AMD Radeon Vega 11 vs NVIDIA GeForce GTX 1660 SUPER Comparison

Head-to-Head Benchmarks

The recorded data contains two direct benchmark comparisons between the AMD Radeon Vega 11 and the NVIDIA GeForce GTX 1660 SUPER, and both are decisive victories for the NVIDIA card. In Geekbench OpenCL, the GTX 1660 SUPER scores 52,490 against the Vega 11's 13,392, a margin of 74.5 percent. The Vulkan result is even more lopsided: the NVIDIA card posts 57,102 while the AMD integrated solution manages 12,273, a 78.5 percent gap. These are not close contests by any measurement.

The average benchmark scores tell the same story, though the gap is compressed by the different test suites available for each product. The Vega 11 has an average score of 14,352 across its recorded benchmarks, which places it in the 56th percentile of all GPUs in the database. The GTX 1660 SUPER averages 12,986, which is the 53rd percentile. The apparent inconsistency between the head-to-head deltas and the average scores reflects the fact that the two products share only two benchmark entries in the database; the NVIDIA card's average is dragged down by its Passmark results, which are not recorded for the AMD part.

Looking at the nearest rivals for each card provides additional context. The Vega 11 sits within a tight cluster: the NVIDIA GeForce GTX TITAN averages 14,373, a 0.1 percent lead over the AMD part. The AMD Radeon RX Vega 11 averages 14,385, a 0.2 percent lead. The Intel Iris Xe MAX Graphics trails by 0.3 percent at 14,315, and the NVIDIA GeForce GTX 965M leads by 0.4 percent at 14,404. The Vega 11 is effectively at parity with all four of these products, suggesting its position is determined more by the specific workload than by any inherent performance ceiling.

The GTX 1660 SUPER's nearest rivals show a similar pattern of tight grouping. The NVIDIA GeForce RTX 3050 Ti Mobile averages 12,940, a 0.4 percent lead over the GTX 1660 SUPER. The AMD Radeon RX 580 averages 12,928, also a 0.4 percent lead. The NVIDIA Tesla M2090 averages 13,075, which is 0.7 percent ahead. The AMD Radeon 740M averages 12,870, a 0.9 percent deficit. The GTX 1660 SUPER is therefore bracketed by a set of discrete and integrated GPUs that all land within a narrow band of average scores.

The decisive factor in the head-to-head tests is the sheer scale of the compute advantage. In OpenCL, the GTX 1660 SUPER delivers roughly four times the score of the Vega 11. In Vulkan, the ratio is closer to 4.7 times. The Vega 11's best recorded result is its Geekbench Metal score of 17,392, but there is no corresponding Metal test for the GTX 1660 SUPER, so that figure cannot be compared directly. The Vega 11 also has a Geekbench OpenCL score of 13,392 and a Vulkan score of 12,273, both of which are eclipsed by the NVIDIA part.

The Verdict

The data supports a clear separation between these two products. The NVIDIA GeForce GTX 1660 SUPER is the faster GPU in every shared benchmark, and the margins are substantial. In OpenCL, the NVIDIA card leads by 74.5 percent. In Vulkan, the lead expands to 78.5 percent. Anyone comparing these two on raw compute performance should expect the GTX 1660 SUPER to dominate.

The AMD Radeon Vega 11 is an integrated graphics processor with a 15 W TDP, no power connectors, and system-shared memory. The GTX 1660 SUPER is a dual-slot discrete card with a 125 W TDP, an 8-pin power connector, a suggested 300 W power supply, and 6 GB of dedicated GDDR6 memory on a 192-bit bus. The architectural and physical differences are extreme, and the benchmark results reflect that chasm.

The Vega 11 does have one advantage in the database: its average benchmark score of 14,352 is higher than the GTX 1660 SUPER's average of 12,986, and its percentile rank is 56 versus 53. However, this is a function of the test sets, not a claim of superior performance. The Vega 11's averages come from Geekbench Metal, OpenCL, and Vulkan, all of which tend to reward its GCN architecture. The GTX 1660 SUPER's average includes Passmark DirectX 9, 10, 11, and 12 results, plus G2D, G3D, and compute tests, which pull its mean downward. When the two share a benchmark, the NVIDIA card wins by a wide margin.

For a user who needs maximum compute throughput in OpenCL or Vulkan workloads, the GTX 1660 SUPER is the only rational choice from this data. For a user constrained to integrated graphics, the Vega 11 is what it is: a low-power IGP that sits in the 56th percentile of all GPUs and trades blows with the GTX TITAN, RX Vega 11, Iris Xe MAX, and GTX 965M. There is no scenario in the recorded benchmarks where the Vega 11 outperforms the GTX 1660 SUPER.

Architecture Differences

The two products come from different manufacturers and different design philosophies. The AMD Radeon Vega 11 uses the Picasso chip, built on GCN 5.0 architecture at GlobalFoundries' 12 nm process. It packs 4,940 million transistors into a 210 mm² die, yielding a transistor density of 23.5 million per square millimeter. The NVIDIA GeForce GTX 1660 SUPER uses the TU116 chip, built on Turing architecture at TSMC's 12 nm process. It contains 6,600 million transistors on a 284 mm² die, for a density of 23.2 million per square millimeter. The process nodes are the same, and the densities are nearly identical, but the NVIDIA die is larger and holds more hardware.

The compute resources diverge sharply. The Vega 11 has 704 shading units, 44 texture mapping units, and 8 raster output units. The GTX 1660 SUPER has 1,408 shading units, 88 TMUs, and 48 ROPs. In every category, the NVIDIA card has exactly double the shading units and TMUs, and six times the ROPs. The pixel rate tells the story: the Vega 11 manages 11.20 GPixel/s, while the GTX 1660 SUPER reaches 85.68 GPixel/s. The texture rate is 61.60 GTexel/s for the AMD part versus 157.1 GTexel/s for the NVIDIA part. The FP32 throughput is 1.971 TFLOPS for the Vega 11 and 5.027 TFLOPS for the GTX 1660 SUPER. Both support FP16 at a 2:1 ratio, giving 3.942 TFLOPS and 10.05 TFLOPS respectively.

Memory is the other major divider. The Vega 11 uses system-shared memory, with the bus width, type, and bandwidth all listed as system dependent. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus, with 336.0 GB/s of bandwidth and a memory clock of 1750 MHz, or 14 Gbps effective. The Vega 11's memory performance cannot be quantified from the database because it depends entirely on the host system's RAM.

Clock speeds also favor the NVIDIA card. The Vega 11 has a base clock of 300 MHz and a boost of 1400 MHz. The GTX 1660 SUPER has a base clock of 1530 MHz and a boost of 1785 MHz. The NVIDIA part starts at a clock higher than the AMD part's maximum boost.

The feature sets are similar on the API front. Both support DirectX 12 with feature level 12_1 and OpenGL 4.6. The Vulkan support differs: the Vega 11 supports Vulkan 1.3, while the GTX 1660 SUPER supports Vulkan 1.4. Neither has ray tracing cores or tensor cores.

The physical specifications are also distinct. The Vega 11 is an IGP with no slot width, no power connectors, and no dedicated dimensions; its display outputs are motherboard dependent. The GTX 1660 SUPER is a dual-slot card measuring 229 mm in length, 111 mm in height, and 35 mm in width, with a 1x 8-pin power connector, a suggested 300 W power supply, and display outputs of 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a. The TDP difference is 15 W versus 125 W.

The release dates are close: the Vega 11 launched on September 29, 2019, and the GTX 1660 SUPER launched on October 28, 2019. Both are end-of-life products. The Vega 11's predecessor is GCN 3.0 IGP and its successor is Vega II IGP. The GTX 1660 SUPER's predecessor is GeForce 10 and its successor is GeForce 20. The GTX 1660 SUPER has a launch MSRP of 229 USD.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon Vega 11 has an average score of 14,352 across its recorded benchmarks, compared to the NVIDIA GeForce GTX 1660 SUPER's average of 12,986. However, the Vega 11's average is based on only three Geekbench tests, while the GTX 1660 SUPER's average includes ten tests spanning Passmark and 3DMark.

Q: How large is the performance gap in the shared benchmarks?

A: In Geekbench OpenCL, the GTX 1660 SUPER leads the Vega 11 by 74.5 percent, scoring 52,490 versus 13,392. In Geekbench Vulkan, the lead is 78.5 percent, with scores of 57,102 versus 12,273.

Q: Does the Vega 11 have any benchmark where it beats the GTX 1660 SUPER?

A: No. The database records zero wins for the AMD Radeon Vega 11 against the NVIDIA GeForce GTX 1660 SUPER. The GTX 1660 SUPER wins both head-to-head tests.

Q: What is the memory configuration of each GPU?

A: The Vega 11 uses system-shared memory, with size, type, bus width, and bandwidth all dependent on the host system. The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s of bandwidth.

Q: How do the nearest rivals compare to each GPU?

A: The Vega 11's nearest rivals are all within 0.4 percent of its average score: the GTX TITAN is 0.1 percent ahead, the RX Vega 11 is 0.2 percent ahead, the Iris Xe MAX is 0.3 percent behind, and the GTX 965M is 0.4 percent ahead. The GTX 1660 SUPER's nearest rivals are within 0.9 percent: the RTX 3050 Ti Mobile and RX 580 are both 0.4 percent ahead, the Tesla M2090 is 0.7 percent ahead, and the Radeon 740M is 0.9 percent behind.

Q: What are the power requirements for each card?

A: The Vega 11 is an IGP with a 15 W TDP and no power connectors. The GTX 1660 SUPER has a 125 W TDP, requires a 1x 8-pin power connector, and has a suggested power supply of 300 W.

Where Each One Wins

The NVIDIA GeForce GTX 1660 SUPER wins every shared benchmark category in the database. Its OpenCL score of 52,490 is 74.5 percent higher than the Vega 11's 13,392, and its Vulkan score of 57,102 is 78.5 percent higher than the Vega 11's 12,273. The GTX 1660 SUPER also holds a massive advantage in raw throughput metrics: 5.027 TFLOPS versus 1.971 TFLOPS in FP32, 157.1 GTexel/s versus 61.60 GTexel/s in texture rate, and 85.68 GPixel/s versus 11.20 GPixel/s in pixel rate. Its 6 GB of GDDR6 memory on a 192-bit bus with 336.0 GB/s of bandwidth is a decisive advantage over the Vega 11's system-shared memory, which is entirely dependent on the host platform. The GTX 1660 SUPER is the clear pick for anyone running OpenCL compute tasks, Vulkan workloads, or any application that benefits from high pixel throughput and dedicated memory bandwidth.

The AMD Radeon Vega 11 wins in the categories that matter for a different class of user. Its 15 W TDP makes it viable in systems with no power connectors and no discrete GPU slot. Its average benchmark score of 14,352 is higher than the GTX 1660 SUPER's 12,986, which reflects its strong showing in Geekbench Metal, where it scores 17,392. The Vega 11 also sits in the 56th percentile of all GPUs, three points above the GTX 1660 SUPER's 53rd percentile. For a user who cannot install a dual-slot, 229 mm card with a 125 W TDP and an 8-pin connector, the Vega 11 is the only option in this comparison. Its performance is competitive with the GTX TITAN, RX Vega 11, Iris Xe MAX, and GTX 965M, all within 0.4 percent of its average score. The GTX 1660 SUPER, by contrast, is a discrete card that requires a 300 W power supply and a PCIe 3.0 x16 slot.

The database does not record any benchmark where the Vega 11 beats the GTX 1660 SUPER. The GTX 1660 SUPER wins both head-to-head tests, and its architectural advantages in shading units, TMUs, ROPs, clocks, and memory are reflected in every comparable metric. The Vega 11's only advantages are its lower power draw, its integrated nature, and its higher average score in a test suite that does not overlap with the NVIDIA card's. For pure performance, the GTX 1660 SUPER is the answer. For integrated, low-power operation, the Vega 11 holds its own against a cluster of nearby rivals.