA card is its single recorded benchmark score in 3DMark Steel Nomad DX12, which places it in the 34th percentile. The Intel Arc Pro B60 Dual has no recorded benchmark scores in the database, making direct numerical comparison impossible, yet the architectural and specification differences provide a clear picture of their distinct positioning.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two cards, and the Intel Arc Pro B60 Dual has no individual benchmark scores listed. The only measurable performance data available belongs to the NVIDIA RTX PRO 6000 Blackwell Server, which achieved a score of 5996 in the 3dmark_3dmark_steel_nomad_dx12 test. This result is remarkably close to its nearest rivals in the database. The NVIDIA card trails the NVIDIA GeForce GTX 770M by a negligible 0.1 percent, as that rival scored 6000. It also sits 0.1 percent behind the AMD Radeon RX 6400, which scored 6001. Conversely, the RTX PRO 6000 Blackwell Server leads the AMD FirePro W4100 by 0.2 percent, as that card scored 5987, and it also edges out the NVIDIA Quadro K4000M by 0.2 percent, which scored 5986. These delta percentages, all within a fraction of a point, indicate that the single benchmark result places the RTX PRO 6000 Blackwell Server in a performance tier that is statistically indistinguishable from these older, lower-tier mobile and entry-level desktop parts. The data suggests that this particular benchmark workload does not utilize the NVIDIA card's substantial compute resources effectively, or the recorded score is an outlier. Without any scores for the Intel Arc Pro B60 Dual, the database cannot establish which card wins in any direct comparison; the only conclusion is that the NVIDIA card has a measurable, albeit low, percentile ranking in this specific test.

FAQ

Q: What is the only recorded benchmark score for these two GPUs?

A: The NVIDIA RTX PRO 6000 Blackwell Server has a single recorded score of 5996 in the 3dmark_3dmark_steel_nomad_dx12 test. The Intel Arc Pro B60 Dual has no benchmark scores listed in the database.

Q: How does the NVIDIA GPU's benchmark score compare to its nearest rivals?

A: The RTX PRO 6000 Blackwell Server's score of 5996 is 0.1 percent lower than the NVIDIA GeForce GTX 770M (6000) and the AMD Radeon RX 6400 (6001). It is 0.2 percent higher than the AMD FirePro W4100 (5987) and the NVIDIA Quadro K4000M (5986).

Q: What is the difference in memory capacity between the two cards?

A: The Intel Arc Pro B60 Dual features 24 GB of GDDR6 memory on a 192-bit bus, while the NVIDIA RTX PRO 6000 Blackwell Server features 96 GB of GDDR7 memory on a 512-bit bus.

Q: Which card has a higher boost clock speed?

A: The NVIDIA RTX PRO 6000 Blackwell Server has a boost clock of 2617 MHz, which is higher than the Intel Arc Pro B60 Dual's boost clock of 2400 MHz.

Q: What are the power connector requirements for each card?

A: Both cards use a single 16-pin power connector. The Intel card has a suggested PSU of 800 W, while the NVIDIA card has a suggested PSU of 1000 W.

Q: What is the difference in FP32 performance?

A: The NVIDIA RTX PRO 6000 Blackwell Server delivers 126.0 TFLOPS of FP32 performance. The Intel Arc Pro B60 Dual delivers 12.29 TFLOPS.

Where Each One Wins

Based on the recorded specifications, the NVIDIA RTX PRO 6000 Blackwell Server wins in nearly every measurable compute and memory category. It delivers 126.0 TFLOPS of FP32 performance compared to the Intel card's 12.29 TFLOPS, a more than tenfold advantage. Its texture rate of 1,968.0 GTexel/s dwarfs the Intel card's 384.0 GTexel/s. The pixel rate also favors NVIDIA at 502.5 GPixel/s versus 192.0 GPixel/s. Memory bandwidth is another decisive win for the NVIDIA card, with 1.79 TB/s available against the Intel card's 456.0 GB/s. The NVIDIA card also has a wider PCIe interface, using PCIe 5.0 x16 compared to the Intel card's PCIe 5.0 x8. The NVIDIA card holds a significant advantage in shading units, with 24064 compared to 2560, and in ray tracing cores, with 188 versus 20. The only area where the Intel Arc Pro B60 Dual wins is in physical length, as it measures 300 mm compared to the NVIDIA card's 267 mm, which is a longer dimension and not a performance win. The Intel card also has a lower base clock of 2000 MHz versus 1590 MHz, but this does not translate into a compute advantage given the massive disparity in core counts. The data clearly indicates that the NVIDIA card is the dominant performer across all computational workloads.

Specification Differences

The two cards differ substantially across nearly all core specifications. The Intel Arc Pro B60 Dual uses a BMG-G21 chip with 19,600 million transistors on a 272 mm² die, while the NVIDIA RTX PRO 6000 Blackwell Server uses a GB202 chip with 92,200 million transistors on a 750 mm² die. The transistor density is higher on the NVIDIA card at 122.9M / mm², compared to 72.1M / mm² for the Intel card. Clock speeds differ, with the Intel card having a higher base clock at 2000 MHz versus 1590 MHz, but the NVIDIA card has a higher boost clock at 2617 MHz versus 2400 MHz. The memory subsystems are entirely different: the Intel card uses 24 GB of GDDR6 with a 192-bit bus and 456.0 GB/s bandwidth, while the NVIDIA card uses 96 GB of GDDR7 with a 512-bit bus and 1.79 TB/s bandwidth. Core counts are drastically different, with the NVIDIA card featuring 24064 shading units, 752 TMUs, and 192 ROPs, compared to the Intel card's 2560 shading units, 160 TMUs, and 80 ROPs. The NVIDIA card also includes 752 tensor cores and 188 RT cores, while the Intel card has 20 RT cores and no listed tensor cores. The power requirements scale accordingly, with the Intel card rated at 400 W and the NVIDIA card at 600 W. The suggested PSU is 800 W for the Intel card and 1000 W for the NVIDIA card. Display outputs also differ, with the Intel card using 4x mini-DisplayPort 2.1 and the NVIDIA card using 4x DisplayPort 2.1b.

Architecture Differences

The architectural divide between these two GPUs is fundamental. The Intel Arc Pro B60 Dual is built on the Xe2-HPG architecture, representing the Battlemage Pro Series generation. The NVIDIA RTX PRO 6000 Blackwell Server uses the Blackwell 2.0 architecture, from the Server Blackwell (Bxx) generation. Both are fabricated on a 5 nm process at TSMC, but the NVIDIA chip is significantly larger and denser. The NVIDIA card includes dedicated tensor cores, with 752 of them, which are absent from the Intel card's specification list. The ray tracing capabilities differ as well, with NVIDIA featuring 188 RT cores compared to Intel's 20. The memory architecture is a major divergence: NVIDIA uses GDDR7 memory with a 512-bit interface, while Intel uses GDDR6 with a 192-bit interface. The FP16 compute ratio also differs. The Intel card lists FP16 performance as 24.58 TFLOPS with a 2:1 ratio relative to FP32, while the NVIDIA card lists FP16 performance as 126.0 TFLOPS with a 1:1 ratio. This indicates that the NVIDIA architecture is designed for equal throughput across FP32 and FP16 workloads, which is common for compute and AI tasks. The NVIDIA card also has a wider PCIe interface at x16 versus x8, which provides more bandwidth for data transfer with the host system. The Intel card's predecessor and successor fields are null, while the NVIDIA card lists its predecessor as Server Hopper and successor as Server Rubin, indicating a clear product lineage within NVIDIA's server segment.

The Verdict

The recorded data draws an unambiguous conclusion for compute-heavy workloads. The NVIDIA RTX PRO 6000 Blackwell Server is the superior choice based on every measured specification. It provides 126.0 TFLOPS of FP32 compute, 96 GB of GDDR7 memory, 1.79 TB/s of bandwidth, and 752 tensor cores. These figures position it as a card for large-scale AI, rendering, and scientific computing tasks. The Intel Arc Pro B60 Dual, with 12.29 TFLOPS of FP32, 24 GB of GDDR6, 456.0 GB/s bandwidth, and no tensor cores, is a more modest offering. Its lower TDP of 400 W and shorter length of 267 mm might suit constrained physical or thermal environments, but the performance gap is immense. The NVIDIA card's single benchmark score of 5996 in 3DMark Steel Nomad is perplexing given its high-end specifications; the score places it near much older and smaller GPUs like the GeForce GTX 770M and Radeon RX 6400. This discrepancy suggests that either the benchmark does not stress the card's strengths or the recorded result is not representative of its full potential. For users selecting a GPU strictly from the database's specification sheet, the NVIDIA RTX PRO 6000 Blackwell Server is the clear choice for maximum performance. The Intel Arc Pro B60 Dual would only be considered if the lower power draw of 400 W and the smaller 267 mm length are hard requirements, or if the workload is light enough to not need the NVIDIA card's massive compute and memory resources. The data shows no scenario where the Intel card outperforms the NVIDIA card on any technical specification.