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

AMD
RADEON

AMD Radeon RX 5700 XT

CORE STATE Navi 10
VRAM 8 GB
CLOCK SPEED 1905 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2019
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

3dmark_3dmark_steel_nomad_dx12
2,134
16,504
geekbench_metal
74,647
N/A
geekbench_opencl
9,524
N/A
geekbench_vulkan
68,310
N/A
passmark_directx_10
97
N/A
passmark_directx_11
116
N/A
passmark_directx_12
64
N/A
passmark_directx_9
226
N/A
passmark_g2d
922
N/A
passmark_g3d
16,277
N/A
passmark_gpu_compute
7,650
N/A

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

The NVIDIA GeForce RTX 5090 D V2 and the AMD Radeon RX 5700 XT represent two distinct eras of graphics hardware, separated by six years of architectural evolution. The data shows a stark contrast in their benchmark performance, with the RTX 5090 D V2 dominating the single shared test. However, the RX 5700 XT holds its own in a broader suite of legacy benchmarks, making this comparison less about a direct rivalry and more about generational capability versus specialized workload efficiency.

Head-to-Head Benchmarks

The only directly comparable benchmark in the dataset is the 3DMark Steel Nomad DX12 test, and the results are decisively lopsided. The NVIDIA GeForce RTX 5090 D V2 scores 16,504 points, while the AMD Radeon RX 5700 XT manages only 2,134 points. This translates to a delta of 673.4% in favor of the newer NVIDIA card, a margin that underscores the sheer computational leap between the two generations. In practical terms, the RTX 5090 D V2 delivers over seven times the raw performance of the RX 5700 XT in this modern DirectX 12 workload, a gap that reflects the massive differences in shader count, memory bandwidth, and architectural efficiency.

The RTX 5090 D V2’s victory is comprehensive, but the RX 5700 XT’s other benchmark results provide context for its strengths outside of this single test. For instance, in Geekbench Metal, the RX 5700 XT scores 74,647, which is notably higher than its OpenCL score of 9,524 and its Vulkan score of 68,310. This indicates that while the RX 5700 XT is not competitive with the RTX 5090 D V2 in DX12, it retains respectable performance in Apple-centric Metal workloads, likely due to its RDNA 1.0 architecture’s efficiency in that API. The RTX 5090 D V2, by contrast, has no listed scores for these other benchmarks, so its dominance is confined to the 3DMark test.

The deltaPct values in the nearest rivals list further contextualize the RTX 5090 D V2’s position. Its average score of 16,504 is within 0.6% of the NVIDIA RTX PRO 6000 Blackwell (16,408) and 0.5% of the AMD Radeon PRO W7500 (16,415), placing it in a tight cluster of high-end workstation cards. The RX 5700 XT’s average score of 16,361 is just 0.9% behind the RTX 5090 D V2, which is surprising given the 673.4% disparity in the head-to-head test. This discrepancy arises because the RX 5700 XT’s average is pulled from its multiple benchmark scores, including the high Geekbench Metal result, while the RTX 5090 D V2’s average is based solely on the 3DMark score. In essence, the averages measure different things, but the head-to-head test remains the clearest apples-to-apples comparison.

Where Each One Wins

The RTX 5090 D V2 wins unequivocally in modern DirectX 12 gaming and compute workloads, as evidenced by its 3DMark Steel Nomad result. This test is designed to stress current-generation GPUs with advanced rendering techniques, and the RTX 5090 D V2’s 104.8 TFLOPS of FP32 performance and 1.34 TB/s memory bandwidth are clearly sufficient to obliterate the RX 5700 XT’s 9.754 TFLOPS and 448.0 GB/s. For users targeting 4K high-refresh-rate gaming or professional 3D rendering, the RTX 5090 D V2 is the only viable option of the two.

The RX 5700 XT, however, wins in legacy and cross-platform benchmarks. Its Geekbench Metal score of 74,647 is exceptional, and its Passmark G3D score of 16,277 is respectable, suggesting it remains capable for older DirectX 11 titles or OpenGL applications where its RDNA 1.0 architecture can still flex its muscles. The RX 5700 XT also shows a strong Passmark G2D score of 922, indicating robust 2D desktop acceleration, which is less relevant for gaming but useful for productivity tasks. In contrast, the RTX 5090 D V2 has no data for these tests, so the RX 5700 XT is the clear winner in scenarios that rely on Metal, OpenGL, or 2D performance.

The win count is 1-0 in favor of the RTX 5090 D V2, but this single tally masks the RX 5700 XT’s versatility across the broader benchmark suite. The RTX 5090 D V2 is a specialist in modern DX12, while the RX 5700 XT is a generalist that still handles older APIs with grace. The data suggests that for a user with a legacy software library, the RX 5700 XT offers more balanced performance, whereas the RTX 5090 D V2 is the clear choice for future-proofing.

Architecture Differences

The architectural chasm between these two GPUs is vast. The RTX 5090 D V2 is built on the Blackwell 2.0 architecture using TSMC’s 5 nm process node, packing 92,200 million transistors onto a 750 mm² die. This results in a transistor density of 122.9 million per square millimeter, a figure that highlights the extreme miniaturization of the design. The RX 5700 XT, in contrast, uses the RDNA 1.0 architecture on TSMC’s 7 nm node, with 10,300 million transistors on a 251 mm² die, yielding a density of 41.0 million per square millimeter. The RTX 5090 D V2 has nearly nine times the transistor count and three times the die area, which directly translates to its massive compute advantage.

The RTX 5090 D V2 features 21,760 shading units, 680 texture mapping units (TMUs), and 176 render output units (ROPs), alongside 170 dedicated ray tracing cores and 680 tensor cores. This configuration is designed for hybrid rendering and AI-accelerated workloads. The RX 5700 XT, by contrast, has only 2,560 shading units, 160 TMUs, and 64 ROPs, with no dedicated ray tracing or tensor cores. The lack of RT cores means the RX 5700 XT cannot perform hardware-accelerated ray tracing, a feature that is standard in modern games. The tensor cores on the RTX 5090 D V2 enable DLSS and other AI-driven features, which the RX 5700 XT cannot leverage.

Memory architecture also differs fundamentally. The RTX 5090 D V2 uses 24 GB of GDDR7 memory on a 384-bit bus, delivering 1.34 TB/s of bandwidth. The RX 5700 XT has 8 GB of GDDR6 on a 256-bit bus, offering 448.0 GB/s. This threefold difference in bandwidth is critical for high-resolution textures and compute tasks. The RTX 5090 D V2 also supports PCIe 5.0 x16, while the RX 5700 XT is limited to PCIe 4.0 x16, which could impact data transfer rates in CPU-bound scenarios.

Specification Differences

The two cards differ across nearly every measurable specification. The RTX 5090 D V2 has a base clock of 2017 MHz and a boost clock of 2407 MHz, while the RX 5700 XT operates at 1605 MHz base and 1905 MHz boost. The RTX 5090 D V2’s memory clock is listed as 1750 MHz with 28 Gbps effective, whereas the RX 5700 XT’s memory clock is 1750 MHz with 14 Gbps effective, highlighting the GDDR7 advantage. The RTX 5090 D V2’s pixel rate is 423.6 GPixel/s and texture rate is 1,636.8 GTexel/s, dwarfing the RX 5700 XT’s 121.9 GPixel/s and 304.8 GTexel/s. FP32 performance is 104.8 TFLOPS for the RTX 5090 D V2 versus 9.754 TFLOPS for the RX 5700 XT, a 10.7x difference. FP16 performance is also stark: 104.8 TFLOPS (1:1) for the RTX 5090 D V2 versus 19.51 TFLOPS (2:1) for the RX 5700 XT, indicating the NVIDIA card handles FP16 at full rate while AMD halves its throughput.

Power requirements differ substantially. The RTX 5090 D V2 has a TDP of 575 W and requires a 950 W power supply, with a single 16-pin connector. The RX 5700 XT has a 225 W TDP, a 550 W suggested PSU, and uses a 6-pin plus 8-pin setup. The RTX 5090 D V2 is also physically larger at 304 mm in length, 137 mm in height, and 48 mm in width, compared to the RX 5700 XT’s 272 mm, 111 mm, and 36 mm. Display outputs differ as well: the RTX 5090 D V2 offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RX 5700 XT has 1x HDMI 2.0b and 3x DisplayPort 1.4a. API support shows the RTX 5090 D V2 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the RX 5700 XT is limited to DirectX 12 (12_1) but also supports Vulkan 1.4.

FAQ

Q: Which GPU is faster in 3DMark Steel Nomad DX12?

A: The NVIDIA GeForce RTX 5090 D V2 scores 16,504 versus the AMD Radeon RX 5700 XT’s 2,134, a delta of 673.4% in NVIDIA’s favor.

Q: Does the AMD Radeon RX 5700 XT have ray tracing cores?

A: No, the RX 5700 XT has no dedicated ray tracing cores. The RTX 5090 D V2 includes 170 RT cores for hardware-accelerated ray tracing.

Q: What is the memory bandwidth difference?

A: The RTX 5090 D V2 has 1.34 TB/s of bandwidth from 24 GB GDDR7 on a 384-bit bus, while the RX 5700 XT has 448.0 GB/s from 8 GB GDDR6 on a 256-bit bus.

Q: Which card has a higher FP32 performance?

A: The RTX 5090 D V2 delivers 104.8 TFLOPS of FP32, compared to the RX 5700 XT’s 9.754 TFLOPS, making the NVIDIA card approximately 10.7 times faster.

Q: Are both cards still in production?

A: No, the RTX 5090 D V2 is listed as Active, while the RX 5700 XT is End-of-life.

Q: What is the launch MSRP for each card?

A: The RTX 5090 D V2 had a launch MSRP of 2,299 USD, and the RX 5700 XT had a launch MSRP of 399 USD.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 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
1605 MHz
2017 MHz
Boost Clock
1905 MHz
2407 MHz
Game Clock
1755 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
8 GB
24 GB
VRAM (MB)
8,192
24,576 +200.0%
Memory Type
GDDR6
GDDR7
Memory Bus
256 bit
384 bit
Bandwidth
448.0 GB/s
1.34 TB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
96 MB
Performance
Pixel Rate
121.9 GPixel/s
423.6 GPixel/s
Texture Rate
304.8 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
9.754 TFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
609.6 GFLOPS (1:16)
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
19.51 TFLOPS (2:1)
104.8 TFLOPS (1:1)
AI/RT
RT Cores
—
170
Tensor Cores
—
680
Power
TDP
225 W
575 W
TDP (W)
225
575 +155.6%
Suggested PSU
550 W
950 W
Power Connectors
1x 6-pin + 1x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 1.0
Blackwell 2.0
GPU Name
Navi 10
GB202
Generation
Navi (RX 5000)
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
Dual-slot
Dual-slot
Length
272 mm 10.7 inches
304 mm 12 inches
Height
111 mm 4.4 inches
137 mm 5.4 inches
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
399 USD
2,299 USD
Production
End-of-life
Active
Predecessor
Vega
GeForce 40
Successor
Navi II
GeForce 60
View Radeon RX 5700 XT Details View GeForce RTX 5090 D V2 Details