AMD Radeon RX 580 vs NVIDIA GeForce GTX 1650 SUPER Comparison

Head-to-Head Benchmarks

The head-to-head data shows a clear overall victory for the NVIDIA GeForce GTX 1650 SUPER, which wins 8 of the 10 recorded comparisons. However, the AMD Radeon RX 580 claims the two most dramatic individual results, including the single largest margin in the entire dataset. In the 3DMark Steel Nomad DX12 test, the RX 580 scores 1005 against the GTX 1650 SUPER's 352, a massive 185.5% advantage. This is the defining win for AMD, and it is not a narrow edge but a dominant one. The RX 580 also takes the PassMark G2D test with 769 points versus 749, a smaller but still positive 2.7% lead.

Beyond those two tests, the GTX 1650 SUPER controls the rest of the field. The largest NVIDIA victory comes in PassMark GPU Compute, where it scores 4477 against the RX 580's 3488, a 22.1% gap. The PassMark DirectX 11 result shows a 17.8% lead for NVIDIA (73 vs 60), while the DirectX 9 test shows a 16.2% advantage (148 vs 124). The PassMark G3D score, which is often a strong indicator of overall gaming performance, favors NVIDIA at 10179 versus 8813, a 13.4% edge. In OpenCL, the GTX 1650 SUPER leads by 14.6% (43875 vs 37453), and in Vulkan it leads by 10.6% (50519 vs 45173). The two remaining tests, PassMark DirectX 10 and DirectX 12, are closer: NVIDIA wins DirectX 10 by 8% (50 vs 46) and DirectX 12 by 4.4% (45 vs 43).

The average benchmark score reflects this split. The RX 580 has an average score of 12928, which places it in the 53rd percentile of all GPUs in the database, while the GTX 1650 SUPER averages 11047, sitting in the 50th percentile. Despite the RX 580 having a higher average, the head-to-head results show that NVIDIA wins more individual tests, often by comfortable margins. The RX 580's average is propped up by its enormous 3DMark Steel Nomad score, which is more than double the GTX 1650 SUPER's result in that specific test.

Where Each One Wins

The RX 580's wins are concentrated in two specific areas: the modern DirectX 12 workload represented by 3DMark Steel Nomad, and 2D performance as measured by PassMark G2D. The 185.5% lead in Steel Nomad is not a minor advantage; it indicates that in this particular DX12 scenario, the AMD card operates at a completely different performance tier. The 2.7% lead in G2D is modest but still a win, suggesting slightly stronger 2D rasterization or desktop composition performance.

The GTX 1650 SUPER wins across a broader spread of workloads. Its largest lead, 22.1% in PassMark GPU Compute, points to a significant advantage in compute-oriented tasks. The 17.8% lead in DirectX 11 is notable because that API remains widely used in games. The 16.2% lead in DirectX 9 also matters for older titles. The 13.4% lead in PassMark G3D, which is a general 3D graphics score, reinforces the idea that the NVIDIA card is faster in typical gaming scenarios. The OpenCL lead of 14.6% and the Vulkan lead of 10.6% show that the GTX 1650 SUPER also holds the edge in cross-platform compute and modern graphics APIs, though not by the same margin as in DX11.

The pattern is clear from the data, the RX 580 is the specialist, winning big in one modern test and barely edging out in 2D, while the GTX 1650 SUPER is the generalist, winning the majority of tests with consistent, moderate-to-large margins. For users who prioritize a single DX12 benchmark, the RX 580 is the obvious choice. For everyone else, the GTX 1650 SUPER appears to be the more balanced performer.

The Verdict

Based strictly on the recorded benchmarks, the NVIDIA GeForce GTX 1650 SUPER is the recommended card for most users. It wins 8 out of 10 head-to-head tests, and its victories span DirectX 9, DirectX 10, DirectX 11, DirectX 12, OpenCL, Vulkan, G3D, and GPU Compute. The only areas where the AMD Radeon RX 580 takes the lead are 3DMark Steel Nomad DX12 and PassMark G2D. If the workload is heavily weighted toward that specific 3DMark test, the RX 580's 185.5% advantage is overwhelming, but that single result does not translate into a broader pattern of superiority.

The GTX 1650 SUPER also has the advantage in raw compute performance, with a 22.1% lead in PassMark GPU Compute, which could matter for non-gaming tasks. Its leads in DirectX 11 and DirectX 9 are particularly relevant for a large library of existing games. The RX 580's average benchmark score is higher at 12928 versus 11047, but that average is skewed by the Steel Nomad outlier. The percentile rankings are close, 53rd for the RX 580 and 50th for the GTX 1650 SUPER, but the distribution of wins favors NVIDIA.

For a user whose primary concern is the 3DMark Steel Nomad DX12 result, the RX 580 is the clear winner. For a user who wants consistent performance across a wide range of APIs and compute workloads, the GTX 1650 SUPER is the better pick. The data does not support a general recommendation for the RX 580 beyond its niche strengths.

FAQ

Q: Which GPU wins the most head-to-head benchmarks?

A: The NVIDIA GeForce GTX 1650 SUPER wins 8 of the 10 head-to-head tests, while the AMD Radeon RX 580 wins 2.

Q: What is the largest performance gap between the two cards?

A: In the 3DMark Steel Nomad DX12 test, the AMD Radeon RX 580 scores 1005 versus the GTX 1650 SUPER's 352, a 185.5% advantage for AMD.

Q: How do the two cards compare in OpenCL performance?

A: The NVIDIA GeForce GTX 1650 SUPER leads in OpenCL with a score of 43875, which is 14.6% higher than the RX 580's 37453.

Q: Does the AMD Radeon RX 580 have any wins outside of 3DMark Steel Nomad?

A: Yes, the RX 580 also wins the PassMark G2D test with 769 points, a 2.7% lead over the GTX 1650 SUPER's 749.

Q: Which card has the higher average benchmark score?

A: The AMD Radeon RX 580 has an average benchmark score of 12928, compared to the GTX 1650 SUPER's 11047, but the GTX 1650 SUPER wins more individual tests.

Q: What is the percentile ranking of each card in the database?

A: The RX 580 sits in the 53rd percentile of all GPUs, while the GTX 1650 SUPER is in the 50th percentile.

Architecture Differences

The two cards are built on fundamentally different architectures from different manufacturers. The AMD Radeon RX 580 uses the Polaris 20 chip, which is based on the GCN 4.0 architecture, and belongs to the Polaris (RX 500 generation, released on April 17, 2017. It is manufactured by GlobalFoundries on a 14 nm process node. The die size is 232 mm², and the chip contains 5,700 million transistors, giving a transistor density of 24.6 million per mm².

The NVIDIA GeForce GTX 1650 SUPER, meanwhile, uses the TU116 chip, which is based on the Turing architecture. It belongs to the GeForce 16 generation and the GeForce 10-series, and was released on November 21, 2019, making it significantly newer. NVIDIA uses TSMC as the foundry, with a 12 nm process node. The die size is larger at 284 mm², and the transistor count is higher at 6,600 million, resulting in a slightly lower transistor density of 23.2 million per mm². The RX 580's architecture is GCN 4.0, while the GTX 1650 SUPER is Turing, and neither card has dedicated RT cores or tensor cores.

The GTX 1650 SUPER's Turing architecture supports DirectX 12 with feature level 12_1, and it supports Vulkan 1.4, while the RX 580 supports DirectX 12 with feature level 12_0 and Vulkan 1.3. Both cards support OpenGL 4.6. The GTX 1650 SUPER also has a higher boost clock, 1725 MHz, compared to the RX 580's boost clock of 1340 MHz, and a higher base clock of 1530 MHz versus 1257 MHz.

The RX 580 has a larger die area, more shading units at 2304, and higher texture rate of 193.0 GTexel/s, but the GTX 1650 SUPER achieves a higher pixel rate of 55.20 GPixel/s versus 42.88 GPixel/s. The RX 580's FP32 performance is 6.175 TFLOPS with a 1:1 FP16 ratio, while the GTX 1650 SUPER reaches 4.416 TFLOPS FP32 and 8.832 TFLOPS FP16 with a 2:1 ratio.

The RX 580 has a TDP of 185 W and requires a 450 W PSU, while the GTX 450 W PSU. The RX 580 is a dual-slot card, and the GTX 1650 SUPER is also dual-slot. The RX 580 uses a 1x 8-pin power connector, while the GTX 1650 SUPER uses a 1x 6-pin connector. The RX 580's memory is 8 GB of GDDR5 on a 256-bit bus with 256.0 GB/s bandwidth, while the GTX 1650 SUPER has 4 GB of GDDR6 on a 128-bit bus with 192.0 GB/s bandwidth. The RX 580's memory clock is 2000 MHz (8 Gbps effective), and the GTX 1650 SUPER's memory clock is 1500 MHz (12 Gbps effective). The RX 580 is longer at 241 mm (9.5 inches), while the GTX 1650 SUPER is 229 mm (9 inches) with a height of 111 mm (4.4 inches) and a width of 35 mm (1.4 inches). The RX 580 has display outputs of 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the GTX 1650 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The RX 580's predecessor is Arctic Islands and its successor is Vega, while the GTX 1650 SUPER's predecessor is GeForce 10 and its successor is GeForce 20.

Specification Differences

The most direct specification differences between the two cards are clear from the data. The AMD Radeon RX 580 has 8 GB of GDDR5 memory with a 256-bit bus and 256.0 GB/s bandwidth, while the NVIDIA GeForce GTX 1650 SUPER has 4 GB of GDDR6 memory with a 128-bit bus and 192.0 GB/s bandwidth. The RX 580 has 2304 shading units and 144 TMUs, while the GTX 1650 SUPER has 1280 shading units and 80 TMUs. Both have 32 ROPs.

The RX 580 has a base clock of 1257 MHz and a boost clock of 1340 MHz, while the GTX 1650 SUPER has a base clock of 1530 MHz and a boost clock of 1725 MHz. The RX 580's TDP is 185 W with a suggested PSU of 450 W, while the GTX 1650 SUPER's TDP is 100 W with a suggested PSU of 300 W. The RX 580 uses a 1x 8-pin power connector, and the GTX 1650 SUPER uses a 1x 6-pin connector.

The RX 580 has a transistor count of 5,700 million on a 232 mm² die, while the GTX 1650 SUPER has 6,600 million transistors on a 284 mm² die. The RX 580 is built on a 14 nm process by GlobalFoundries, while the GTX 1650 SUPER is built on a 12 nm process by TSMC. The RX 580 measures 241 mm in length, while the GTX 1650 SUPER measures 229 mm in length with a height of 111 mm and width of 35 mm.

The RX 580 has a pixel rate of 42.88 GPixel/s and a texture rate of 193.0 GTexel/s, while the GTX 1650 SUPER has a pixel rate of 55.20 GPixel/s and a texture rate of 138.0 GTexel/s. The RX 580 achieves 6.175 TFLOPS FP32 and 6.175 TFLOPS FP16, while the GTX 1650 SUPER achieves 4.416 TFLOPS FP32 and 8.832 TFLOPS FP16. The RX 580 supports DirectX 12 (12_0) and Vulkan 1.3, while the GTX 1650 SUPER supports DirectX 12 (12_1) and Vulkan 1.4. Both support OpenGL 4.6. The RX 580 has 1x HDMI 2.0b and 3x DisplayPort 1.4a outputs, while the GTX 1650 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.