AMD Radeon RX Vega 11 vs NVIDIA GeForce GTX 1660 SUPER Comparison
AMD Radeon RX Vega 11
GeForce GTX 1660 SUPER
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX Vega 11 vs NVIDIA GeForce GTX 1660 SUPER
AMD Radeon RX Vega 11 and NVIDIA GeForce GTX 1660 SUPER occupy different tiers entirely, and the benchmark data reflects a decisive gulf in raw performance. The GTX 1660 SUPER dominates in every recorded head-to-head test, while the RX Vega 11 trails by margins that define its role as an integrated graphics solution rather than a discrete competitor. This analysis breaks down the recorded scores, architectural implications, and the specific workloads where each part can claim relevance.
Head-to-Head Benchmarks
The database records two direct comparisons between the AMD Radeon RX Vega 11 and the NVIDIA GeForce GTX 1660 SUPER, and both results are lopsided. In the Geekbench OpenCL test, the RX Vega 11 scored 12525, while the GTX 1660 SUPER delivered 52490. That is a delta of -76.1%, meaning the NVIDIA card is roughly four times faster in this compute-oriented workload. The Vulkan test tells the same story: the RX Vega 11 scored 13543, the GTX 1660 SUPER scored 57102, for a delta of -76.3%. These are not close calls; they are categorical separations.
Looking at the broader benchmark averages, the RX Vega 11 posts an average score of 14385 across its three recorded tests, while the GTX 1660 SUPER averages 12986 across its ten recorded tests. However, this comparison is misleading because the test suites differ. The RX Vega 11's scores come exclusively from Geekbench API tests, whereas the GTX 1660 SUPER includes PassMark DirectX and 3DMark workloads. What matters is the head-to-head data: in the only tests where both parts appear, the GTX 1660 SUPER holds a commanding lead.
The percentile rankings show both parts sitting in the middle of the database, with the RX Vega 11 at the 56th percentile and the GTX 1660 SUPER at the 53rd percentile. This proximity is surprising given the raw score gap, but it reflects the broader distribution of GPU performance where many integrated and older discrete parts cluster together. The RX Vega 11's nearest rivals include the NVIDIA GeForce GTX TITAN with an average score of 14373 and a delta of 0.1%, the GTX 965M at 14404 with a delta of -0.1%, and the Intel Iris Xe MAX Graphics at 14315 with a delta of 0.5%. The GTX 1660 SUPER's neighbors include the RTX 3050 Ti Mobile at 12940 with a delta of 0.4%, the RX 580 at 12928 with a delta of 0.4%, and the Tesla M2090 at 13075 with a delta of -0.7%.
Where Each One Wins
The RX Vega 11 wins in exactly zero recorded head-to-head tests. Its strongest individual score is 13543 in Geekbench Vulkan, which is its best API result but still far behind the GTX 1660 SUPER's 57102 in the same test. The integrated part does show some capability in OpenCL with 12525, but again the discrete card more than quadruples that output.
The GTX 1660 SUPER claims both head-to-head wins, and its recorded data reveals where it excels. In PassMark DirectX 9, it scores 189, which is its highest DirectX result. DirectX 11 yields 104, DirectX 10 yields 65, and DirectX 12 yields 50. The PassMark G3D score of 12699 indicates strong general 3D rendering, while PassMark G2D at 805 shows modest 2D performance. The GPU compute score of 5076 further confirms its compute capability. The 3DMark Steel Nomad DX12 score of 1278 provides a modern DirectX 12 workload result.
For use cases, the GTX 1660 SUPER is the clear choice for any application that stresses graphics throughput, whether that is gaming, 3D rendering, or GPU-accelerated compute. The RX Vega 11, with its system-shared memory and integrated design, is suited only for basic desktop acceleration or legacy workloads where a discrete card is not available. The data offers no scenario where the integrated part outperforms the discrete card in a shared benchmark.
Architecture Differences
The two parts come from fundamentally different design philosophies. The AMD Radeon RX Vega 11 uses the GCN 5.0 architecture on the Picasso chip, built on a 12 nm process at GlobalFoundries. It contains 4,940 million transistors on a 210 mm² die, with a transistor density of 23.5M per mm². The NVIDIA GeForce GTX 1660 SUPER uses the Turing architecture on the TU116 chip, also on a 12 nm process but at TSMC. It packs 6,600 million transistors across a 284 mm² die, with a density of 23.2M per mm². The die size and transistor count differences are substantial, with the NVIDIA chip holding 34% more transistors on a 35% larger die.
Clock speeds diverge sharply. The RX Vega 11 runs at a base clock of 300 MHz with a boost of 1400 MHz, while the GTX 1660 SUPER runs at a base of 1530 MHz and boosts to 1785 MHz. The NVIDIA card's base clock is higher than the AMD part's boost clock, which explains much of the performance gap.
The memory subsystem is where the architectures separate completely. The RX Vega 11 uses system-shared memory, meaning its bandwidth is system dependent and its memory size is whatever the host system allocates. The GTX 1660 SUPER has 6 GB of dedicated GDDR6 memory on a 192-bit bus, delivering 336.0 GB/s of bandwidth at an effective 14 Gbps. This dedicated high-bandwidth memory is a primary reason for the GTX 1660 SUPER's dominance in bandwidth-sensitive workloads.
Compute resources also differ by large factors. The RX Vega 11 has 704 shading units, 44 texture mapping units, and 8 raster output units. The GTX 1660 SUPER has 1408 shading units, 88 TMUs, and 48 ROPs. That is exactly double the shading units and TMUs, and six times the ROPs. Pixel rate for the RX Vega 11 is 11.20 GPixel/s versus 85.68 GPixel/s for the GTX 1660 SUPER. Texture rate is 61.60 GTexel/s versus 157.1 GTexel/s. FP32 throughput is 1.971 TFLOPS versus 5.027 TFLOPS. FP16 is 3.942 TFLOPS versus 10.05 TFLOPS, both using a 2:1 ratio.
Power and physical design differ as expected. The RX Vega 11 is an integrated graphics processor with a 15 W TDP, no power connectors, and no dedicated slot width. The GTX 1660 SUPER is a dual-slot card with a 125 W TDP, one 8-pin power connector, a suggested PSU of 300 W, and dimensions of 229 mm length, 111 mm height, and 35 mm width. The RX Vega 11 uses the IGP bus interface, while the GTX 1660 SUPER uses PCIe 3.0 x16.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The AMD Radeon RX Vega 11 has an average benchmark score of 14385, while the NVIDIA GeForce GTX 1660 SUPER has an average of 12986. However, these averages come from different test sets, and the direct head-to-head comparisons show the GTX 1660 SUPER winning by over 76%.
Q: What is the memory configuration difference?
A: The RX Vega 11 uses system-shared memory with bandwidth described as system dependent, while the GTX 1660 SUPER has 6 GB of dedicated GDDR6 memory on a 192-bit bus with 336.0 GB/s bandwidth.
Q: How do the compute resources compare?
A: The GTX 1660 SUPER has 1408 shading units, 88 TMUs, and 48 ROPs, while the RX Vega 11 has 704 shading units, 44 TMUs, and 8 ROPs. The GTX 1660 SUPER delivers 5.027 TFLOPS FP32 versus 1.971 TFLOPS for the RX Vega 11.
Q: Which GPU has the higher boost clock?
A: The GTX 1660 SUPER boosts to 1785 MHz, while the RX Vega 11 boosts to 1400 MHz. The GTX 1660 SUPER's base clock of 1530 MHz is also higher than the RX Vega 11's boost clock.
Q: Are both GPUs end-of-life?
A: Yes, both the AMD Radeon RX Vega 11 and the NVIDIA GeForce GTX 1660 SUPER have a production status of end-of-life.
Q: What are the power requirements?
A: The RX Vega 11 has a 15 W TDP with no power connectors, while the GTX 1660 SUPER has a 125 W TDP with one 8-pin connector and a suggested PSU of 300 W.
The Verdict
The data is unambiguous: the NVIDIA GeForce GTX 1660 SUPER is the superior graphics processor for any performance-relevant task. It wins both recorded head-to-head benchmarks by margins exceeding 76%, it has more than double the shading units and TMUs, six times the ROPs, and it uses dedicated GDDR6 memory with 336.0 GB/s bandwidth versus system-shared memory. Its FP32 output of 5.027 TFLOPS is more than 2.5 times the RX Vega 11's 1.971 TFLOPS. The GTX 1660 SUPER also has higher base and boost clocks, a larger die with more transistors, and a higher pixel rate of 85.68 GPixel/s versus 11.20 GPixel/s.
The AMD Radeon RX Vega 11 should be considered only in the context of an integrated graphics solution where no discrete card is present. Its 15 W TDP and lack of power connectors make it suitable for low-power systems, and its system-shared memory means it relies entirely on the host platform. Its best recorded score of 13543 in Geekbench Vulkan is respectable for an IGP, but it does not approach the GTX 1660 SUPER's 57102 in the same test.
For anyone choosing between these two parts for a build, the GTX 1660 SUPER is the only option that provides meaningful 3D performance, modern API support including Vulkan 1.4, and sufficient bandwidth for demanding workloads. The RX Vega 11 exists in a different category, and the benchmark data confirms that no workload in the shared test suite gives it an edge.
Specification Differences
The two GPUs differ in nearly every measurable specification. The RX Vega 11 uses GCN 5.0 architecture on the Picasso chip, while the GTX 1660 SUPER uses Turing on the TU116 chip. The RX Vega 11 is built by GlobalFoundries, the GTX 1660 SUPER by TSMC. Transistors number 4,940 million versus 6,600 million, with die sizes of 210 mm² versus 284 mm². Clock speeds differ: 300 MHz base and 1400 MHz boost for the AMD part, 1530 MHz base and 1785 MHz boost for the NVIDIA part.
Memory is the largest differentiator: the RX Vega 11 has system-shared memory with system-dependent bandwidth, while the GTX 1660 SUPER has 6 GB GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. Shading units are 704 versus 1408, TMUs are 44 versus 88, and ROPs are 8 versus 48. Pixel rates are 11.20 GPixel/s versus 85.68 GPixel/s, texture rates are 61.60 GTexel/s versus 157.1 GTexel/s, and FP32 performance is 1.971 TFLOPS versus 5.027 TFLOPS.
TDP is 15 W for the RX Vega 11 versus 125 W for the GTX 1660 SUPER. The AMD part is an IGP with no slot width or power connectors, while the NVIDIA part is dual-slot with one 8-pin connector and a suggested 300 W PSU. The bus interface is IGP versus PCIe 3.0 x16. Display outputs are motherboard dependent for the RX Vega 11, while the GTX 1660 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. API support is similar with DirectX 12 (12_1) and OpenGL 4.6 on both, but Vulkan support differs: 1.3 for the AMD part and 1.4 for the NVIDIA part. Release dates differ by roughly three months, with the RX Vega 11 launching on 2019-07-06 and the GTX 1660 SUPER on 2019-10-28. The GTX 1660 SUPER has a launch MSRP of 229 USD.