AMD Radeon RX 9070 XT vs NVIDIA GeForce RTX 5070 SUPER Comparison

AMD
RADEON

AMD Radeon RX 9070 XT

CORE STATE Navi 48
VRAM 16 GB
CLOCK SPEED 2970 MHz
TDP 304 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 4.0
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

GeForce RTX 5070 SUPER

CORE STATE GB205
VRAM 18 GB
CLOCK SPEED 2512 MHz
TDP 275 W
BUS WIDTH 192 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
7,260
2,690
geekbench_opencl
17,428
N/A
geekbench_vulkan
65,879
N/A
passmark_directx_10
154
N/A
passmark_directx_11
292
N/A
passmark_directx_12
78
N/A
passmark_directx_9
353
N/A
passmark_g2d
1,328
N/A
passmark_g3d
26,795
N/A
passmark_gpu_compute
15,864
N/A

Analysis: AMD Radeon RX 9070 XT vs NVIDIA GeForce RTX 5070 SUPER

Where Each One Wins

The recorded data shows a sharply divided picture between these two graphics cards. The AMD Radeon RX 9070 XT wins the only head-to-head benchmark available, the 3DMark Steel Nomad DX12 test, with a score of 7260 against the NVIDIA GeForce RTX 5070 SUPER's 2690. That is a 169.9% advantage, meaning the AMD card delivers nearly three times the performance in this specific DirectX 12 workload.

The AMD Radeon RX 9070 XT holds the win across every metric where both cards have recorded data. Beyond the single head-to-head result, the RX 9070 XT's broader benchmark suite shows consistent strength: it scores 17,428 in Geekbench OpenCL, 65,879 in Geekbench Vulkan, 26,795 in Passmark G3D, and 15,864 in Passmark GPU Compute. These results place it at the 55th percentile among all GPUs in the database. The NVIDIA GeForce RTX 5070 SUPER, by contrast, has only the one 3DMark Steel Nomad result, which puts it at the 18th percentile. The percentile gap is substantial, 37 points, and it reflects the performance chasm between the two in the measured workload.

The NVIDIA card does not win any recorded benchmark, so its strengths must be assessed qualitatively from the architecture data rather than from score results. The RTX 5070 SUPER carries more shading units, 6400 versus 4096, and includes 200 tensor cores, which the AMD card does not list. These features suggest a different optimization target, but the database contains no benchmark results to confirm any win for NVIDIA in those areas. The only measured comparison, the 3DMark Steel Nomad test, belongs entirely to AMD.

Architecture Differences

The two cards come from different manufacturers, process nodes, and architectural generations, and those differences explain much of the performance gap. The AMD Radeon RX 9070 XT uses the Navi 48 chip built on RDNA 4.0 architecture, manufactured on a 4 nm process at TSMC. It integrates 53,900 million transistors on a 357 mm² die, yielding a transistor density of 151.0 million per mm². The NVIDIA GeForce RTX 5070 SUPER uses the GB205 chip on Blackwell 2.0 architecture, built on a 5 nm process also at TSMC. It packs 31,100 million transistors on a 263 mm² die, for a density of 118.3 million per mm². The AMD chip is larger, denser, and carries roughly 73% more transistors than the NVIDIA chip.

Clock speeds differ significantly. The RX 9070 XT runs a base clock of 1660 MHz, a boost clock of 2970 MHz, and a game clock of 2400 MHz. The RTX 5070 SUPER has a higher base clock at 2325 MHz but a lower boost clock at 2512 MHz. The AMD card's boost clock exceeds the NVIDIA card's by 458 MHz, a substantial margin that contributes to its higher throughput in the recorded benchmark.

Memory configurations also diverge. The RX 9070 XT uses 16 GB of GDDR6 on a 256 bit bus, with a memory clock of 2518 MHz (20.1 Gbps effective), delivering 644.6 GB/s of bandwidth. The RTX 5070 SUPER uses 18 GB of GDDR7 on a 192 bit bus, with a memory clock of 1750 MHz (28 Gbps effective), delivering 672.0 GB/s of bandwidth. The NVIDIA card has 2 GB more capacity and slightly higher bandwidth, but the AMD card has a wider bus. The AMD card also offers higher pixel and texture rates: 380.2 GPixel/s and 760.3 GTexel/s versus 201.0 GPixel/s and 502.4 GTexel/s for NVIDIA. In raw FP32 compute, the RX 9070 XT delivers 48.66 TFLOPS, while the RTX 5070 SUPER delivers 32.15 TFLOPS, a 51% lead for AMD. Both cards support FP16 at a 1:1 ratio with their FP32 figures.

The RX 9070 XT lists 64 ray tracing cores and no tensor cores, while the RTX 5070 SUPER lists 50 ray tracing cores and 200 tensor cores. The AMD card has 128 ROPs and 256 TMUs, whereas the NVIDIA card has 80 ROPs and 200 TMUs. Power consumption is lower on the NVIDIA side at 275 W TDP, compared with 304 W for AMD. The AMD card draws power through two 8-pin connectors and suggests a 700 W PSU, while the NVIDIA card uses a single 16-pin connector and does not list a suggested PSU. The NVIDIA card is physically compact at 245 mm long, 115 mm tall, and 40 mm wide, while the AMD card's dimensions are not recorded. Both use PCIe 5.0 x16, dual-slot cooling, and support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs are similar, with one HDMI 2.1b and three DisplayPort connections, though the AMD card uses DisplayPort 2.1a while NVIDIA uses DisplayPort 2.1b.

Head-to-Head Benchmarks

The only direct comparison in the database is the 3DMark Steel Nomad DX12 test. The AMD Radeon RX 9070 XT scores 7260, and the NVIDIA GeForce RTX 5070 SUPER scores 2690. The delta is 169.9%, meaning the AMD card is 170% faster in this test. That is a decisive margin, not a marginal one. The AMD card's score is 4570 points higher, a gap that dwarfs the NVIDIA card's entire result.

Context from the nearest rivals reinforces the scale of this difference. The RX 9070 XT's average benchmark score is 13,543, placing it just 0.1% above the AMD Radeon HD 7770M, 0.2% above the NVIDIA GeForce GTX 570, 0.5% above the NVIDIA P106-090, and 1% above the AMD Radeon Pro 555. These are extremely close margins, all within 1% of each other, which indicates that the RX 9070 XT sits in a tight cluster of mid-range performers in the database's overall scoring. The RTX 5070 SUPER's average score is 2690, which sits 1% above the NVIDIA Quadro K1100M, 1.1% above the NVIDIA GeForce GT 1030, 1.1% above the Intel Arc Pro B50, and 1.7% above the NVIDIA GeForce GT 440. The NVIDIA card's nearest rivals are all low-end or entry-level parts, which aligns with its 18th percentile standing.

The RX 9070 XT's additional benchmark results provide a fuller picture of its capabilities. In Geekbench OpenCL, it scores 17,428, and in Geekbench Vulkan, it scores 65,879. The Vulkan result is notably higher than the OpenCL result, suggesting strong compute performance under that API. Passmark results show 26,795 in G3D, 15,864 in GPU Compute, 1,328 in G2D, and lower scores in legacy DirectX tests: 353 in DirectX 9, 292 in DirectX 11, 154 in DirectX 10, and 78 in DirectX 12. These legacy scores are not directly comparable to the 3DMark Steel Nomad result, but they indicate that the AMD card performs best in modern APIs and compute workloads. The RTX 5070 SUPER has no such additional measurements, so its performance outside the 3DMark test remains unquantified in the database.

The Verdict

The data points to a clear verdict for the measured workload. The AMD Radeon RX 9070 XT outperforms the NVIDIA GeForce RTX 5070 SUPER in the 3DMark Steel Nomad DX12 benchmark by 169.9%, and it holds the 55th percentile overall, 37 points above the NVIDIA card's 18th percentile. The AMD card also delivers higher raw compute, higher pixel and texture rates, and a larger transistor count on a denser chip. For any use case that relies on the recorded DirectX 12 performance, the RX 9070 XT is the stronger choice.

The NVIDIA card's strengths are architectural rather than measured. It offers 18 GB of GDDR7 memory, 200 tensor cores, a lower 275 W TDP, and a compact physical footprint. Those features may matter in specific contexts, but the database does not include benchmark results that demonstrate a win for NVIDIA. The single recorded score, 2690 in 3DMark Steel Nomad, sits in the 18th percentile, surrounded by rivals such as the GT 1030 and GT 440. That placement does not suggest competitive performance against the RX 9070 XT in the same workload.

For users prioritizing the recorded performance data, the AMD Radeon RX 9070 XT is the clear pick. It wins the only head-to-head test, holds a far higher overall percentile, and shows strong compute results across OpenCL and Vulkan. Its launch MSRP is 599 USD, which the database records without further pricing context. The NVIDIA GeForce RTX 5070 SUPER has no recorded launch MSRP and no winning benchmark, so its position in the database rests entirely on architectural specifications and a single low-scoring result. The verdict from the data is unambiguous: the RX 9070 XT delivers the measured performance, and the RTX 5070 SUPER does not match it in the recorded tests.

FAQ

Q: Which card scores higher in the 3DMark Steel Nomad DX12 benchmark?

A: The AMD Radeon RX 9070 XT scores 7260, while the NVIDIA GeForce RTX 5070 SUPER scores 2690. The AMD card leads by 169.9%.

Q: What are the memory configurations of the two cards?

A: The AMD Radeon RX 9070 XT has 16 GB of GDDR6 on a 256 bit bus with 644.6 GB/s bandwidth. The NVIDIA GeForce RTX 5070 SUPER has 18 GB of GDDR7 on a 192 bit bus with 672.0 GB/s bandwidth.

Q: Which card has more shading units?

A: The NVIDIA GeForce RTX 5070 SUPER has 6400 shading units, while the AMD Radeon RX 9070 XT has 4096 shading units. The NVIDIA card also includes 200 tensor cores, which the AMD card does not list.

Q: How do the cards compare in FP32 compute performance?

A: The AMD Radeon RX 9070 XT delivers 48.66 TFLOPS, while the NVIDIA GeForce RTX 5070 SUPER delivers 32.15 TFLOPS. The AMD card is 51% higher in this metric.

Q: What is the overall percentile ranking for each card?

A: The AMD Radeon RX 9070 XT sits at the 55th percentile among all GPUs, with an average benchmark score of 13,543. The NVIDIA GeForce RTX 5070 SUPER sits at the 18th percentile, with an average benchmark score of 2690.

Q: Which card has the lower power draw?

A: The NVIDIA GeForce RTX 5070 SUPER has a TDP of 275 W, while the AMD Radeon RX 9070 XT has a TDP of 304 W. The NVIDIA card uses a single 16-pin power connector, while the AMD card uses two 8-pin connectors and suggests a 700 W PSU.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 9070 XT
RTX 5070 SUPER
Core Specs
Shading Units
4,096
6,400 +56.3%
Shaders
4,096
6,400 +56.3%
TMUs
256
200 -21.9%
ROPs
128
80 -37.5%
Compute Units
64
—
Clocks
Base Clock
1660 MHz
2325 MHz
Boost Clock
2970 MHz
2512 MHz
Game Clock
2400 MHz
—
Memory Clock
2518 MHz 20.1 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
16 GB
18 GB
VRAM (MB)
16,384
18,432 +12.5%
Memory Type
GDDR6
GDDR7
Memory Bus
256 bit
192 bit
Bandwidth
644.6 GB/s
672.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
8 MB
48 MB
L3 Cache
64 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
380.2 GPixel/s
201.0 GPixel/s
Texture Rate
760.3 GTexel/s
502.4 GTexel/s
FP32 (TFLOPS)
48.66 TFLOPS
32.15 TFLOPS
FP64 (TFLOPS)
1.521 TFLOPS (1:32)
502.4 GFLOPS (1:64)
FP16 (TFLOPS)
48.66 TFLOPS (1:1)
32.15 TFLOPS (1:1)
AI/RT
RT Cores
64
50 -21.9%
Tensor Cores
—
200
Matrix Cores
128
—
Power
TDP
304 W
275 W
TDP (W)
304
275 -9.5%
Suggested PSU
700 W
—
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 4.0
Blackwell 2.0
GPU Name
Navi 48
GB205
Generation
Navi IV (RX 9000)
GeForce 50
Process Size
4 nm
5 nm
Transistors
53,900 million
31,100 million
Die Size
357 mm²
263 mm²
Foundry
TSMC
TSMC
Density
151.0M / mm²
118.3M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.2
3.0
Shader Model
6.9
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
—
245 mm 9.6 inches
Height
—
115 mm 4.5 inches
Outputs
1x HDMI 2.1b3x DisplayPort 2.1a
1x HDMI 2.1b 3x DisplayPort 2.1b
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Other
Launch Price
599 USD
—
Production
Active
Active
Predecessor
Navi III
—
View Radeon RX 9070 XT Details View GeForce RTX 5070 SUPER Details