AMD Radeon RX 7800 XT vs NVIDIA GeForce GTX 950 Comparison

AMD
RADEON

AMD Radeon RX 7800 XT

CORE STATE Navi 32
VRAM 16 GB
CLOCK SPEED 2430 MHz
TDP 263 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 3.0
nm
PROCESS 5 nm
LAUNCH DATE 2023
VS
NVIDIA
GEFORCE

GeForce GTX 950

CORE STATE GM206
VRAM 2 GB
CLOCK SPEED 1188 MHz
TDP 90 W
BUS WIDTH 128 bit
ARCHITECTURE Maxwell 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2015

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
4,157
N/A
geekbench_opencl
18,290
15,662
geekbench_vulkan
54,228
16,734
passmark_directx_10
121
N/A
passmark_directx_11
249
N/A
passmark_directx_12
93
N/A
passmark_directx_9
304
N/A
passmark_g2d
1,177
N/A
passmark_g3d
24,176
N/A
passmark_gpu_compute
13,473
N/A
geekbench_metal
N/A
7,172

Analysis: AMD Radeon RX 7800 XT vs NVIDIA GeForce GTX 950

Where Each One Wins

The recorded data presents a clear, lopsided split between these two GPUs. The AMD Radeon RX 7800 XT wins both of the head-to-head benchmark comparisons, leaving the NVIDIA GeForce GTX 950 without a single victory in the direct matchups. This is not a close contest; the margin in each test is substantial.

The GTX 950's strongest showing comes in the Geekbench OpenCL test, where it scores 15,662 points. This represents its highest compute-oriented result in the available data, and it sits within a narrow band of its own nearest rivals. For context, the GTX 950's average benchmark score is 13,189, placing it at the 53rd percentile among all GPUs. Its nearest rivals include the NVIDIA GeForce GTX 480 at 13,300 (0.8% higher), the AMD Radeon Pro 555X at 13,321 (1% higher), and the AMD FirePro M6100 at 13,354 (1.2% higher). The GTX 950 is essentially level with these cards, showing that its compute performance in this legacy workload is competitive with its direct contemporaries.

The RX 7800 XT, by contrast, dominates the Geekbench Vulkan test with a score of 54,228, which is 69.1% higher than the GTX 950's 16,734 in that same test. The RX 7800 XT's average benchmark score is 11,627, which places it at the 51st percentile, slightly below the GTX 950's percentile ranking despite its far higher peak scores. This discrepancy is explained by its nearest rivals: the NVIDIA GeForce GTX 1660 at 11,680 (0.5% higher), the AMD Radeon RX 6500 XT at 11,842 (1.8% higher), and the AMD Radeon Pro 5500M at 11,528 (0.9% lower). The RX 7800 XT's average is dragged down by its low PassMark DirectX scores, which are not representative of its modern API performance.

The use-case split is therefore straightforward. The GTX 950 belongs to an era of legacy compute workloads, where its OpenCL result is respectable but not remarkable. The RX 7800 XT is the clear choice for any workload that leverages Vulkan, where its score is not merely higher, but categorically in a different performance class.

Architecture Differences

The two cards are separated by nearly a decade of GPU architecture evolution, and the data shows this in every structural metric.

The GTX 950 is built on NVIDIA's Maxwell 2.0 architecture, using the GM206 chip fabricated on a 28 nm process at TSMC. It contains 2,940 million transistors on a die size of 228 mm², yielding a transistor density of 12.9 million per square millimeter. The RX 7800 XT uses AMD's RDNA 3.0 architecture, built around the Navi 32 chip on a 5 nm process, also at TSMC. It packs 28,100 million transistors into a 346 mm² die, achieving a density of 81.2 million per square millimeter. The density difference is more than sixfold, reflecting the process node advancement.

Memory configurations differ dramatically. The GTX 950 has 2 GB of GDDR5 on a 128-bit bus, providing 105.8 GB/s of bandwidth. The RX 7800 XT has 16 GB of GDDR6 on a 256-bit bus, delivering 624.1 GB/s. That is an eightfold increase in capacity and nearly sixfold in bandwidth.

The compute resources scale similarly. The GTX 950 has 768 shading units, 48 texture mapping units, and 32 ROPs. The RX 7800 XT has 3,840 shading units, 240 TMUs, and 96 ROPs. The RX 7800 XT also includes 60 ray tracing cores, a feature entirely absent from the GTX 950, which predates hardware ray tracing. The pixel rate jumps from 38.02 GPixel/s to 233.3 GPixel/s, and the texture rate from 57.02 GTexel/s to 583.2 GTexel/s. FP32 throughput rises from 1.825 TFLOPS to 37.32 TFLOPS, a 20-fold increase. The RX 7800 XT also offers FP16 at the same 37.32 TFLOPS rate, while the GTX 950 has no listed FP16 capability.

Clock speeds tell a nuanced story. The GTX 950 has a base clock of 1024 MHz and a boost clock of 1188 MHz. The RX 7800 XT has a lower base clock of 1295 MHz, but a much higher boost clock of 2430 MHz, with a game clock of 2124 MHz. The memory clock on the GTX 950 is 1653 MHz (6.6 Gbps effective), while the RX 7800 XT runs at 2438 MHz (19.5 Gbps effective).

Power and interface specifications also differ. The GTX 950 has a TDP of 90 W, a single 6-pin power connector, and a suggested PSU of 250 W. The RX 7800 XT has a TDP of 263 W, dual 8-pin connectors, and a suggested PSU of 600 W. The GTX 950 uses PCIe 3.0 x16, while the RX 7800 XT uses PCIe 4.0 x16. Display outputs also differ: the GTX 950 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, while the RX 7800 XT has 1x HDMI 2.1a and 3x DisplayPort 2.1. Both cards are dual-slot, but the RX 7800 XT is longer at 267 mm versus 202 mm.

Head-to-Head Benchmarks

The direct comparison data includes two tests, both of which the RX 7800 XT wins decisively.

In Geekbench OpenCL, the RX 7800 XT scores 18,290 points against the GTX 950's 15,662. The delta is 14.4% in favor of the AMD card. This is a meaningful margin, but not overwhelming. It suggests that in compute-heavy OpenCL workloads, the newer architecture provides a solid advantage, but the older Maxwell design still offers respectable raw throughput. The GTX 950's 15,662 OpenCL score is its best result across all benchmarks, so this test represents its highest point of relative strength.

In Geekbench Vulkan, the gap becomes enormous. The RX 7800 XT scores 54,228 points, while the GTX 950 manages only 16,734. The delta is 69.1% in favor of the AMD card. This is a generational chasm. The Vulkan API leverages modern hardware features such as asynchronous compute and explicit multi-queue execution, which the Maxwell architecture from 2015 cannot fully utilize. The RX 7800 XT's RDNA 3.0 design is built for these modern APIs, and the result shows it clearly.

Looking at the broader benchmark data, the RX 7800 XT also posts results in other tests that the GTX 950 has no equivalent for. Its PassMark G3D score is 24,176, its PassMark GPU Compute score is 13,473, and its 3DMark Steel Nomad DX12 score is 4,157. The GTX 950 has no corresponding scores in these tests, so a direct comparison is not possible. However, the RX 7800 XT's PassMark DirectX scores are notably low: 121 for DirectX 10, 249 for DirectX 11, 93 for DirectX 12, and 304 for DirectX 9. These scores are likely the reason its average benchmark score sits at 11,627, below the GTX 950's 13,189 average. The GTX 950 also has a Geekbench Metal score of 7,172, which the RX 7800 XT does not have.

The wins tally is 0 for the GTX 950 and 2 for the RX 7800 XT. The head-to-head data is unambiguous.

The Verdict

The data does not support any scenario where the GTX 950 is the preferred choice for modern workloads. It loses both head-to-head tests, and the margin in the Vulkan test is 69.1%. The GTX 950's only advantage is its lower power draw and smaller physical footprint, but those are not benchmark performance metrics. Its 53rd percentile ranking versus the RX 7800 XT's 51st percentile is misleading, because the RX 7800 XT's average is pulled down by its anomalously low PassMark DirectX scores. In the two tests that directly compare the cards, the RX 7800 XT is superior in both.

The GTX 950 is an end-of-life product from 2015, and its data reflects that. Its 2 GB memory capacity and 105.8 GB/s bandwidth are insufficient for any modern game or compute workload. Its 1.825 TFLOPS FP32 performance is a fraction of the RX 7800 XT's 37.32 TFLOPS. The GTX 950's nearest rivals are all similarly aged cards, and it sits comfortably among them in performance.

The RX 7800 XT, by contrast, is an active product from 2023. Its 16 GB memory and 624.1 GB/s bandwidth provide ample headroom. Its 60 ray tracing cores enable hardware ray tracing, which the GTX 950 cannot do at all. Its FP16 performance at 37.32 TFLOPS matches its FP32, making it suitable for mixed-precision workloads.

Who should pick which? The RX 7800 XT is the only rational choice for any user running Vulkan-based applications, modern games, or compute tasks that leverage its architectural features. The GTX 950 is a historical artifact, suitable only for legacy systems running older APIs where its OpenCL performance is adequate. Its 14.4% deficit in OpenCL is the closest the two cards come, and even there, the RX 7800 XT wins. The verdict is one-sided: the RX 7800 XT wins decisively on every metric that matters.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 950 has an average benchmark score of 13,189, while the AMD Radeon RX 7800 XT has an average of 11,627. However, the RX 7800 XT's average is reduced by its low PassMark DirectX scores, and it wins both head-to-head tests.

Q: What is the performance gap in the Vulkan benchmark?

A: The AMD Radeon RX 7800 XT scores 54,228 in Geekbench Vulkan, while the NVIDIA GeForce GTX 950 scores 16,734. The RX 7800 XT is 69.1% ahead.

Q: How much memory does each card have?

A: The NVIDIA GeForce GTX 950 has 2 GB of GDDR5 memory on a 128-bit bus, while the AMD Radeon RX 7800 XT has 16 GB of GDDR6 memory on a 256-bit bus.

Q: Does the GTX 950 support hardware ray tracing?

A: No. The GTX 950 has no ray tracing cores listed in its specifications. The AMD Radeon RX 7800 XT includes 60 ray tracing cores.

Q: Which card has a higher transistor count?

A: The AMD Radeon RX 7800 XT has 28,100 million transistors, compared to the NVIDIA GeForce GTX 950's 2,940 million transistors.

Q: What are the nearest rivals for each card?

A: The GTX 950's nearest rivals include the NVIDIA GeForce GTX 480 (0.8% higher average score), AMD Radeon Pro 555X (1% higher), and AMD FirePro M6100 (1.2% higher). The RX 7800 XT's nearest rivals include the NVIDIA GeForce GTX 1660 (0.5% higher), AMD Radeon RX 6500 XT (1.8% higher), and AMD Radeon Pro 5500M (0.9% lower).

DETAILED SPECIFICATIONS

SPECIFICATION
RX 7800 XT
GTX 950
Core Specs
Shading Units
3,840
768 -80.0%
Shaders
3,840
768 -80.0%
TMUs
240
48 -80.0%
ROPs
96
32 -66.7%
Compute Units
60
—
Clocks
Base Clock
1295 MHz
1024 MHz
Boost Clock
2430 MHz
1188 MHz
Game Clock
2124 MHz
—
Shader Clock
2124 MHz
—
Memory Clock
2438 MHz 19.5 Gbps effective
1653 MHz 6.6 Gbps effective
Memory
Memory Size
16 GB
2 GB
VRAM (MB)
16,384
2,048 -87.5%
Memory Type
GDDR6
GDDR5
Memory Bus
256 bit
128 bit
Bandwidth
624.1 GB/s
105.8 GB/s
Cache
L1 Cache
128 KB per Array
48 KB (per SMM)
L2 Cache
4 MB
1024 KB
L3 Cache
64 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
233.3 GPixel/s
38.02 GPixel/s
Texture Rate
583.2 GTexel/s
57.02 GTexel/s
FP32 (TFLOPS)
37.32 TFLOPS
1.825 TFLOPS
FP64 (TFLOPS)
1,166.4 GFLOPS (1:32)
57.02 GFLOPS (1:32)
FP16 (TFLOPS)
37.32 TFLOPS (1:1)
—
AI/RT
RT Cores
60
—
Matrix Cores
120
—
Power
TDP
263 W
90 W
TDP (W)
263
90 -65.8%
Suggested PSU
600 W
250 W
Power Connectors
2x 8-pin
1x 6-pin
Architecture
Architecture
RDNA 3.0
Maxwell 2.0
GPU Name
Navi 32
GM206
Codename
Wheat Nas
—
Generation
Navi III (RX 7000)
GeForce 900
Process Size
5 nm
28 nm
Transistors
28,100 million
2,940 million
Die Size
346 mm²
228 mm²
Foundry
TSMC
TSMC
Density
81.2M / mm²
12.9M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.2
3.0
CUDA
—
5.2
Shader Model
6.9
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm 10.5 inches
202 mm 8 inches
Height
111 mm 4.4 inches
—
Outputs
1x HDMI 2.1a3x DisplayPort 2.1
1x DVI1x HDMI 2.03x DisplayPort 1.2
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Launch Price
499 USD
159 USD
Production
Active
End-of-life
Predecessor
Navi II
GeForce 700
Successor
Navi IV
GeForce 10
View Radeon RX 7800 XT Details View GeForce GTX 950 Details