AMD Radeon RX 6800 XT vs NVIDIA GeForce RTX 5090 D Comparison

AMD
RADEON

AMD Radeon RX 6800 XT

CORE STATE Navi 21
VRAM 16 GB
CLOCK SPEED 2250 MHz
TDP 300 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2020
VS
NVIDIA
GEFORCE

GeForce RTX 5090 D

CORE STATE GB202
VRAM 32 GB
CLOCK SPEED 2407 MHz
TDP 575 W
BUS WIDTH 512 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
3,689
14,326
geekbench_metal
181,337
N/A
geekbench_opencl
171,304
310,674
geekbench_vulkan
136,875
376,915
passmark_directx_10
155
231
passmark_directx_11
264
371
passmark_directx_12
100
219
passmark_directx_9
265
434
passmark_g2d
1,030
1,487
passmark_g3d
24,980
44,065
passmark_gpu_compute
13,245
28,396

Analysis: AMD Radeon RX 6800 XT vs NVIDIA GeForce RTX 5090 D

Head-to-Head Benchmarks

The benchmark record is unambiguous: the NVIDIA GeForce RTX 5090 D wins all ten head-to-head tests, with margins that range from substantial to overwhelming. The largest single gap appears in 3DMark Steel Nomad DX12, where the RTX 5090 D scores 14,326 against the RX 6800 XT's 3,689, a delta of 288.3%. That is not a close contest; it is a generational gap expressed in a single workload.

Vulkan performance tells a similar story. The RTX 5090 D posts 376,915 in Geekbench Vulkan versus 136,875 for the RX 6800 XT, a 175.4% advantage. OpenCL is less extreme but still decisive: 310,674 versus 171,304, a lead of 81.4%. The pattern holds across legacy DX9, DX10, and DX11 tests. In PassMark DX9, the RTX 5090 D scores 434 versus 265, a 63.8% edge. In DX10, it is 231 versus 155, or 49% ahead. DX11 shows 371 versus 264, a 40.5% margin.

The DX12 PassMark test produces one of the more striking results: the RTX 5090 D scores 219, the RX 6800 XT scores 100, a 119% advantage. The compute-oriented PassMark GPU Compute test shows 28,396 versus 13,245, a 114.4% lead. Even the 2D-focused PassMark G2D test, which typically favors older or simpler architectures, goes to the RTX 5090 D at 1,487 versus 1,030, a 44.4% gain. Finally, the aggregate PassMark G3D score lands at 44,065 for the RTX 5090 D against 24,980 for the RX 6800 XT, a 76.4% difference.

The average benchmark score in the database reinforces this hierarchy: the RTX 5090 D averages 77,712 across all recorded tests, while the RX 6800 XT averages 48,477. That is a 60.3% higher average, which is consistent with the individual test deltas. The RTX 5090 D sits at the 92nd percentile of all GPUs, the RX 6800 XT at the 85th. Neither is a weak card, but the raw performance gap is large enough that the RX 6800 XT's nearest rivals in the database are the NVIDIA RTX A1000 Mobile, Intel Arc A550M, RTX 5070 Ti, and RX Vega 64, all within a 3% band of its average score. The RTX 5090 D, by contrast, sits near the NVIDIA Tesla P100 family and the RX 6850M XT, all within roughly 2.4% of its average.

Architecture Differences

The two GPUs come from different design philosophies and different process generations. The RTX 5090 D is built on the Blackwell 2.0 architecture, using NVIDIA's GB202 chip, fabricated on a 5 nm process at TSMC. The RX 6800 XT uses AMD's RDNA 2.0 architecture, with the Navi 21 chip, on a 7 nm process, also at TSMC. The process node difference translates directly into transistor density: the RTX 5090 D packs 92,200 million transistors into a 750 mm² die, yielding 122.9 million transistors per square millimeter. The RX 6800 XT has 26,800 million transistors on a 520 mm² die, for 51.5 million per square millimeter. That is a 2.4x density advantage for the newer part.

The core counts reflect the scale difference. The RTX 5090 D has 21,760 shading units, 680 texture mapping units, and 176 ROPs. The RX 6800 XT has 4,608 shading units, 288 TMUs, and 128 ROPs. Ray tracing hardware is also asymmetric: 170 RT cores for the RTX 5090 D versus 72 for the RX 6800 XT. The RTX 5090 D additionally features 680 tensor cores, a resource the RX 6800 XT does not include at all; the database records no tensor core count for the AMD card.

Memory is another major divergence. The RTX 5090 D ships with 32 GB of GDDR7 on a 512-bit bus, delivering 1.79 TB/s of bandwidth. The RX 6800 XT has 16 GB of GDDR6 on a 256-bit bus, with 512.0 GB/s. That is a 3.5x bandwidth advantage for the NVIDIA part, which matters for high-resolution textures and compute workloads. The RX 6800 XT does counter with a higher memory clock specification in some senses, but the effective bandwidth gap is determined by bus width and memory generation, not raw clock.

Clock speeds tell a more nuanced story. The RTX 5090 D has a base clock of 2017 MHz and a boost of 2407 MHz. The RX 6800 XT has a base of 1825 MHz, a game clock of 2015 MHz, and a boost of 2250 MHz. The NVIDIA chip runs faster at both base and boost, but the AMD card's game clock is a useful reference for sustained gaming performance. Even so, the throughput figures are far apart: the RTX 5090 D reaches 104.8 TFLOPS FP32 and 104.8 TFLOPS FP16 (1:1 ratio), while the RX 6800 XT delivers 20.74 TFLOPS FP32 and 41.47 TFLOPS FP16 (2:1 ratio). The pixel rate is 423.6 GPixel/s versus 288.0 GPixel/s, and the texture rate is 1,636.8 GTexel/s versus 648.0 GTexel/s.

Power and interface specifications also differ. The RTX 5090 D has a TDP of 575 W, requires a 950 W suggested PSU, and uses a single 16-pin power connector. The RX 6800 XT has a TDP of 300 W, a 700 W suggested PSU, and uses two 8-pin connectors. The RTX 5090 D runs on PCIe 5.0 x16, the RX 6800 XT on PCIe 4.0 x16. Display outputs diverge as well: the RTX 5090 D offers 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RX 6800 XT provides 1x HDMI 2.1, 2x DisplayPort 1.4a, and 1x USB Type-C.

The Verdict

The data points to a clear conclusion: the RTX 5090 D is the faster card in every measured benchmark. The question is not whether it wins, but by how much, and the margins range from 40.5% to 288.3%. For users who prioritize raw performance, ray tracing capability, or compute throughput, the RTX 5090 D is the only choice in this comparison. Its 32 GB of GDDR7 memory and 1.79 TB/s bandwidth provide headroom that the RX 6800 XT cannot match, and its 170 RT cores and 680 tensor cores open up workloads that the AMD card cannot accelerate at all.

However, the RX 6800 XT is not without merit in specific contexts. It is an end-of-life product, but it still sits in the 85th percentile of all GPUs, and its 16 GB of GDDR6 memory on a 256-bit bus is a capable configuration for 1440p and even some 4K gaming. Its 300 W TDP and 700 W PSU requirement make it far less demanding on system power delivery. For users building a system with an existing 700 W PSU or a smaller chassis, the RX 6800 XT's dual-slot form factor and two 8-pin connectors are easier to accommodate than the RTX 5090 D's 575 W TDP and 16-pin connector.

The API support is identical: both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. That means software compatibility is not a differentiator. The production status is: the RTX 5090 D is Active, the RX 6800 XT is End-of-life. The RTX 5090 D is the current generation, the RX 6800 XT is two generations old in AMD's lineup. For anyone buying new hardware today, the RTX 5090 D is the data-backed recommendation. For someone who already owns an RX 6800 XT, the benchmark data suggests an upgrade would yield dramatic improvements, but the power supply and connector requirements must be verified first.

Specification Differences

The following fields differ between the two cards, based on the database records:

| Specification | NVIDIA GeForce RTX 5090 D | AMD Radeon RX 6800 XT |

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

| Architecture | Blackwell 2.0 | RDNA 2.0 |

| Process node | 5 nm | 7 nm |

| Transistors | 92,200 million | 26,800 million |

| Die size | 750 mm² | 520 mm² |

| Transistor density | 122.9M / mm² | 51.5M / mm² |

| Base clock | 2017 MHz | 1825 MHz |

| Boost clock | 2407 MHz | 2250 MHz |

| Game clock | None recorded | 2015 MHz |

| Memory clock | 1750 MHz, 28 Gbps effective | 2000 MHz, 16 Gbps effective |

| Memory size | 32 GB | 16 GB |

| Memory type | GDDR7 | GDDR6 |

| Memory bus | 512 bit | 256 bit |

| Memory bandwidth | 1.79 TB/s | 512.0 GB/s |

| Shading units | 21,760 | 4,608 |

| TMUs | 680 | 288 |

| ROPs | 176 | 128 |

| RT cores | 170 | 72 |

| Tensor cores | 680 | None recorded |

| Pixel rate | 423.6 GPixel/s | 288.0 GPixel/s |

| Texture rate | 1,636.8 GTexel/s | 648.0 GTexel/s |

| FP32 | 104.8 TFLOPS | 20.74 TFLOPS |

| FP16 | 104.8 TFLOPS (1:1) | 41.47 TFLOPS (2:1) |

| TDP | 575 W | 300 W |

| Power connectors | 1x 16-pin | 2x 8-pin |

| Suggested PSU | 950 W | 700 W |

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

| Display outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b | 1x HDMI 2.1, 2x DisplayPort 1.4a, 1x USB Type-C |

| Dimensions | 304 mm x 137 mm x 48 mm | 267 mm x 120 mm x 50 mm |

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

| Release date | 2025-01-29 | 2020-10-27 |

| Launch MSRP | 2,299 USD | 649 USD |

FAQ

Q: Which GPU wins the most head-to-head benchmarks?

A: The NVIDIA GeForce RTX 5090 D wins all ten recorded head-to-head tests, with a 100% win rate. The AMD Radeon RX 6800 XT wins none of them.

Q: What is the biggest performance gap between the two cards?

A: The largest delta is in 3DMark Steel Nomad DX12, where the RTX 5090 D scores 14,326 versus 3,689 for the RX 6800 XT, a 288.3% advantage.

Q: How does memory bandwidth compare?

A: The RTX 5090 D has 1.79 TB/s of bandwidth from 32 GB of GDDR7 on a 512-bit bus. The RX 6800 XT has 512.0 GB/s from 16 GB of GDDR6 on a 256-bit bus.

Q: Does the RX 6800 XT have tensor cores?

A: No. The database records 680 tensor cores for the RTX 5090 D, but no tensor core count for the RX 6800 XT.

Q: What is the TDP difference?

A: The RTX 5090 D has a TDP of 575 W with a suggested PSU of 950 W. The RX 6800 XT has a TDP of 300 W with a suggested PSU of 700 W.

Q: Are the two cards in the same performance percentile?

A: No. The RTX 5090 D is in the 92nd percentile of all GPUs, while the RX 6800 XT is in the 85th percentile. Their average benchmark scores are 77,712 and 48,477, respectively.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6800 XT
RTX 5090 D
Core Specs
Shading Units
4,608
21,760 +372.2%
Shaders
4,608
21,760 +372.2%
TMUs
288
680 +136.1%
ROPs
128
176 +37.5%
Compute Units
72
—
SM Count
—
170
Clocks
Base Clock
1825 MHz
2017 MHz
Boost Clock
2250 MHz
2407 MHz
Game Clock
2015 MHz
—
Memory Clock
2000 MHz 16 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
16 GB
32 GB
VRAM (MB)
16,384
32,768 +100.0%
Memory Type
GDDR6
GDDR7
Memory Bus
256 bit
512 bit
Bandwidth
512.0 GB/s
1.79 TB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
4 MB
96 MB
L3 Cache
128 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
288.0 GPixel/s
423.6 GPixel/s
Texture Rate
648.0 GTexel/s
1,636.8 GTexel/s
FP32 (TFLOPS)
20.74 TFLOPS
104.8 TFLOPS
FP64 (TFLOPS)
1,296.0 GFLOPS (1:16)
1.637 TFLOPS (1:64)
FP16 (TFLOPS)
41.47 TFLOPS (2:1)
104.8 TFLOPS (1:1)
AI/RT
RT Cores
72
170 +136.1%
Tensor Cores
—
680
Power
TDP
300 W
575 W
TDP (W)
300
575 +91.7%
Suggested PSU
700 W
950 W
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 2.0
Blackwell 2.0
GPU Name
Navi 21
GB202
Generation
Navi II (RX 6000)
GeForce 50
Process Size
7 nm
5 nm
Transistors
26,800 million
92,200 million
Die Size
520 mm²
750 mm²
Foundry
TSMC
TSMC
Density
51.5M / mm²
122.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
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
267 mm 10.5 inches
304 mm 12 inches
Height
120 mm 4.7 inches
137 mm 5.4 inches
Outputs
1x HDMI 2.12x DisplayPort 1.4a1x USB Type-C
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
649 USD
2,299 USD
Production
End-of-life
Active
Predecessor
Navi
GeForce 40
Successor
Navi III
GeForce 60
View Radeon RX 6800 XT Details View GeForce RTX 5090 D Details