AMD Radeon RX 5700 XT vs NVIDIA GeForce GTX 1080 Ti Comparison

AMD
RADEON

AMD Radeon RX 5700 XT

CORE STATE Navi 10
VRAM 8 GB
CLOCK SPEED 1905 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 1.0
nm
PROCESS 7 nm
LAUNCH DATE 2019
VS
NVIDIA
GEFORCE

GeForce GTX 1080 Ti

CORE STATE GP102
VRAM 11 GB
CLOCK SPEED 1582 MHz
TDP 250 W
BUS WIDTH 352 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2017

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
2,134
2,231
geekbench_metal
74,647
30,624
geekbench_opencl
9,524
67,929
geekbench_vulkan
68,310
40,511
passmark_directx_10
97
118
passmark_directx_11
116
151
passmark_directx_12
64
66
passmark_directx_9
226
231
passmark_g2d
922
939
passmark_g3d
16,277
18,600
passmark_gpu_compute
7,650
9,632

Analysis: AMD Radeon RX 5700 XT vs NVIDIA GeForce GTX 1080 Ti

The AMD Radeon RX 5700 XT and NVIDIA GeForce GTX 1080 Ti represent two distinct approaches to high-end graphics from different eras, with the former built on a modern 7 nm process and the latter on a mature 16 nm design. Benchmark results reveal a fascinating split: the GTX 1080 Ti wins the majority of tests with a 9-2 victory in the head-to-head, yet the RX 5700 XT dominates in specific API workloads, particularly Metal and Vulkan, by margins that are far larger than any single loss. The data suggests that raw compute throughput and memory bandwidth favor the older NVIDIA card, while architectural efficiency in certain APIs gives the newer AMD card decisive advantages that are easy to overlook when only counting wins.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 5700 XT posts an average benchmark score of 16361, while the NVIDIA GeForce GTX 1080 Ti posts 15548. Despite losing more individual tests, the RX 5700 XT's average is higher by roughly 800 points, indicating that its wins are in higher-magnitude tests.

Q: How does the GTX 1080 Ti perform in the 3DMark Steel Nomad DX12 test?

A: The GTX 1080 Ti scores 2231 in 3DMark Steel Nomad DX12, which is 4.3% ahead of the RX 5700 XT's 2134. This is a narrow margin, showing that the two cards are closely matched in this modern DX12 workload.

Q: What is the most significant single benchmark win for the RX 5700 XT?

A: The RX 5700 XT's biggest win is in Geekbench Metal, where it scores 74647 versus the GTX 1080 Ti's 30624, a 143.8% lead. This is by far the largest delta in the entire comparison.

Q: In which benchmark does the GTX 1080 Ti achieve its largest victory?

A: The GTX 1080 Ti's largest win is in Geekbench OpenCL, scoring 67929 against the RX 5700 XT's 9524, an 86% advantage. This is a dramatic reversal of the Metal result.

Q: What are the percentile rankings of these two GPUs?

A: The RX 5700 XT sits at the 59th percentile against all GPUs, while the GTX 1080 Ti sits at the 58th percentile. The RX 5700 XT holds a slight edge in overall standing despite the older card's higher peak scores in many tests.

Q: How do the two cards compare in PassMark G3D, a general gaming metric?

A: The GTX 1080 Ti scores 18600 in PassMark G3D, which is 12.5% higher than the RX 5700 XT's 16277. This is a substantial lead for the NVIDIA card in a widely-used gaming benchmark.

Where Each One Wins

The GTX 1080 Ti is the clear winner in traditional and compute-oriented workloads. It takes the PassMark DirectX 10, 11, 12, and 9 tests, along with G2D, G3D, and GPU Compute. The margins in DirectX 11 and GPU Compute are particularly notable, at 23.2% and 20.6% respectively. This points to a card that excels in legacy API scenarios and raw computational tasks, which aligns with its higher FP32 throughput of 11.34 TFLOPS and larger 11 GB memory buffer with 484.4 GB/s bandwidth.

The RX 5700 XT wins exclusively in the Geekbench Metal and Vulkan tests. The Metal victory is staggering at 143.8%, and the Vulkan win is also commanding at 68.6%. These are modern, low-level APIs where the RDNA 1.0 architecture appears to have a significant efficiency advantage. The RX 5700 XT also has a higher transistor density (41.0M per mm² versus 25.1M) and a smaller die (251 mm² versus 471 mm²), which suggests that its design is more optimized for per-transistor performance in certain workloads.

The split is stark: the older NVIDIA card dominates across a broad spectrum of tests, while the AMD card shows it can decisively outperform in specific API environments. The data implies that the GTX 1080 Ti is a more versatile performer for general use, but the RX 5700 XT has specialized strengths that could be decisive for users working within Metal or Vulkan ecosystems.

Architecture Differences

The fundamental architectural gap is process node and design philosophy. The RX 5700 XT uses a 7 nm TSMC process with 10,300 million transistors on a 251 mm² die, yielding a density of 41.0M transistors per mm². The GTX 1080 Ti uses a 16 nm TSMC process with 11,800 million transistors on a much larger 471 mm² die, giving a density of only 25.1M per mm². The RX 5700 XT's RDNA 1.0 architecture is newer and more compact, while the GTX 1080 Ti's Pascal architecture is older and physically larger.

The memory subsystems differ fundamentally: the RX 5700 XT uses 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth, while the GTX 1080 Ti uses 11 GB of GDDR5X on a 352-bit bus with 484.4 GB/s bandwidth. The NVIDIA card has more memory and higher bandwidth, but the AMD card's GDDR6 runs at a higher effective speed of 14 Gbps versus 11 Gbps. The RX 5700 XT also supports PCIe 4.0 x16, while the GTX 1080 Ti is limited to PCIe 3.0 x16.

Compute capabilities show a clear divergence. The GTX 1080 Ti has 3584 shading units, 224 TMUs, and 88 ROPs, while the RX 5700 XT has 2560 shading units, 160 TMUs, and 64 ROPs. The NVIDIA card has more of everything, but the RX 5700 XT achieves comparable FP16 performance (19.51 TFLOPS versus 177.2 GFLOPS) due to its 2:1 FP16 ratio, whereas the GTX 1080 Ti has a 1:64 ratio. The RX 5700 XT's FP16 capability is a major architectural difference that explains its compute versatility.

Specification Differences

The two cards differ in nearly every core specification. The RX 5700 XT has a base clock of 1605 MHz and a boost of 1905 MHz, while the GTX 1080 Ti has a base of 1481 MHz and a boost of 1582 MHz. The AMD card runs significantly faster, but the NVIDIA card compensates with more execution units. The RX 5700 XT's game clock is 1755 MHz, a metric the GTX 1080 Ti does not list.

Memory is another key differentiator: the RX 5700 XT has 8 GB of GDDR6, while the GTX 1080 Ti has 11 GB of GDDR5X. The bus widths are 256-bit versus 352-bit, and bandwidth is 448.0 GB/s versus 484.4 GB/s. The TDP also differs at 225 W for AMD versus 250 W for NVIDIA, with a suggested PSU of 550 W versus 600 W.

Physical dimensions are close but not identical: the RX 5700 XT is 272 mm long, 111 mm tall, and 36 mm wide, while the GTX 1080 Ti is 267 mm long, 112 mm tall, and 40 mm wide. Both are dual-slot cards with 1x 6-pin and 1x 8-pin power connectors. The RX 5700 XT's FP32 throughput is 9.754 TFLOPS, while the GTX 1080 Ti's is 11.34 TFLOPS, and pixel rates are 121.9 GPixel/s versus 139.2 GPixel/s. The launch MSRP for the RX 5700 XT is 399 USD, and for the GTX 1080 Ti it is 699 USD.

Head-to-Head Benchmarks

The 3DMark Steel Nomad DX12 test shows a close contest: the GTX 1080 Ti wins with 2231 against 2134, a 4.3% lead. This is the smallest single-digit margin in the entire comparison, suggesting that in this modern DX12 workload, the two cards are nearly equivalent. The PassMark DirectX 12 result is even tighter at 3% (66 versus 64), reinforcing that DX12 performance is a wash.

The Geekbench results are where the data becomes dramatic. In Metal, the RX 5700 XT's 74647 crushes the GTX 1080 Ti's 30624, a 143.8% advantage. In Vulkan, the RX 5700 XT again wins decisively with 68310 against 40511, a 68.6% lead. However, in OpenCL, the tables turn completely: the GTX 1080 Ti scores 67929 versus 9524, an 86% margin. This suggests that the AMD card is highly optimized for Apple's Metal API and Vulkan, while NVIDIA's card dominates the more general OpenCL compute standard.

The PassMark suite heavily favors NVIDIA. The DirectX 11 test shows a 23.2% lead (151 versus 116), and DirectX 10 shows a 17.8% lead (118 versus 97). DirectX 9 is close at 2.2% (231 versus 226), and G2D is nearly identical at 1.8% (939 versus 922). The G3D result gives NVIDIA a 12.5% win (18600 versus 16277), and GPU Compute gives a 20.6% win (9632 versus 7650). The pattern is consistent: in every PassMark test except the closest DX12 and DX9 margins, the GTX 1080 Ti is ahead.

The Verdict

From the data, the NVIDIA GeForce GTX 1080 Ti is the better overall performer. It wins 9 of 11 head-to-head benchmarks, with leads ranging from 1.8% to 86%, and it holds a decisive advantage in PassMark G3D, which is a common proxy for gaming performance. Its higher FP32 throughput, larger memory capacity, and greater bandwidth are backed by benchmark results that show consistent superiority in DirectX and compute workloads. Users who prioritize broad compatibility and raw performance across many different applications should choose the GTX 1080 Ti.

The AMD Radeon RX 5700 XT is the specialist. Its wins in Metal and Vulkan are so large that they cannot be ignored, and its higher average benchmark score of 16361 indicates that these tests carry significant weight. For users whose workloads are dominated by Vulkan or Metal—such as those in Linux environments or Apple ecosystems—the RX 5700 XT is clearly the superior card. Its modern 7 nm architecture also brings higher clock speeds and better transistor density, which may have implications for longevity that are not captured in these specific benchmarks.

The verdict is nuanced: the GTX 1080 Ti is the safer, more powerful choice for general use, but the RX 5700 XT is the right pick for API-specific workloads where it demonstrates a massive edge. The 59th percentile ranking of the RX 5700 XT versus 58th for the GTX 1080 Ti suggests that, in aggregate, the AMD card is slightly better positioned, but this is driven by its extraordinary Metal and Vulkan results rather than broad superiority. Ultimately, the data tells a story of two cards with complementary strengths, and the correct choice depends entirely on the user's software stack.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 5700 XT
GTX 1080 Ti
Core Specs
Shading Units
2,560
3,584 +40.0%
Shaders
2,560
3,584 +40.0%
TMUs
160
224 +40.0%
ROPs
64
88 +37.5%
Compute Units
40
—
SM Count
—
28
Clocks
Base Clock
1605 MHz
1481 MHz
Boost Clock
1905 MHz
1582 MHz
Game Clock
1755 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
1376 MHz 11 Gbps effective
Memory
Memory Size
8 GB
11 GB
VRAM (MB)
8,192
11,264 +37.5%
Memory Type
GDDR6
GDDR5X
Memory Bus
256 bit
352 bit
Bandwidth
448.0 GB/s
484.4 GB/s
Cache
L1 Cache
—
48 KB (per SM)
L2 Cache
4 MB
2.75 MB
Performance
Pixel Rate
121.9 GPixel/s
139.2 GPixel/s
Texture Rate
304.8 GTexel/s
354.4 GTexel/s
FP32 (TFLOPS)
9.754 TFLOPS
11.34 TFLOPS
FP64 (TFLOPS)
609.6 GFLOPS (1:16)
354.4 GFLOPS (1:32)
FP16 (TFLOPS)
19.51 TFLOPS (2:1)
177.2 GFLOPS (1:64)
Power
TDP
225 W
250 W
TDP (W)
225
250 +11.1%
Suggested PSU
550 W
600 W
Power Connectors
1x 6-pin + 1x 8-pin
1x 6-pin + 1x 8-pin
Architecture
Architecture
RDNA 1.0
Pascal
GPU Name
Navi 10
GP102
Generation
Navi (RX 5000)
GeForce 10
Process Size
7 nm
16 nm
Transistors
10,300 million
11,800 million
Die Size
251 mm²
471 mm²
Foundry
TSMC
TSMC
Density
41.0M / mm²
25.1M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
272 mm 10.7 inches
267 mm 10.5 inches
Height
111 mm 4.4 inches
112 mm 4.4 inches
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
1x HDMI 2.03x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x16
PCIe 3.0 x16
Other
Launch Price
399 USD
699 USD
Production
End-of-life
End-of-life
Predecessor
Vega
GeForce 900
Successor
Navi II
GeForce 20
View Radeon RX 5700 XT Details View GeForce GTX 1080 Ti Details