AMD Radeon RX 460 vs NVIDIA GeForce RTX 2060 SUPER Comparison

The AMD Radeon RX 460 and NVIDIA GeForce RTX 2060 SUPER represent two vastly different eras of GPU design, separated by three years of architectural evolution and a massive shift in performance class. The data places both at the 62nd percentile among all GPUs, yet their average benchmark scores tell a more nuanced story: the RX 460 averages 18,373 points, while the RTX 2060 SUPER averages 18,093 points. This near-parity in aggregate scores is misleading, as the head-to-head benchmarks reveal a decisive victory for NVIDIA in every shared test, with the older AMD card holding its own only in specific legacy workloads.

Head-to-Head Benchmarks

The only two directly comparable benchmarks in the data are Geekbench OpenCL and Geekbench Vulkan, and in both, the NVIDIA GeForce RTX 2060 SUPER delivers a commanding performance advantage. In Geekbench OpenCL, the RTX 2060 SUPER scores 76,957 points against the RX 460's 17,855 points, a delta of -76.8% from NVIDIA's perspective. This is not a marginal win; it is a four-fold increase in raw compute throughput, reflecting the fundamental gulf in shading units, memory bandwidth, and architecture generation between the two cards.

The Vulkan results follow a similar pattern. The RTX 2060 SUPER posts 77,402 points in Geekbench Vulkan, while the RX 460 manages 20,198 points, yielding a -73.9% delta. Notably, the RX 460 performs relatively better in Vulkan than in OpenCL — its Vulkan score is 13% higher than its OpenCL score — suggesting the GCN 4.0 architecture responds well to modern low-level APIs. However, this improvement still leaves it far behind NVIDIA's Turing implementation, which shows only a 0.6% gap between its own OpenCL and Vulkan scores, indicating more consistent performance across API environments.

The win tally is unambiguous: the RTX 2060 SUPER wins 2 out of 2 head-to-head benchmarks, while the RX 460 secures zero victories. Yet the deltaPct values in the nearestRivals data add context. The RX 460 sits within 1.2% of the NVIDIA GeForce RTX 3060 Mobile and 1% of the AMD Radeon Pro 5700 in average score, while the RTX 2060 SUPER trails the same RTX 3060 Mobile by only 0.4%. This means both cards occupy a similar aggregate performance tier, but the RTX 2060 SUPER achieves this with far more consistency across its broader benchmark suite, which includes DirectX 9 through 12, G2D, and compute tests.

Architecture Differences

The architectural gap between these two GPUs is vast, starting with the manufacturing process. The RX 460 uses a 14 nm node from GlobalFoundries, while the RTX 2060 SUPER is built on TSMC's 12 nm process. Despite the smaller node, the NVIDIA chip is dramatically larger: the TU106 die measures 445 mm² with 10,800 million transistors, compared to the Baffin chip's 123 mm² and 3,000 million transistors. Transistor density is nearly identical — 24.4M per mm² for AMD versus 24.3M per mm² for NVIDIA — meaning the size difference comes entirely from the sheer scale of the Turing design.

The RX 460 is built on GCN 4.0 architecture, part of the Arctic Islands generation, while the RTX 2060 SUPER uses Turing, NVIDIA's first architecture to introduce dedicated ray tracing and tensor cores. The RTX 2060 SUPER packs 34 RT cores and 272 tensor cores, features entirely absent from the RX 460. This is a generational leap in feature support: the NVIDIA card supports DirectX 12 Ultimate (12_2), whereas the AMD card is limited to DirectX 12 (12_0). Both support OpenGL 4.6, but NVIDIA edges ahead with Vulkan 1.4 support versus AMD's Vulkan 1.3.

Core counts tell the same story. The RTX 2060 SUPER has 2,176 shading units, 136 texture mapping units, and 64 ROPs. The RX 460 has 896 shading units, 56 TMUs, and 16 ROPs. This translates to a pixel rate of 105.6 GPixel/s and texture rate of 224.4 GTexel/s for NVIDIA, against 19.20 GPixel/s and 67.20 GTexel/s for AMD. Floating-point performance follows suit: the RTX 2060 SUPER delivers 7.181 TFLOPS FP32 and 14.36 TFLOPS FP16 (2:1 ratio), while the RX 460 manages 2.150 TFLOPS for both FP32 and FP16 (1:1 ratio). The RTX 2060 SUPER also has a 256-bit memory bus with 8 GB of GDDR6 at 448.0 GB/s, versus the RX 460's 128-bit bus, 2 GB of GDDR5, and 112.0 GB/s bandwidth.

Clock speeds and power draw further separate them. The RTX 2060 SUPER boosts to 1650 MHz from a 1470 MHz base, while the RX 460 boosts to 1200 MHz from 1090 MHz. The NVIDIA card consumes 175 W TDP and requires a single 8-pin power connector, whereas the RX 460 draws only 75 W and needs no external power. The suggested PSU rating is 450 W for NVIDIA and 250 W for AMD. Both are dual-slot cards, but the RTX 2060 SUPER is physically larger at 229 mm long, 113 mm tall, and 35 mm wide, compared to the RX 460's 170 mm length.

Where Each One Wins

The RTX 2060 SUPER wins in every scenario that requires raw compute throughput. Its OpenCL score of 76,957 is more than four times the RX 460's 17,855, making it the clear choice for GPU-accelerated compute workloads, rendering, and any application that leverages general-purpose GPGPU processing. The Vulkan advantage of 77,402 versus 20,198 similarly positions it for modern games and applications built on low-level APIs. The presence of RT and tensor cores means the RTX 2060 SUPER can handle ray-traced effects and AI-accelerated features like DLSS, which the RX 460 cannot do at all.

The RX 460's wins are more contextual than absolute. Its 62nd percentile ranking matches the RTX 2060 SUPER, and its average benchmark score of 18,373 is actually 1.5% higher than the RTX 2060 SUPER's 18,093. This suggests the AMD card performs relatively better in aggregate across a mix of workloads, possibly due to its efficiency in lighter tasks. The RX 460 also holds a 1.2% advantage over the RTX 3060 Mobile and a 1% edge over the Radeon Pro 5700, whereas the RTX 2060 SUPER trails both of those same rivals. For users constrained by power delivery — the RX 460 needs no external power connector and only a 250 W PSU — it remains a viable option in systems where the RTX 2060 SUPER's 175 W TDP and 8-pin connector are not feasible.

In legacy DirectX workloads, the RTX 2060 SUPER's PassMark scores show strengths in DirectX 9 (218 points) and DirectX 11 (130 points), but a notable weakness in DirectX 12 (61 points). This is an interesting anomaly, as its 3DMark Steel Nomad DX12 score of 2,011 indicates strong modern API performance. The RX 460 has no equivalent DirectX PassMark data in the pack, so direct comparison is impossible, but the RTX 2060 SUPER's compute score of 6,721 and G2D score of 854 suggest balanced performance across non-gaming tasks.

FAQ

Q: Which GPU has higher raw compute performance in OpenCL?

A: The NVIDIA GeForce RTX 2060 SUPER scores 76,957 in Geekbench OpenCL, which is 76.8% higher than the AMD Radeon RX 460's 17,855 points.

Q: Does the AMD Radeon RX 460 support ray tracing?

A: No. The RX 460 has no RT cores, while the RTX 2060 SUPER includes 34 RT cores and 272 tensor cores for ray tracing and AI acceleration.

Q: What is the memory configuration difference between the two cards?

A: The RTX 2060 SUPER has 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth, while the RX 460 has 2 GB of GDDR5 on a 128-bit bus with 112.0 GB/s bandwidth.

Q: How do their average benchmark scores compare?

A: The RX 460 averages 18,373 points, which is 1.5% higher than the RTX 2060 SUPER's 18,093 points, despite losing both head-to-head tests.

Q: Which card requires more power from the PSU?

A: The RTX 2060 SUPER has a 175 W TDP and suggests a 450 W PSU, while the RX 460 has a 75 W TDP and suggests a 250 W PSU. The NVIDIA card needs a single 8-pin connector; the AMD card needs none.

Q: What is the DirectX feature level difference?

A: The RTX 2060 SUPER supports DirectX 12 Ultimate (12_2), whereas the RX 460 is limited to DirectX 12 (12_0).

The Verdict

The data is unambiguous on performance: the NVIDIA GeForce RTX 2060 SUPER wins every head-to-head benchmark by a massive margin — 76.8% in OpenCL and 73.9% in Vulkan. Its 7.181 TFLOPS FP32 throughput, 448.0 GB/s memory bandwidth, and dedicated RT and tensor cores place it in a completely different performance class than the RX 460. For any application that leverages modern APIs, ray tracing, or AI features, the RTX 2060 SUPER is the only choice between the two.

However, the RX 460 is not without its niche. Its higher average benchmark score of 18,373 versus 18,093, combined with its 75 W power draw, no external power connector, and 250 W PSU requirement, makes it suitable for low-power or legacy systems where the RTX 2060 SUPER's 175 W TDP and 8-pin connector are prohibitive. The RX 460 also matches the RTX 2060 SUPER's 62nd percentile ranking, indicating that in mixed or lighter workloads, the older AMD card can hold its own.

For buyers building a new system or upgrading for modern gaming and compute, the RTX 2060 SUPER is the definitive pick, with a launch MSRP of 399 USD. Its DirectX 12 Ultimate support and Vulkan 1.4 compliance future-proof it for upcoming titles. For users with strict power or physical constraints — the RX 460 is 59 mm shorter and requires no external power — the AMD card remains a functional, if dated, alternative. The RTX 2060 SUPER is the superior hardware by every measurable metric in the head-to-head data, but the RX 460's efficiency and lower system demands keep it relevant for specific use cases.