AMD Radeon Pro 5700 XT vs NVIDIA GeForce RTX 5090 D V2 Comparison

AMD
RADEON

AMD Radeon Pro 5700 XT

CORE STATE Navi 10
VRAM 16 GB
CLOCK SPEED 1499 MHz
TDP 130 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2020
VS
NVIDIA
GEFORCE

GeForce RTX 5090 D V2

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2407 MHz
TDP 575 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

geekbench_metal
51,272
N/A
geekbench_opencl
59,467
N/A
geekbench_vulkan
56,593
N/A
passmark_directx_10
76
N/A
passmark_directx_11
85
N/A
passmark_directx_12
59
N/A
passmark_directx_9
153
N/A
passmark_g2d
810
N/A
passmark_g3d
12,547
N/A
passmark_gpu_compute
5,787
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
16,504

Analysis: AMD Radeon Pro 5700 XT vs NVIDIA GeForce RTX 5090 D V2

Where Each One Wins

The AMD Radeon Pro 5700 XT and NVIDIA GeForce RTX 5090 D V2 occupy completely different performance tiers, and the benchmark data reflects that starkly. The Radeon Pro 5700 XT is a professional Mac-oriented workstation card built on RDNA 1.0, while the RTX 5090 D V2 is NVIDIA's flagship Blackwell consumer GPU. Their recorded benchmarks show no overlap in test suites, which makes direct comparisons tricky, but the available data still tells a clear story about their respective strengths.

For the Radeon Pro 5700 XT, the wins come across the Geekbench suite and a full Passmark battery. Its Geekbench Metal score of 51272, OpenCL score of 59467, and Vulkan score of 56593 indicate strong compute performance for a 2020-era card. In Passmark, it posts a G3D score of 12547 and a GPU compute score of 5787, with legacy DirectX results including 153 in DirectX 9, 85 in DirectX 11, 76 in DirectX 10, and 59 in DirectX 12. The card also shows a Passmark G2D score of 810, which reflects 2D desktop rendering capability.

The RTX 5090 D V2, by contrast, has only one recorded benchmark in the database: a 3DMark Steel Nomad DX12 score of 16504. That single number represents a modern, demanding DX12 workload, and it is the only direct performance evidence for this GPU. The absence of Geekbench or Passmark results for the RTX 5090 D V2 means we cannot compare those specific workloads, but the 3DMark score alone positions it far above the Radeon Pro 5700 XT's Passmark DX12 result of 59. That is not an apples-to-apples comparison, but it does illustrate the generational gulf.

For use-case splitting, the Radeon Pro 5700 XT wins in scenarios where its specific drivers and RDNA 1.0 feature set are relevant, particularly in Mac-based professional environments. Its 16 GB of GDDR6 memory and 384.0 GB/s bandwidth serve compute-heavy tasks like rendering or machine learning inference within that ecosystem. The RTX 5090 D V2 wins in raw modern gaming and DX12 performance, given its 24 GB GDDR7 memory and 1.34 TB/s bandwidth, plus its dedicated ray tracing and tensor cores.

Architecture Differences

The architectural divide is enormous. The Radeon Pro 5700 XT uses the Navi 10 chip on RDNA 1.0 architecture, manufactured on TSMC's 7 nm process. It integrates 10,300 million transistors on a 251 mm² die, yielding a transistor density of 41.0M per mm². The RTX 5090 D V2 uses the GB202 chip on Blackwell 2.0 architecture, built on TSMC's 5 nm process. It packs 92,200 million transistors across a 750 mm² die, with a density of 122.9M per mm². That is nearly nine times the transistor count and roughly three times the die area, with a density advantage of 200% for NVIDIA.

Clock speeds differ substantially. The Radeon Pro 5700 XT runs at a base of 1243 MHz and boost of 1499 MHz, with memory at 1500 MHz (12 Gbps effective). The RTX 5090 D V2 boosts to 2407 MHz from a 2017 MHz base, with memory at 1750 MHz (28 Gbps effective). The NVIDIA card has nearly 61% higher boost clock and more than double the effective memory speed.

Shading resources are in different leagues. The Radeon Pro 5700 XT has 2560 shading units, 160 TMUs, and 64 ROPs. The RTX 5090 D V2 has 21760 shading units, 680 TMUs, and 176 ROPs. That is 8.5 times the shading units, 4.25 times the TMUs, and 2.75 times the ROPs. The NVIDIA card also includes 170 ray tracing cores and 680 tensor cores, neither of which the AMD card has at all.

Memory architecture diverges completely. The AMD card uses 16 GB of GDDR6 on a 256-bit bus, achieving 384.0 GB/s. The NVIDIA card uses 24 GB of GDDR7 on a 384-bit bus, achieving 1.34 TB/s, which is roughly 3.5 times the bandwidth. Pixel rate for the RTX 5090 D V2 is 423.6 GPixel/s versus 95.94 GPixel/s for the AMD card. Texture rate is 1,636.8 GTexel/s versus 239.8 GTexel/s. FP32 compute is 104.8 TFLOPS versus 7.675 TFLOPS, a 13.7-fold difference. FP16 for the NVIDIA card is 104.8 TFLOPS (1:1), while the AMD card achieves 15.35 TFLOPS (2:1).

Power and connectivity also differ. The Radeon Pro 5700 XT is an integrated GPU (IGP) with no power connectors and a 130 W TDP, requiring a 300 W suggested PSU. The RTX 5090 D V2 is a dual-slot card with a single 16-pin connector, a 575 W TDP, and a 950 W suggested PSU. The AMD card uses PCIe 4.0 x16 and has no display outputs; the NVIDIA card uses PCIe 5.0 x16 and offers 1x HDMI 2.1b and 3x DisplayPort 2.1b. The NVIDIA card's dimensions are 304 mm by 137 mm by 48 mm.

FAQ

Q: Which card has more memory bandwidth?

A: The RTX 5090 D V2 offers 1.34 TB/s of memory bandwidth from its 384-bit GDDR7 interface, while the Radeon Pro 5700 XT provides 384.0 GB/s from a 256-bit GDDR6 bus. The NVIDIA card delivers roughly 3.5 times the bandwidth.

Q: Does the Radeon Pro 5700 XT support ray tracing?

A: No. The Radeon Pro 5700 XT has no ray tracing cores listed in the database. In contrast, the RTX 5090 D V2 includes 170 dedicated ray tracing cores and 680 tensor cores.

Q: What is the process node difference?

A: The Radeon Pro 5700 XT is built on TSMC's 7 nm process, while the RTX 5090 D V2 uses TSMC's 5 nm process. The newer node allows NVIDIA to pack 92,200 million transistors versus AMD's 10,300 million.

Q: Which card has a higher boost clock?

A: The RTX 5090 D V2 boosts to 2407 MHz, compared to the Radeon Pro 5700 XT's 1499 MHz boost. That is a 60.6% higher boost clock for the NVIDIA card.

Q: What is the power consumption difference?

A: The Radeon Pro 5700 XT has a 130 W TDP and requires a 300 W suggested PSU. The RTX 5090 D V2 has a 575 W TDP and requires a 950 W suggested PSU.

Q: Which card has more shading units?

A: The RTX 5090 D V2 has 21760 shading units, while the Radeon Pro 5700 XT has 2560. The NVIDIA card has 8.5 times as many shading units.

Specification Differences

| Specification | AMD Radeon Pro 5700 XT | NVIDIA GeForce RTX 5090 D V2 |

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

| Architecture | RDNA 1.0 | Blackwell 2.0 |

| Process node | 7 nm | 5 nm |

| Transistors | 10,300 million | 92,200 million |

| Die size | 251 mm² | 750 mm² |

| Base clock | 1243 MHz | 2017 MHz |

| Boost clock | 1499 MHz | 2407 MHz |

| Memory size | 16 GB | 24 GB |

| Memory type | GDDR6 | GDDR7 |

| Memory bus | 256 bit | 384 bit |

| Memory bandwidth | 384.0 GB/s | 1.34 TB/s |

| Shading units | 2560 | 21760 |

| TMUs | 160 | 680 |

| ROPs | 64 | 176 |

| Ray tracing cores | None | 170 |

| Tensor cores | None | 680 |

| Pixel rate | 95.94 GPixel/s | 423.6 GPixel/s |

| Texture rate | 239.8 GTexel/s | 1,636.8 GTexel/s |

| FP32 | 7.675 TFLOPS | 104.8 TFLOPS |

| FP16 | 15.35 TFLOPS (2:1) | 104.8 TFLOPS (1:1) |

| TDP | 130 W | 575 W |

| Slot width | IGP | Dual-slot |

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

| Suggested PSU | 300 W | 950 W |

| Bus interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Display outputs | No outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| DirectX support | 12 (12_1) | 12 Ultimate (12_2) |

| Release date | 2020-08-03 | 2025-08-14 |

| Production status | End-of-life | Active |

Head-to-Head Benchmarks

The recorded benchmarks for these two cards do not share a single common test. The Radeon Pro 5700 XT's database entry contains 10 benchmark results across Geekbench and Passmark suites. The RTX 5090 D V2's entry contains exactly one result: 3DMark Steel Nomad DX12 at 16504.

Within the Radeon Pro 5700 XT's own results, the strongest showing is in Geekbench OpenCL at 59467, followed by Vulkan at 56593 and Metal at 51272. In Passmark, the G3D score of 12547 and GPU compute score of 5787 are the highlights. The DirectX 12 score of 59 is notably weak, reflecting the card's age and driver priorities.

For the RTX 5090 D V2, the 3DMark Steel Nomad DX12 score of 16504 is a modern, high-end gaming and compute workload. To put that in context using the nearest rivals in the database, the NVIDIA T400 scores 16508 (a 0% delta), the AMD Radeon PRO W7500 scores 16415 (a 0.5% delta), the NVIDIA RTX PRO 6000 Blackwell scores 16408 (a 0.6% delta), and the AMD Radeon RX 5700 XT scores 16361 (a 0.9% delta). The RTX 5090 D V2 essentially matches its closest rivals in this single test, sitting within 1% of all four.

The Radeon Pro 5700 XT's nearest rivals tell a different story. The AMD Radeon RX 560X averages 18626 (a 0.3% delta), the NVIDIA GeForce RTX 2070 averages 18789 (a -0.6% delta), the AMD FirePro D500 averages 18533 (a 0.8% delta), and the NVIDIA Tesla K80 averages 18866 (a -1% delta). The Radeon Pro 5700 XT's average benchmark score is 18685, placing it right in the middle of that group.

The average benchmark scores themselves are telling. The Radeon Pro 5700 XT has an average of 18685 across its 10 tests, while the RTX 5090 D V2 has an average of 16504 across its single test. That average is misleading because the test suites are completely different. The Radeon Pro 5700 XT's percentile ranking is 63rd among all GPUs, while the RTX 5090 D V2 sits at the 59th percentile. Again, these percentiles come from different benchmark pools, so they are not directly comparable.

The biggest win for the RTX 5090 D V2, based on the available data, is in raw modern DX12 performance. The 3DMark Steel Nomad score of 16504 dwarfs the Radeon Pro 5700 XT's Passmark DX12 score of 59, though these are different workloads. The NVIDIA card's 104.8 TFLOPS FP32 versus 7.675 TFLOPS for AMD represents a 13.7-fold compute advantage, and its 1.34 TB/s bandwidth versus 384.0 GB/s is a 3.5-fold advantage.

The biggest win for the Radeon Pro 5700 XT is in its diverse benchmark coverage and its efficiency profile. At 130 W TDP versus 575 W, it uses 77% less power. Its IGP form factor means it requires no power connectors and fits in systems where a dual-slot card with a 16-pin connector would not. For Mac-oriented workloads, its Geekbench Metal score of 51272 shows it can handle Apple's compute framework, something the RTX 5090 D V2 has no recorded equivalent for.

The Verdict

The data points to a clear conclusion: these are not competing products. The Radeon Pro 5700 XT is an end-of-life, integrated, Mac-focused workstation GPU from 2020. The RTX 5090 D V2 is an active, dual-slot, consumer flagship from 2025 with a launch MSRP of 2,299 USD. Their specifications and benchmark results place them in entirely different segments.

For users working within Apple's Mac ecosystem, the Radeon Pro 5700 XT is the only one of the two with any recorded Metal performance (51272 in Geekbench Metal). It also offers 16 GB of memory and a 130 W TDP, making it feasible for systems without discrete power connectors. Its end-of-life status means it is no longer in production, but its 10 benchmark results show a versatile compute profile across OpenCL, Vulkan, and Passmark tests.

For anyone building a high-end Windows or Linux gaming or compute workstation, the RTX 5090 D V2 is the obvious choice based on the recorded data. Its 3DMark Steel Nomad DX12 score of 16504, while only one data point, comes from a modern benchmark that stresses current GPUs. Its 24 GB of GDDR7 memory, 1.34 TB/s bandwidth, 21760 shading units, 170 ray tracing cores, and 680 tensor cores provide the hardware foundation for both gaming and AI workloads. Its active production status and PCIe 5.0 interface mean it is current and forward-looking.

The practical advice from the database is straightforward. If you need a low-power, no-connector, Mac-compatible GPU with 16 GB of memory and you are working within the Radeon Pro ecosystem, the 5700 XT remains a valid option despite being end-of-life. If you need maximum modern DX12 performance, massive memory bandwidth, ray tracing, and tensor core acceleration, and you have the power delivery (950 W suggested PSU) and physical space (304 mm long, dual-slot), the RTX 5090 D V2 is the only choice between these two.

The percentile rankings (63rd for AMD, 59th for NVIDIA) are close, but they come from different benchmark suites and should not be read as equivalence. The RTX 5090 D V2's single 3DMark result aligns it with the NVIDIA T400, AMD Radeon PRO W7500, NVIDIA RTX PRO 6000 Blackwell, and AMD Radeon RX 5700 XT within a 1% band. The Radeon Pro 5700 XT's average score aligns it with the RX 560X, RTX 2070, FirePro D500, and Tesla K80 within a 1% band. Those rival groups tell you everything: the RTX 5090 D V2 competes with modern professional and high-end gaming cards, while the Radeon Pro 5700 XT competes with older mid-range hardware. Choose accordingly.

DETAILED SPECIFICATIONS

SPECIFICATION
Pro 5700 XT
RTX 5090 D V2
Core Specs
Shading Units
2,560
21,760 +750.0%
Shaders
2,560
21,760 +750.0%
TMUs
160
680 +325.0%
ROPs
64
176 +175.0%
Compute Units
40
—
SM Count
—
170
Clocks
Base Clock
1243 MHz
2017 MHz
Boost Clock
1499 MHz
2407 MHz
Memory Clock
1500 MHz 12 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
16 GB
24 GB
VRAM (MB)
16,384
24,576 +50.0%
Memory Type
GDDR6
GDDR7
Memory Bus
256 bit
384 bit
Bandwidth
384.0 GB/s
1.34 TB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
96 MB
Performance
Pixel Rate
95.94 GPixel/s
423.6 GPixel/s
Texture Rate
239.8 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
7.675 TFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
479.7 GFLOPS (1:16)
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
15.35 TFLOPS (2:1)
104.8 TFLOPS (1:1)
AI/RT
RT Cores
—
170
Tensor Cores
—
680
Power
TDP
130 W
575 W
TDP (W)
130
575 +342.3%
Suggested PSU
300 W
950 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
RDNA 1.0
Blackwell 2.0
GPU Name
Navi 10
GB202
Generation
Radeon Pro Mac (Navi Series)
GeForce 50
Process Size
7 nm
5 nm
Transistors
10,300 million
92,200 million
Die Size
251 mm²
750 mm²
Foundry
TSMC
TSMC
Density
41.0M / mm²
122.9M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
12.0
Shader Model
6.8
6.9
Physical
Slot Width
IGP
Dual-slot
Length
—
304 mm 12 inches
Height
—
137 mm 5.4 inches
Outputs
No outputs
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
—
2,299 USD
Production
End-of-life
Active
Predecessor
—
GeForce 40
Successor
—
GeForce 60
View Radeon Pro 5700 XT Details View GeForce RTX 5090 D V2 Details