Intel Arc Pro B60 Dual vs NVIDIA RTX PRO 2000 Blackwell Comparison

Head-to-Head Benchmarks

The recorded database contains a full benchmark suite for the NVIDIA RTX PRO 2000 Blackwell, while the Intel Arc Pro B60 Dual has no benchmark entries in the current dataset. This asymmetry limits direct score-for-score comparisons, but the available measurements for the NVIDIA card establish a clear performance baseline. The RTX PRO 2000 Blackwell achieves an average benchmark score of 25,269 across all recorded tests, placing it in the 70th percentile of all GPUs in the database. The Intel card holds a 50th percentile position, though its average benchmark score is recorded as zero due to the absence of tested workloads.

The NVIDIA RTX PRO 2000 Blackwell delivers its strongest result in Geekbench Vulkan with a score of 113,865, followed closely by Geekbench OpenCL at 106,087. These two compute-oriented tests indicate that the card handles general-purpose GPU workloads with substantial headroom. The 3DMark Steel Nomad DX12 test produces a score of 2,374.5, which reflects modern DirectX 12 rendering performance under synthetic load. PassMark results show a G3D score of 20,049, a GPU Compute score of 8,396, and legacy API scores of 241 for DirectX 9, 174 for DirectX 11, and 122 for DirectX 10. The PassMark G2D score of 1,303 captures 2D desktop and compositing performance.

Relative to its nearest rivals in the database, the RTX PRO 2000 Blackwell sits within a narrow competitive band. The AMD Radeon RX 6700M posts an average score of 25,633, which is 1.4% higher than the NVIDIA card. The AMD Radeon Pro W5700 averages 25,726, a 1.8% advantage, and the NVIDIA GeForce RTX 3080 Ti Mobile also averages 25,740, again 1.8% ahead. Conversely, the RTX PRO 2000 Blackwell leads the NVIDIA RTX A5000 Mobile by 2.0%, as that card averages 24,763. These delta percentages place the RTX PRO 2000 Blackwell in a tightly contested mid-range segment where no rival exceeds it by more than 1.8% and it leads its closest competitor by 2.0%.

The Intel Arc Pro B60 Dual has no benchmark scores recorded, so no head-to-head wins can be attributed to either card based on direct measurements. The database records zero wins for each product in the head-to-head benchmark section. The absence of Intel benchmark data means the only quantitative comparison available comes from the NVIDIA card's percentile ranking and its rival deltas. The Intel card's 50th percentile position, while lower than NVIDIA's 70th percentile, carries no direct benchmark confirmation in the current records.

FAQ

Q: How does the NVIDIA RTX PRO 2000 Blackwell compare to its nearest rivals in average benchmark score?

A: The RTX PRO 2000 Blackwell averages 25,269 across recorded tests. It trails the AMD Radeon RX 6700M (25,633, 1.4% higher), the AMD Radeon Pro W5700 (25,726, 1.8% higher), and the NVIDIA GeForce RTX 3080 Ti Mobile (25,740, 1.8% higher), while leading the NVIDIA RTX A5000 Mobile (24,763, 2.0% lower).

Q: What is the strongest benchmark result for the RTX PRO 2000 Blackwell?

A: The highest recorded score is 113,865 in Geekbench Vulkan, followed by 106,087 in Geekbench OpenCL. The 3DMark Steel Nomad DX12 test yields 2,374.5, and PassMark G3D records 20,049.

Q: Does the Intel Arc Pro B60 Dual have any benchmark data in the database?

A: No benchmark scores are recorded for the Intel card. Its average benchmark score is listed as zero, and its percentile versus all GPUs is 50, but no individual test results exist in the current records.

Q: Which card has the higher percentile ranking among all GPUs?

A: The NVIDIA RTX PRO 2000 Blackwell ranks in the 70th percentile, while the Intel Arc Pro B60 Dual ranks in the 50th percentile.

Q: What do the PassMark legacy API scores indicate for the RTX PRO 2000 Blackwell?

A: The card scores 241 in DirectX 9, 174 in DirectX 11, and 122 in DirectX 10. These lower scores compared to its G3D result of 20,049 indicate that the card's performance is heavily concentrated in modern API workloads rather than legacy rendering paths.

Q: How large is the performance gap between the RTX PRO 2000 Blackwell and its closest rival?

A: The narrowest delta is 1.4%, with the AMD Radeon RX 6700M ahead. The largest recorded delta is 2.0%, where the RTX PRO 2000 Blackwell leads the NVIDIA RTX A5000 Mobile.

Architecture Differences

The Intel Arc Pro B60 Dual and NVIDIA RTX PRO 2000 Blackwell diverge fundamentally in chip design and processing philosophy. Intel uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage Pro Series generation. NVIDIA employs the GB206 chip on the Blackwell 2.0 architecture, within the Blackwell PRO W (x000) generation. Both are fabricated on a 5 nm process at TSMC, but the transistor counts and die sizes differ substantially. Intel packs 19,600 million transistors onto a 272 mm² die, yielding a transistor density of 72.1 million per mm². NVIDIA fits 21,900 million transistors onto a smaller 181 mm² die, achieving 121.0 million per mm², a significantly higher density.

The shading unit counts tell opposite stories. The Intel card carries 2,560 shading units, 160 texture mapping units, and 80 render output units. NVIDIA counters with 4,352 shading units, 136 TMUs, and 48 ROPs. This means NVIDIA allocates far more execution units for shader work, while Intel emphasizes ROP throughput for pixel fill operations. The RT core counts also differ: Intel has 20 RT cores, NVIDIA has 34. NVIDIA additionally includes 136 tensor cores, a feature Intel does not list at all. Tensor cores enable AI-accelerated workloads that the Intel architecture lacks a direct equivalent for in the recorded specifications.

Clock speeds show a sharp contrast. Intel runs a base clock of 2000 MHz and a boost clock of 2400 MHz, while NVIDIA operates at a 982 MHz base and 1957 MHz boost. Despite the lower clocks, NVIDIA achieves higher FP32 throughput at 17.03 TFLOPS compared to Intel's 12.29 TFLOPS, a direct result of the larger shader count. FP16 performance reveals a philosophical split: Intel delivers 24.58 TFLOPS at a 2:1 ratio versus its FP32 rate, while NVIDIA matches its FP32 at 17.03 TFLOPS with a 1:1 ratio. Pixel rate favors Intel at 192.0 GPixel/s versus NVIDIA's 93.94 GPixel/s, and texture rate also favors Intel at 384.0 GTexel/s versus 266.2 GTexel/s.

Memory architecture differs across every major parameter. Intel uses 24 GB of GDDR6 on a 192-bit bus, delivering 456.0 GB/s of bandwidth. NVIDIA uses 16 GB of GDDR7 on a 128-bit bus, providing 288.0 GB/s. The Intel card has a memory clock of 2375 MHz with 19 Gbps effective speed, while NVIDIA runs at 1125 MHz with 18 Gbps effective. The Intel card offers 50% more memory capacity and 58.3% more bandwidth, but the NVIDIA card uses newer GDDR7 technology. Both cards share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs are similar with four mini-DisplayPort connections, though Intel uses DisplayPort 2.1 while NVIDIA uses DisplayPort 2.1b.

Power characteristics could not be more different. Intel lists a TDP of 400 W with a single 16-pin power connector and a suggested PSU of 800 W. NVIDIA lists a TDP of 70 W, no power connectors, and a suggested PSU of 250 W. This is a 330 W gap in thermal design power. The Intel card is a dual-slot design measuring 300 mm in length, 110 mm in height, and 40 mm in width. NVIDIA is also dual-slot but far more compact at 167 mm long, 69 mm high, and 20 mm wide. Both use a PCIe 5.0 x8 bus interface.

The Verdict

The recorded data supports a clear separation of use cases. The NVIDIA RTX PRO 2000 Blackwell is the only card with measured benchmark results, and those results show a solid mid-range performer that sits within 1.8% of its nearest rivals in either direction. Its 70th percentile ranking among all GPUs indicates it outperforms the majority of the database. The absence of Intel benchmark data means no performance verdict can be assigned to that card from measurements, only from its 50th percentile placeholder position.

For compute-oriented workloads where FP32 throughput matters, the NVIDIA card holds the specification advantage with 17.03 TFLOPS versus Intel's 12.29 TFLOPS, a 38.6% higher figure. The NVIDIA card also includes 136 tensor cores, which the Intel card lacks entirely, suggesting an edge for AI inference workloads. The RT core count of 34 versus 20 also points to stronger ray tracing throughput on the NVIDIA side.

For memory-heavy workloads, the Intel card presents a compelling specification case. Its 24 GB capacity exceeds NVIDIA's 16 GB by 50%, and its 456.0 GB/s bandwidth exceeds NVIDIA's 288.0 GB/s by 58.3%. The Intel card also has a higher pixel rate of 192.0 GPixel/s, more than double NVIDIA's 93.94 GPixel/s, and a higher texture rate of 384.0 GTexel/s versus 266.2 GTexel/s. These figures indicate the Intel card is built for fill-rate-bound rendering scenarios.

Power consumption is a decisive differentiator. The NVIDIA card draws 70 W with no external power connectors and a 250 W suggested PSU, making it suitable for compact or power-constrained systems. The Intel card demands 400 W, a 16-pin connector, and an 800 W PSU. This 330 W difference in TDP represents a substantial operating cost and cooling burden. The NVIDIA card's smaller physical footprint, at 167 mm versus 300 mm in length, also expands installation options.

The verdict from the recorded data is that the NVIDIA RTX PRO 2000 Blackwell is the validated performer with confirmed benchmark scores, while the Intel Arc Pro B60 Dual is an unmeasured specification sheet. Users who require verified performance data should select the NVIDIA card. Users who prioritize memory capacity, bandwidth, and fill rates may find the Intel card's specifications attractive, but no benchmark confirmation exists to support that choice.

Specification Differences

The two cards differ across nearly every recorded specification field.

| Specification | Intel Arc Pro B60 Dual | NVIDIA RTX PRO 2000 Blackwell |

|---|---|---|

| Chip | BMG-G21 | GB206 |

| Architecture | Xe2-HPG | Blackwell 2.0 |

| Generation | Battlemage (Pro Series) | Blackwell PRO W (x000) |

| Transistors | 19,600 million | 21,900 million |

| Die Size | 272 mm² | 181 mm² |

| Transistor Density | 72.1M / mm² | 121.0M / mm² |

| Base Clock | 2000 MHz | 982 MHz |

| Boost Clock | 2400 MHz | 1957 MHz |

| Memory Clock | 2375 MHz (19 Gbps) | 1125 MHz (18 Gbps) |

| Memory Size | 24 GB | 16 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 192 bit | 128 bit |

| Memory Bandwidth | 456.0 GB/s | 288.0 GB/s |

| Shading Units | 2560 | 4352 |

| TMUs | 160 | 136 |

| ROPs | 80 | 48 |

| RT Cores | 20 | 34 |

| Tensor Cores | None listed | 136 |

| Pixel Rate | 192.0 GPixel/s | 93.94 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 266.2 GTexel/s |

| FP32 | 12.29 TFLOPS | 17.03 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 17.03 TFLOPS (1:1) |

| TDP | 400 W | 70 W |

| Power Connectors | 1x 16-pin | None |

| Suggested PSU | 800 W | 250 W |

| Display Outputs | 4x mini-DisplayPort 2.1 | 4x mini-DisplayPort 2.1b |

| Length | 300 mm (11.8 in) | 167 mm (6.6 in) |

| Height | 110 mm (4.3 in) | 69 mm (2.7 in) |

| Width | 40 mm (1.6 in) | 20 mm (0.8 in) |

| Release Date | 2025-09-04 | 2025-08-10 |

| Launch MSRP | 1,199 USD | None listed |

Both cards share a 5 nm TSMC process, dual-slot form factor, PCIe 5.0 x8 interface, DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 support. The NVIDIA card has a predecessor listed as Workstation Ada, while the Intel card lists no predecessor or successor.

Where Each One Wins

The NVIDIA RTX PRO 2000 Blackwell wins in every category where measured performance exists. Its benchmark scores establish confirmed capability in Geekbench OpenCL and Vulkan compute tests, 3DMark Steel Nomad DX12 rendering, and PassMark G3D and GPU Compute workloads. The specification sheet also gives it advantages in FP32 throughput (17.03 TFLOPS versus 12.29 TFLOPS), shading unit count (4,352 versus 2,560), RT core count (34 versus 20), and tensor core availability (136 versus none). Its 70 W TDP and 250 W suggested PSU make it the clear choice for power-sensitive deployments. The 167 mm length and 20 mm width allow installation in spaces that cannot accommodate the Intel card's 300 mm length and 40 mm width.

The Intel Arc Pro B60 Dual wins on memory capacity and bandwidth. Its 24 GB GDDR6 configuration exceeds the NVIDIA card's 16 GB GDDR7 by 8 GB, and its 456.0 GB/s bandwidth surpasses 288.0 GB/s by 168 GB/s. The Intel card also leads in pixel rate at 192.0 GPixel/s, more than double the NVIDIA card's 93.94 GPixel/s, and texture rate at 384.0 GTexel/s versus 266.2 GTexel/s. FP16 throughput favors Intel at 24.58 TFLOPS versus 17.03 TFLOPS, though this comes at a 2:1 ratio rather than NVIDIA's 1:1. The Intel card's 2000 MHz base clock and 2400 MHz boost clock are both higher than NVIDIA's 982 MHz and 1957 MHz, respectively. The Intel card also has a higher ROP count at 80 versus 48, supporting its pixel fill advantage.

The release dates place the NVIDIA card roughly three weeks earlier, with a recorded release date of 2025-08-10 versus the Intel card's 2025-09-04. The Intel card has a launch MSRP of 1,199 USD, while the NVIDIA card has no listed MSRP. The Intel card's 400 W TDP and 800 W suggested PSU indicate it is designed for systems with substantial power delivery, while the NVIDIA card's lack of power connectors and 250 W PSU requirement fit lower-capacity builds. The NVIDIA card has a predecessor in Workstation Ada, indicating a product lineage, while the Intel card stands alone in the database without predecessor or successor entries.