AMD Radeon RX 7700 XT vs NVIDIA GeForce RTX 5090 SE Comparison

AMD
RADEON

AMD Radeon RX 7700 XT

CORE STATE Navi 32
VRAM 12 GB
CLOCK SPEED 2544 MHz
TDP 245 W
BUS WIDTH 192 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 5 nm
LAUNCH DATE 2023
VS
NVIDIA
GEFORCE

GeForce RTX 5090 SE

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2377 MHz
TDP 500 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
3,316
N/A
geekbench_opencl
138,383
N/A
geekbench_vulkan
46,443
N/A
passmark_directx_10
119
N/A
passmark_directx_11
232
N/A
passmark_directx_12
79
N/A
passmark_directx_9
294
N/A
passmark_g2d
1,161
N/A
passmark_g3d
22,547
N/A
passmark_gpu_compute
12,912
N/A

Analysis: AMD Radeon RX 7700 XT vs NVIDIA GeForce RTX 5090 SE

AMD Radeon RX 7700 XT and NVIDIA GeForce RTX 5090 SE sit at opposite ends of the performance spectrum within the database. The RX 7700 XT is an active, shipping product with a substantial body of recorded benchmark results, while the RTX 5090 SE is a newly listed part with no completed measurements yet, holding a placeholder percentile of 50 and an average score of zero. This makes a direct numerical comparison impossible, but the available specification data and the RX 7700 XT’s established results provide a clear picture of what each card is built to do.

Where Each One Wins

The AMD Radeon RX 7700 XT wins in the only category where actual benchmark data exists: measured performance. Its average benchmark score of 22,549 places it in the 67th percentile of all GPUs tracked by the database, with a spread of results across DirectX 10, 11, 12, and 9 tests, OpenCL, Vulkan, and compute workloads. The recorded data shows a 3DMark Steel Nomad DX12 score of 3,316, a Geekbench OpenCL score of 138,383, and a Geekbench Vulkan score of 46,443. PassMark results include a G3D score of 22,547, a G2D score of 1,161, and a GPU compute score of 12,912. These are real, verifiable wins against the RTX 5090 SE, which has no benchmark entries at all.

The NVIDIA GeForce RTX 5090 SE wins on raw hardware capability as defined by its specifications. It carries 14,080 shading units, 440 texture mapping units, 160 ROPs, 110 RT cores, and 440 tensor cores. Its FP32 compute is rated at 66.94 TFLOPS, and its pixel rate is 380.3 GPixel/s with a texture rate of 1,045.9 GTexel/s. The RX 7700 XT, by contrast, has 3,456 shading units, 216 TMUs, 96 ROPs, 54 RT cores, and no tensor cores, with FP32 at 35.17 TFLOPS, pixel rate at 244.2 GPixel/s, and texture rate at 549.5 GTexel/s. The RTX 5090 SE is the clear winner in theoretical throughput, memory bandwidth, and feature set, but none of that is yet reflected in measured scores.

The Verdict

The data supports a clear split: the RX 7700 XT is the card with proven results, while the RTX 5090 SE is the card with untested potential. For anyone relying on existing benchmark data to make a purchasing decision, the RX 7700 XT is the only option with recorded performance. It sits comfortably in the 67th percentile, with its nearest rivals being the NVIDIA GeForce RTX 5060 Mobile (0.5% ahead), the NVIDIA GeForce RTX 4060 Mobile (0.8% behind), the NVIDIA GeForce RTX 2080 (1.5% behind), and the AMD Radeon RX 5700 (1.7% ahead). These small deltas indicate the RX 7700 XT is competitive with a cluster of mid-range cards, and its 12 GB of GDDR6 memory on a 192-bit bus delivers 432.0 GB/s of bandwidth.

The RTX 5090 SE, with no benchmark scores, cannot be recommended on measured performance. Its specifications, however, suggest a far more capable card. The 24 GB of GDDR7 memory on a 384-bit bus provides 1.34 TB/s of bandwidth, and the 110 RT cores plus 440 tensor cores indicate a card designed for heavy ray tracing and AI workloads. The 500 W TDP and 900 W suggested PSU requirement reflect a high-power part intended for top-tier systems. The verdict from the data is straightforward: the RX 7700 XT is the proven performer today, and the RTX 5090 SE is the unverified high-end contender that must await benchmark results before its place can be confirmed.

Head-to-Head Benchmarks

There are no head-to-head benchmark entries in the database for these two cards, and the RTX 5090 SE has no individual benchmark scores recorded. The comparison must therefore rely on the RX 7700 XT’s absolute scores and its position relative to its nearest rivals, rather than direct matchup data. The RX 7700 XT’s average score of 22,549 places it 0.5% behind the RTX 5060 Mobile’s 22,435, 0.8% ahead of the RTX 4060 Mobile’s 22,729, 1.5% above the RTX 2080’s 22,895, and 1.7% behind the RX 5700’s 22,170. Note that these deltas are expressed as the RX 7700 XT’s score relative to each rival, so a positive delta means it is ahead. The RX 7700 XT is ahead of the RTX 4060 Mobile and the RTX 2080, and behind the RTX 5060 Mobile and the RX 5700, but all margins are within 1.7%.

The RX 7700 XT’s individual test results show its strengths. The PassMark G3D score of 22,547 is its most substantial single result, while the Geekbench OpenCL score of 138,383 indicates strong compute throughput. The 3DMark Steel Nomad DX12 score of 3,316 is a modern DirectX 12 workload, and the Vulkan score of 46,443 shows API versatility. The PassMark DirectX 9 score of 294 and DirectX 10 score of 119 are legacy tests where the card still performs, while the DirectX 11 score of 232 and DirectX 12 score of 79 round out the feature set. The G2D score of 1,161 covers 2D workloads, and the GPU compute score of 12,912 adds another compute metric. Against the RTX 5090 SE, these are the only numbers available, and they establish the RX 7700 XT as a functional, measurable GPU.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon RX 7700 XT has an average benchmark score of 22,549. The NVIDIA GeForce RTX 5090 SE has an average score of 0 because no benchmarks have been recorded for it.

Q: What is the difference in memory bandwidth between the two cards?

A: The RX 7700 XT provides 432.0 GB/s of bandwidth from 12 GB of GDDR6 memory on a 192-bit bus. The RTX 5090 SE provides 1.34 TB/s from 24 GB of GDDR7 memory on a 384-bit bus.

Q: How do the shading unit counts compare?

A: The RX 7700 XT has 3,456 shading units, while the RTX 5090 SE has 14,080 shading units. The RTX 5090 SE also has 440 tensor cores and 110 RT cores, whereas the RX 7700 XT has 54 RT cores and no tensor cores.

Q: Which card has a higher FP32 compute rating?

A: The RTX 5090 SE is rated at 66.94 TFLOPS FP32, while the RX 7700 XT is rated at 35.17 TFLOPS FP32. Both cards support FP16 at a 1:1 ratio with their FP32 figures.

Q: What are the power requirements for each card?

A: The RX 7700 XT has a TDP of 245 W with a suggested PSU of 550 W and uses 2x 8-pin power connectors. The RTX 5090 SE has a TDP of 500 W with a suggested PSU of 900 W and uses a single 16-pin connector.

Q: Which card has a higher pixel rate?

A: The RTX 5090 SE has a pixel rate of 380.3 GPixel/s and a texture rate of 1,045.9 GTexel/s. The RX 7700 XT has a pixel rate of 244.2 GPixel/s and a texture rate of 549.5 GTexel/s.

Architecture Differences

The two cards are built on fundamentally different architectures. The RX 7700 XT uses AMD’s RDNA 3.0 architecture with the Navi 32 chip, part of the Navi III (RX 7000) generation. It is fabricated on TSMC’s 5 nm process with 28,100 million transistors on a 346 mm² die, giving a transistor density of 81.2 million per mm². The RTX 5090 SE uses NVIDIA’s Blackwell 2.0 architecture with the GB202 chip, part of the GeForce 50 generation. It is also fabricated on TSMC’s 5 nm process, but with 92,200 million transistors on a 750 mm² die, yielding a density of 122.9 million per mm². The RTX 5090 SE has more than three times the transistor count and more than double the die area.

The feature sets diverge significantly. The RTX 5090 SE includes 440 tensor cores, which the RX 7700 XT lacks entirely, and has 110 RT cores compared to the RX 7700 XT’s 54. Memory technology differs as well: the RX 7700 XT uses GDDR6 while the RTX 5090 SE uses GDDR7. The bus interfaces also differ, with the RX 7700 XT on PCIe 4.0 x16 and the RTX 5090 SE on PCIe 5.0 x16. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 7700 XT’s display outputs include 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C, while the RTX 5090 SE offers 1x HDMI 2.1b and 3x DisplayPort 2.1b. The RTX 5090 SE is listed with a predecessor of GeForce 40 and a successor of GeForce 60, while the RX 7700 XT lists Navi II as its predecessor and Navi IV as its successor.

Specification Differences

The specification table shows clear separation between the two cards. The RX 7700 XT has a base clock of 1435 MHz, a boost clock of 2544 MHz, and a game clock of 2171 MHz, with memory clocked at 2250 MHz (18 Gbps effective). The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz, with no game clock listed, and memory clocked at 1750 MHz (28 Gbps effective). The RX 7700 XT’s memory configuration is 12 GB GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth. The RTX 5090 SE’s is 24 GB GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth.

Compute resources differ substantially: the RX 7700 XT has 3,456 shading units, 216 TMUs, and 96 ROPs, while the RTX 5090 SE has 14,080 shading units, 440 TMUs, and 160 ROPs. RT cores are 54 versus 110, and tensor cores are absent on the AMD card versus 440 on the NVIDIA card. Pixel rates are 244.2 GPixel/s versus 380.3 GPixel/s, and texture rates are 549.5 GTexel/s versus 1,045.9 GTexel/s. FP32 compute is 35.17 TFLOPS versus 66.94 TFLOPS, with FP16 matching at 1:1 on both.

Power and physical specifications also differ. The RX 7700 XT has a TDP of 245 W, uses 2x 8-pin connectors, and suggests a 550 W PSU. The RTX 5090 SE has a TDP of 500 W, uses a 1x 16-pin connector, and suggests a 900 W PSU. Both are dual-slot cards, but dimensions vary: the RX 7700 XT measures 267 mm in length, 135 mm in height, and 50 mm in width, while the RTX 5090 SE is 267 mm long, 111 mm high, and 40 mm wide. The RX 7700 XT was released on September 5, 2023, with a launch MSRP of 449 USD, and the RTX 5090 SE is listed with a release date of December 31, 2025, and a launch MSRP of 1,499 USD. The RX 7700 XT has a production status of Active, and the RTX 5090 SE is also listed as Active.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 7700 XT
RTX 5090 SE
Core Specs
Shading Units
3,456
14,080 +307.4%
Shaders
3,456
14,080 +307.4%
TMUs
216
440 +103.7%
ROPs
96
160 +66.7%
Compute Units
54
—
SM Count
—
110
Clocks
Base Clock
1435 MHz
1740 MHz
Boost Clock
2544 MHz
2377 MHz
Game Clock
2171 MHz
—
Shader Clock
2171 MHz
—
Memory Clock
2250 MHz 18 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
12 GB
24 GB
VRAM (MB)
12,288
24,576 +100.0%
Memory Type
GDDR6
GDDR7
Memory Bus
192 bit
384 bit
Bandwidth
432.0 GB/s
1.34 TB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
96 MB
L3 Cache
48 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
244.2 GPixel/s
380.3 GPixel/s
Texture Rate
549.5 GTexel/s
1,045.9 GTexel/s
FP32 (TFLOPS)
35.17 TFLOPS
66.94 TFLOPS
FP64 (TFLOPS)
1,099.0 GFLOPS (1:32)
1,045.9 GFLOPS (1:64)
FP16 (TFLOPS)
35.17 TFLOPS (1:1)
66.94 TFLOPS (1:1)
AI/RT
RT Cores
54
110 +103.7%
Tensor Cores
—
440
Matrix Cores
108
—
Power
TDP
245 W
500 W
TDP (W)
245
500 +104.1%
Suggested PSU
550 W
900 W
Power Connectors
2x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 3.0
Blackwell 2.0
GPU Name
Navi 32
GB202
Codename
Wheat Nas
—
Generation
Navi III (RX 7000)
GeForce 50
Process Size
5 nm
5 nm
Transistors
28,100 million
92,200 million
Die Size
346 mm²
750 mm²
Foundry
TSMC
TSMC
Density
81.2M / 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
2.2
3.0
CUDA
—
12.0
Shader Model
6.9
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
267 mm 10.5 inches
Height
135 mm 5.3 inches
111 mm 4.4 inches
Outputs
1x HDMI 2.1a2x DisplayPort 2.11x USB Type-C
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 4.0 x16
PCIe 5.0 x16
Other
Launch Price
449 USD
1,499 USD
Production
Active
Active
Predecessor
Navi II
GeForce 40
Successor
Navi IV
GeForce 60
View Radeon RX 7700 XT Details View GeForce RTX 5090 SE Details