AMD Radeon RX 5700 vs NVIDIA GeForce RTX 2080 SUPER Comparison

Head-to-Head Benchmarks

The benchmark data shows a decisive sweep for the NVIDIA GeForce RTX 2080 SUPER, winning all 10 recorded head-to-head tests. The largest margin appears in Vulkan compute, where the RTX 2080 SUPER scores 111,284 against the RX 5700's 64,166, a 73.4% advantage. This is not a close contest in any single workload; the smallest gap is in the modern DirectX 12 Steel Nomad test, where the RTX 2080 SUPER scores 1,882 versus 1,862, a mere 1.1% edge.

The biggest practical wins come in legacy and compute-oriented tests. In Passmark DirectX 11, the RTX 2080 SUPER scores 165 versus 101 for the RX 5700, a 63.4% lead. DirectX 10 shows a 60.9% gap (140 vs 87). For general 3D performance, Passmark G3D puts the RTX 2080 SUPER at 19,490 against 14,314, a 36.2% difference. Compute workloads also favor NVIDIA heavily: Passmark GPU Compute shows 8,290 versus 6,517, a 27.2% lead, and OpenCL shows 99,226 versus 69,603, a 42.6% margin.

The RX 5700 does not win a single recorded test. Its closest relative performance is in the newest DirectX 12 workload, where it trails by only 1.1%, and in DirectX 9, where the delta is 8.6% (227 vs 209). Even in 2D tests, the RTX 2080 SUPER leads, scoring 920 versus 877 in Passmark G2D, a 4.9% edge. The average benchmark score reinforces this: the RTX 2080 SUPER sits at 24,170, while the RX 5700 is at 22,170. The RTX 2080 SUPER ranks in the 69th percentile of all GPUs, versus the 67th percentile for the RX 5700.

Looking at the nearest rivals in the database, the RTX 2080 SUPER's average score is essentially tied with the GTX 780 Ti (24,236, delta -0.3%) and GTX 1630 (24,277, delta -0.4%), while it edges out the RX 6800S (24,063, delta 0.4%) and trails the RX 6600 XT (24,442, delta -1.1%). The RX 5700's average score is nearly identical to the RX 6700S (22,154, delta 0.1%), slightly ahead of the GTX 1060 6 GB (21,856, delta 1.4%), and behind the RTX 5060 Mobile (22,435, delta -1.2%) and RX 7700 XT (22,549, delta -1.7%).

FAQ

Q: Which card has the higher average benchmark score?

A: The NVIDIA GeForce RTX 2080 SUPER averages 24,170, which is 2,000 points higher than the AMD Radeon RX 5700's 22,170.

Q: Is the RTX 2080 SUPER always faster in every test?

A: Yes, in the recorded head-to-head data, the RTX 2080 SUPER wins all 10 tests. The smallest margin is 1.1% in 3DMark Steel Nomad, and the largest is 73.4% in Geekbench Vulkan.

Q: How big is the difference in DirectX 12 performance?

A: In the modern 3DMark Steel Nomad DX12 test, the RTX 2080 SUPER scores 1,882 versus 1,862, a 1.1% lead. In Passmark DirectX 12, the gap is larger: 75 versus 54, a 38.9% advantage for NVIDIA.

Q: Which card has better compute performance for non-gaming workloads?

A: The RTX 2080 SUPER is substantially ahead. In OpenCL it scores 99,226 versus 69,603 (42.6% faster), and in Vulkan it scores 111,284 versus 64,166 (73.4% faster). Passmark GPU Compute also favors NVIDIA at 8,290 versus 6,517 (27.2% faster).

Q: Does the RX 5700 have any benchmark where it beats the RTX 2080 SUPER?

A: No. The recorded data shows zero wins for the RX 5700 across all 10 head-to-head tests.

Q: How do these cards compare to their nearest rivals in the database?

A: The RTX 2080 SUPER is within 1.1% of the GTX 780 Ti, GTX 1630, RX 6800S, and RX 6600 XT. The RX 5700 is within 1.7% of the RX 6700S, RTX 5060 Mobile, GTX 1060 6 GB, and RX 7700 XT.

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 2080 SUPER is the faster GPU in every recorded benchmark. If the priority is raw performance, especially in compute or DirectX 11/12 workloads, the RTX 2080 SUPER is the clear choice. It delivers a 27% to 73% advantage in the most demanding compute tests and a 36% lead in general 3D performance.

The AMD Radeon RX 5700 is the card for someone who prioritizes efficiency and platform features over raw speed. It draws 180 W versus 250 W for the RTX 2080 SUPER, and it uses a 7 nm process versus 12 nm. It also supports PCIe 4.0 x16, while the RTX 2080 SUPER is limited to PCIe 3.0 x16. The RX 5700's average score is still respectable, ranking in the 67th percentile of all GPUs, but it is 9% slower on average and loses every head-to-head test.

The RTX 2080 SUPER also brings hardware features the RX 5700 lacks: 48 ray tracing cores, 384 tensor cores, and DirectX 12 Ultimate (12_2) support versus the RX 5700's DirectX 12 (12_1). For a user who wants ray tracing or DLSS-capable tensor core acceleration, the RTX 2080 SUPER is the only option here. The RX 5700 has no ray tracing cores and no tensor cores.

In terms of overall standing, the RTX 2080 SUPER's 69th percentile ranking places it just above the RX 5700's 67th percentile. The average score difference of 2,000 points is consistent across the board, with the RTX 2080 SUPER leading in every single recorded metric. The verdict is simple: pick the RTX 2080 SUPER for performance, pick the RX 5700 for lower power draw and a smaller die.

Specification Differences

The two cards share some basics: both have 8 GB of GDDR6 memory on a 256-bit bus, both are dual-slot, both use 1x 6-pin + 1x 8-pin power connectors, and both output 3x DisplayPort 1.4a and 1x HDMI. Beyond that, they diverge significantly.

The RTX 2080 SUPER has 3,072 shading units, 192 texture mapping units, and 64 ROPs. The RX 5700 has 2,304 shading units, 144 TMUs, and also 64 ROPs. This explains the RTX 2080 SUPER's higher texture rate of 348.5 GTexel/s versus 248.4 GTexel/s, and pixel rate of 116.2 GPixel/s versus 110.4 GPixel/s. The FP32 compute is 11.15 TFLOPS for NVIDIA versus 7.949 TFLOPS for AMD.

Memory bandwidth favors NVIDIA: 495.9 GB/s versus 448.0 GB/s. The RTX 2080 SUPER runs memory at 1937 MHz (15.5 Gbps effective), while the RX 5700 runs at 1750 MHz (14 Gbps effective). Clock speeds are also higher on the RTX 2080 SUPER: base 1650 MHz versus 1465 MHz, boost 1815 MHz versus 1725 MHz. The RX 5700 has a game clock of 1625 MHz, which the RTX 2080 SUPER does not list.

Power and size differ. The RTX 2080 SUPER has a TDP of 250 W and suggests a 600 W PSU. The RX 5700 has a TDP of 180 W and suggests a 450 W PSU. Physically, the RTX 2080 SUPER is 267 mm long, 116 mm tall, and 35 mm wide. The RX 5700 is 268 mm long, 111 mm tall, and 36 mm wide. The RTX 2080 SUPER also has a USB Type-C output, which the RX 5700 lacks.

Architecture Differences

The RTX 2080 SUPER is built on NVIDIA's Turing architecture using the TU104 chip on a 12 nm process at TSMC. It packs 13,600 million transistors on a 545 mm² die, giving a density of 25.0M transistors per mm². The RX 5700 uses AMD's RDNA 1.0 architecture with the Navi 10 chip on a 7 nm process, also at TSMC. It has 10,300 million transistors on a 251 mm² die, yielding a much higher density of 41.0M per mm².

The most important architectural differences are the dedicated hardware blocks. The RTX 2080 SUPER includes 48 ray tracing cores and 384 tensor cores, which enable hardware-accelerated ray tracing and AI-based features like DLSS. The RX 5700 has neither; those fields are null in the data. This is a fundamental capability gap, not just a performance difference.

API support also differs. The RTX 2080 SUPER supports DirectX 12 Ultimate (12_2), while the RX 5700 only supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The RTX 2080 SUPER's FP16 performance is 22.30 TFLOPS (2:1), and the RX 5700's is 15.90 TFLOPS (2:1), but the RTX 2080 SUPER's tensor cores are what actually accelerate FP16-style workloads.

Bus interface differs: the RTX 2080 SUPER uses PCIe 3.0 x16, while the RX 5700 uses PCIe 4.0 x16. The RX 5700's smaller die and newer process node give it a transistor density advantage of 41.0M per mm² versus 25.0M per mm², but the RTX 2080 SUPER compensates with more silicon area and more execution resources.

Where Each One Wins

The RTX 2080 SUPER wins everywhere in the recorded benchmarks. Its biggest advantages are in compute-heavy and legacy API workloads: Vulkan (73.4% faster), DirectX 11 (63.4%), DirectX 10 (60.9%), and OpenCL (42.6%). For users running older games, emulators, or compute applications that rely on these APIs, the RTX 2080 SUPER is dramatically better.

The RX 5700's only theoretical wins are in efficiency and platform features. It draws 70 W less (180 W versus 250 W), uses a smaller die (251 mm² versus 545 mm²), and supports PCIe 4.0. In the newest DirectX 12 test, the RTX 2080 SUPER's lead shrinks to just 1.1%, suggesting that the RX 5700 competes more closely in modern, optimized workloads. But even in DirectX 12, the RTX 2080 SUPER still wins.

For a system builder focused on raw frame rates in DirectX 11 games or compute tasks, the RTX 2080 SUPER is the pick. For a builder who wants a lower-power card with a smaller physical footprint and PCIe 4.0 support, the RX 5700 is the reasonable alternative, as long as they accept a 9% lower average score and zero benchmark wins. The RTX 2080 SUPER also offers ray tracing and tensor cores, making it the only choice for those features. The RX 5700's 67th percentile ranking is respectable, but the RTX 2080 SUPER's 69th percentile and its sweep of all 10 tests make the performance hierarchy clear.