AMD Radeon RX 9060 vs NVIDIA RTX PRO 6000 Blackwell Comparison

The NVIDIA RTX PRO 6000 Blackwell and AMD Radeon RX 9060 occupy opposite ends of the GPU spectrum, and the benchmark data reflects that divide clearly. In the single shared DirectX 12 test, the NVIDIA card delivers a score of 16,408, which is 393.9% higher than the AMD card’s 3,322. However, the AMD card has a broader benchmark portfolio, including OpenCL, Vulkan, and multiple Passmark tests, where it posts competitive scores relative to its own peer group. The data shows two distinct performance envelopes: one built for maximum compute and graphics throughput, the other for efficient, balanced rendering across a variety of legacy and modern APIs.

Where Each One Wins

The NVIDIA RTX PRO 6000 Blackwell wins the only directly comparable test: 3DMark Steel Nomad DX12. Its score of 16,408 places it 0.3% ahead of the AMD Radeon RX 5700 XT and 0.4% ahead of the AMD Radeon Pro 5600M, while sitting 0.6% behind the NVIDIA GeForce RTX 5090 D V2. This single score indicates that in a pure DirectX 12 workload, the RTX PRO 6000 operates at the top of its immediate competitive tier, with no rival in its nearestRivals list exceeding it by more than a fraction of a percent.

The AMD Radeon RX 9060 wins in the breadth of available benchmark data. It has ten recorded scores versus the NVIDIA card’s single entry. In OpenCL, it scores 88,183; in Vulkan, 39,476. Its Passmark results range from 44 in DirectX 12 to 280 in DirectX 9, with a G3D score of 17,631 and a GPU compute score of 9,919. These figures show that the RX 9060 is tested across a wider range of workloads, and its 59th percentile ranking among all GPUs matches the RTX PRO 6000’s percentile, suggesting that despite the massive gap in raw compute on the Steel Nomad test, both cards land in the same overall performance distribution when considering all benchmarks.

The use-case split is straightforward: the NVIDIA card wins the modern, high-end DirectX 12 rasterization test by a wide margin, while the AMD card has demonstrated performance across more diverse testing scenarios, including compute and older DirectX versions.

Architecture Differences

The two GPUs are built on fundamentally different architectures and process nodes. The NVIDIA RTX PRO 6000 Blackwell uses the GB202 chip with a 5 nm TSMC process, containing 92,200 million transistors on a 750 mm² die, giving a transistor density of 122.9 million per mm². It is part of the Blackwell 2.0 architecture and the Blackwell PRO W (x000) generation. The AMD Radeon RX 9060 uses the Navi 44 chip with a 4 nm TSMC process, containing 29,700 million transistors on a 199 mm² die, resulting in a higher transistor density of 149.2 million per mm². It is based on RDNA 4.0 and belongs to the Navi IV (RX 9000) generation.

The NVIDIA card features 24,064 shading units, 752 TMUs, 192 ROPs, 188 RT cores, and 752 tensor cores. The AMD card has 1,792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores, with no tensor cores listed. This represents a 13.4x difference in shading units, a 6.7x difference in TMUs, and a 3x difference in ROPs. The RT core count differs by a factor of 6.7x in NVIDIA’s favor.

Memory architecture is also vastly different. The RTX PRO 6000 has 96 GB of GDDR7 on a 512-bit bus, yielding 1.79 TB/s bandwidth. The RX 9060 has 8 GB of GDDR6 on a 128-bit bus, yielding 288.0 GB/s bandwidth. The NVIDIA card’s memory size is 12x larger, and its bandwidth is 6.2x higher.

Clock speeds tell a different story. The AMD card has a higher base clock at 1700 MHz versus 1590 MHz, and a higher boost clock at 2990 MHz versus 2617 MHz. The AMD card also lists a game clock of 2400 MHz, which the NVIDIA card does not have. However, the NVIDIA card’s much larger execution resources more than compensate for the lower clocks.

FAQ

Q: Which GPU has the higher boost clock?

A: The AMD Radeon RX 9060 has a boost clock of 2990 MHz, which is higher than the NVIDIA RTX PRO 6000 Blackwell’s boost clock of 2617 MHz.

Q: How do the two cards compare in memory capacity?

A: The NVIDIA RTX PRO 6000 Blackwell has 96 GB of GDDR7 memory, while the AMD Radeon RX 9060 has 8 GB of GDDR6 memory. This is a 12x difference in capacity.

Q: What is the transistor density difference between the two chips?

A: The AMD Navi 44 chip has a higher transistor density at 149.2 million per mm², compared to the NVIDIA GB202 chip’s 122.9 million per mm², despite the NVIDIA chip having more total transistors.

Q: Which card has a higher average benchmark score across all its tests?

A: The AMD Radeon RX 9060 has an average benchmark score of 16,014, while the NVIDIA RTX PRO 6000 Blackwell has an average benchmark score of 16,408. The NVIDIA card is higher by 394 points.

Q: Do both cards support the same DirectX version?

A: Yes, both cards support DirectX 12 Ultimate (12_2), as well as OpenGL 4.6 and Vulkan 1.4.

Q: What is the difference in power connector requirements?

A: The NVIDIA RTX PRO 6000 Blackwell requires a 1x 16-pin power connector and suggests a 1000 W PSU, while the AMD Radeon RX 9060 uses a 1x 8-pin connector and suggests a 300 W PSU.

Specification Differences

The following table highlights only the fields where the two GPUs differ:

| Specification | NVIDIA RTX PRO 6000 Blackwell | AMD Radeon RX 9060 |

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

| Chip | GB202 | Navi 44 |

| Architecture | Blackwell 2.0 | RDNA 4.0 |

| Generation | Blackwell PRO W (x000) | Navi IV (RX 9000) |

| Process Node | 5 nm | 4 nm |

| Transistors | 92,200 million | 29,700 million |

| Die Size | 750 mm² | 199 mm² |

| Transistor Density | 122.9M / mm² | 149.2M / mm² |

| Base Clock | 1590 MHz | 1700 MHz |

| Boost Clock | 2617 MHz | 2990 MHz |

| Game Clock | None | 2400 MHz |

| Memory Clock | 1750 MHz (28 Gbps effective) | 2250 MHz (18 Gbps effective) |

| Memory Size | 96 GB | 8 GB |

| Memory Type | GDDR7 | GDDR6 |

| Memory Bus Width | 512 bit | 128 bit |

| Memory Bandwidth | 1.79 TB/s | 288.0 GB/s |

| Shading Units | 24,064 | 1,792 |

| TMUs | 752 | 112 |

| ROPs | 192 | 64 |

| RT Cores | 188 | 28 |

| Tensor Cores | 752 | None |

| Pixel Rate | 502.5 GPixel/s | 191.4 GPixel/s |

| Texture Rate | 1,968.0 GTexel/s | 334.9 GTexel/s |

| FP32 | 126.0 TFLOPS | 21.43 TFLOPS |

| FP16 | 126.0 TFLOPS (1:1) | 21.43 TFLOPS (1:1) |

| TDP | 600 W | 132 W |

| Power Connectors | 1x 16-pin | 1x 8-pin |

| Suggested PSU | 1000 W | 300 W |

| Display Outputs | 4x DisplayPort 2.1b | 1x HDMI 2.1b, 2x DisplayPort 2.1a |

| Dimensions (LxHxW) | 304 mm x 137 mm x 40 mm | Not specified |

| Release Date | 2025-03-17 | 2025-08-04 |

| Launch MSRP | 8,565 USD | None |

Head-to-Head Benchmarks

The single head-to-head benchmark available is 3DMark Steel Nomad DX12. The NVIDIA RTX PRO 6000 Blackwell scores 16,408, while the AMD Radeon RX 9060 scores 3,322. The delta is 393.9%, meaning the NVIDIA card is nearly 5x faster in this test. This is the only direct comparison in the data.

To contextualize the NVIDIA card’s performance: its score of 16,408 is essentially tied with the AMD Radeon PRO W7500, which scores 16,415 (0% delta). It is 0.3% ahead of the AMD Radeon RX 5700 XT and 0.4% ahead of the AMD Radeon Pro 5600M. The only rival it trails is the NVIDIA GeForce RTX 5090 D V2, by 0.6%.

For the AMD card, its Steel Nomad score of 3,322 is not directly listed among its nearestRivals, but its average benchmark score of 16,014 places it 0.7% behind the NVIDIA GeForce RTX 3060 Ti (16,129), 1% ahead of the AMD Radeon R9 370X (15,862), 1% ahead of the AMD Radeon RX 7700 (15,852), and 2.1% ahead of the AMD Radeon Pro W5500 (15,679). Note that the RX 9060’s other individual scores, such as 88,183 in OpenCL and 17,631 in Passmark G3D, are much higher than its Steel Nomad result, indicating that its performance varies significantly by workload type.

The data shows that in the one overlapping modern test, the NVIDIA card dominates by a factor of nearly 5. However, the AMD card’s average score across all its benchmarks is only 2.4% lower than the NVIDIA card’s single score, which suggests that the RX 9060 is far more competitive in non-Steel Nomad workloads.

The Verdict

Based strictly on the data, the NVIDIA RTX PRO 6000 Blackwell is the clear winner for users prioritizing DirectX 12 Steel Nomad performance. Its 393.9% lead over the RX 9060 in that test is decisive. It also offers 96 GB of memory, 24,064 shading units, and 126.0 TFLOPS of FP32 compute, which positions it for extreme compute and rendering workloads. Its launch MSRP is 8,565 USD. The card’s 59th percentile rank among all GPUs, tied with the RX 9060, is notable given that it is based on a single benchmark score.

The AMD Radeon RX 9060, on the other hand, is the more versatile option in terms of tested workloads. It has ten benchmark scores, including strong showings in OpenCL (88,183) and Vulkan (39,476), as well as a Passmark G3D score of 17,631. Its average benchmark score of 16,014 is only 2.4% below the NVIDIA card’s single result. It achieves this with a 132 W TDP, a 300 W suggested PSU, and a 4 nm process node, making it far more power-efficient per the data. It also has a higher boost clock at 2990 MHz.

The choice comes down to workload. For users who need maximum raw performance in a single modern DirectX 12 test, the RTX PRO 6000 is unmatched in this comparison. For users who need a card that performs well across a broader range of benchmarks, including compute APIs and legacy DirectX versions, the RX 9060 offers more evidence of versatility. The data does not support a single winner across all scenarios; it supports two winners for two different use cases.