GeForce RTX 5050 vs Radeon RX 6900 XT

#ad 
Buy on Amazon
VS

Aggregate performance score

We've compared Radeon RX 6900 XT and GeForce RTX 5050, covering specs and all relevant benchmarks.

RX 6900 XT
2020, $999
16 GB GDDR6, 300 Watt
63.66
+59.1%

6900 XT outperforms RTX 5050 by an impressive 59% based on our aggregate benchmark results.

Primary details

GPU architecture, market segment, value for money and other general parameters compared.

Place in the ranking36124
Place by popularitynot in top-10017
Cost-effectiveness evaluation27.1997.53
Power efficiency16.5223.96
ArchitectureRDNA 2.0 (2020−2025)Blackwell 2.0 (2025−2026)
GPU code nameNavi 21GB207
Market segmentDesktopDesktop
Release date28 October 2020 (5 years ago)1 July 2025 (1 year ago)
Launch price (MSRP)$999 $249

Cost-effectiveness evaluation

The higher the ratio, the better. We use the manufacturer's recommended prices.

RTX 5050 has 259% better value for money than RX 6900 XT.

Performance to price scatter graph

Currently popular graphics cards are shown for comparison.

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.

Pipelines / CUDA cores51202560
Core clock speed1825 MHz2317 MHz
Boost clock speed2250 MHz2572 MHz
Number of transistors26,800 million16,900 million
Manufacturing process technology7 nm5 nm
Power consumption (TDP)300 Watt130 Watt
Texture fill rate720.0205.8
Floating-point processing power23.04 TFLOPSno data
ROPs12832
TMUs32080
Tensor Coresno data80
Ray Tracing Cores8020
L0 Cache1.3 MBno data
L1 Cache1 MB2.5 MB
L2 Cache4 MB24 MB
L3 Cache128 MBno data

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

InterfacePCIe 4.0 x16PCIe 5.0 x8
Length267 mmno data
Width3-slot2-slot
Supplementary power connectors2x 8-pin1x 8-pin

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory typeGDDR6GDDR6
Maximum RAM amount16 GB8 GB
Memory bus width256 Bit128 Bit
Memory clock speed2000 MHz2500 MHz
Memory bandwidth512.0 GB/s320.0 GB/s
Shared memory--
Resizable BAR++

Connectivity and outputs

This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.

Display Connectors1x HDMI 2.1, 2x DisplayPort 1.4a, 1x USB Type-C1x HDMI 2.1b, 3x DisplayPort 2.1b
HDMI++

API and SDK support

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX12 Ultimate (12_2)12 Ultimate (12_2)
Shader Model6.86.9
OpenGL4.64.6
OpenCL2.13.0
Vulkan1.31.4
CUDA-12.0
DLSS-+

Synthetic benchmarks

Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.


Combined synthetic benchmark score

This is our combined benchmark score.

RX 6900 XT 63.66
+59.1%
RTX 5050 40.01

Passmark

This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.

RX 6900 XT 26633
+59.1%
Samples: 8454
RTX 5050 16738
Samples: 3054

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Average FPS across all PC games

Here are the average frames per second in a large set of popular games across different resolutions:

Full HD199
+65.8%
120−130
1440p13785−90
−38%
4K85
+70%
50−55

Cost per frame, $

1080p5.022.08
+58.7%
1440p7.292.93
+59.8%
4K11.754.98
+57.6%
  • RTX 5050 has 59% lower cost per frame in 1080p
  • RTX 5050 has 60% lower cost per frame in 1440p
  • RTX 5050 has 58% lower cost per frame in 4K

FPS performance in popular games

Full HD
Low

Counter-Strike 2 300−350
+62.1%
190−200
Cyberpunk 2077 160−170
+61%
100−105
Resident Evil 4 Remake 190−200
+63.3%
120−130

Full HD
Medium

Battlefield 5 195
+62.5%
120−130
Counter-Strike 2 300−350
+62.1%
190−200
Cyberpunk 2077 160−170
+61%
100−105
Far Cry 5 190−200
+59.2%
120−130
Fortnite 300−350
+67.8%
180−190
Forza Horizon 4 283
+66.5%
170−180
PLAYERUNKNOWN'S BATTLEGROUNDS 170−180
+73%
100−105
Valorant 350−400
+63.5%
230−240

Full HD
High

Battlefield 5 196
+63.3%
120−130
Counter-Strike 2 300−350
+62.1%
190−200
Counter-Strike: Global Offensive 270−280
+63.5%
170−180
Cyberpunk 2077 160−170
+61%
100−105
Dota 2 160−170
+69%
100−105
Far Cry 5 190−200
+59.2%
120−130
Far Cry 6 170−180
+60.9%
110−120
Fortnite 300−350
+67.8%
180−190
Forza Horizon 4 279
+64.1%
170−180
Grand Theft Auto V 160−170
+69%
100−105
Metro Exodus 164
+64%
100−105
PLAYERUNKNOWN'S BATTLEGROUNDS 170−180
+73%
100−105
The Witcher 3: Wild Hunt 323
+61.5%
200−210
Valorant 350−400
+63.5%
230−240

Full HD
Ultra

Battlefield 5 197
+64.2%
120−130
Cyberpunk 2077 160−170
+61%
100−105
Dota 2 160−170
+69%
100−105
Far Cry 5 190−200
+59.2%
120−130
Forza Horizon 4 248
+65.3%
150−160
PLAYERUNKNOWN'S BATTLEGROUNDS 170−180
+73%
100−105
The Witcher 3: Wild Hunt 164
+64%
100−105
Valorant 411
+64.4%
250−260

Full HD
Epic

Fortnite 300−350
+67.8%
180−190

1440p
High

Counter-Strike 2 190−200
+63.3%
120−130
Counter-Strike: Global Offensive 500−550
+67.7%
300−310
Far Cry 6 130−140
+61.2%
85−90
Grand Theft Auto V 130−140
+62.4%
85−90
Metro Exodus 102
+70%
60−65
PLAYERUNKNOWN'S BATTLEGROUNDS 170−180
+75%
100−105
Valorant 450−500
+61.1%
280−290

1440p
Ultra

Battlefield 5 196
+63.3%
120−130
Cyberpunk 2077 90−95
+67.3%
55−60
Far Cry 5 160−170
+65%
100−105
Forza Horizon 4 231
+65%
140−150
The Witcher 3: Wild Hunt 150−160
+64.2%
95−100

1440p
Epic

Fortnite 150−160
+67.8%
90−95

4K
High

Counter-Strike 2 85−90
+60%
55−60
Far Cry 6 80−85
+60%
50−55
Grand Theft Auto V 150−160
+66.3%
95−100
Metro Exodus 67
+67.5%
40−45
The Witcher 3: Wild Hunt 122
+62.7%
75−80
Valorant 300−350
+67.4%
190−200

4K
Ultra

Battlefield 5 134
+67.5%
80−85
Counter-Strike 2 85−90
+60%
55−60
Cyberpunk 2077 40−45
+63%
27−30
Dota 2 150−160
+67.4%
95−100
Far Cry 5 100−110
+61.5%
65−70
Forza Horizon 4 162
+62%
100−105
PLAYERUNKNOWN'S BATTLEGROUNDS 95−100
+60%
60−65

4K
Epic

Fortnite 75−80
+75.6%
45−50

This is how RX 6900 XT and RTX 5050 compete in popular games:

  • RX 6900 XT is 66% faster in 1080p
  • RX 6900 XT is 61% faster in 1440p
  • RX 6900 XT is 70% faster in 4K

Pros & cons summary


Performance score 63.66 40.01
Recency 28 October 2020 1 July 2025
Maximum RAM amount 16 GB 8 GB
Chip lithography 7 nm 5 nm
Power consumption (TDP) 300 Watt 130 Watt

RX 6900 XT has a 59% higher aggregate performance score, and a 100% higher maximum VRAM amount.

RTX 5050, on the other hand, has an age advantage of 4 years, a 29% more advanced lithography process, and 57% lower power consumption.

The Radeon RX 6900 XT is our recommended choice as it beats the GeForce RTX 5050 in performance tests.

Other comparisons

We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.

Community ratings

Here you can see the user ratings of the compared graphics cards, as well as rate them yourself.


4.1 4499 votes

Rate Radeon RX 6900 XT on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5
3.8 2329 votes

Rate GeForce RTX 5050 on a scale of 1 to 5:

  • 1
  • 2
  • 3
  • 4
  • 5

Comments

Here you can give us your opinion about Radeon RX 6900 XT or GeForce RTX 5050, agree or disagree with our ratings, or report errors or inaccuracies on the site.