AMD Radeon Pro 455 vs NVIDIA GeForce GTX 1660 SUPER Comparison

The GeForce GTX 1660 SUPER and Radeon Pro 455 represent two very different design philosophies: one a desktop gaming card aimed at high throughput, the other a low-power mobile workstation part. The benchmark data shows a stark performance gulf, but the underlying specifications reveal why these products target entirely separate markets.

Head-to-Head Benchmarks

The two products share only two common benchmark results in the data set, and both are decisive victories for the NVIDIA GeForce GTX 1660 SUPER. In Geekbench OpenCL, the GTX 1660 SUPER scores 52,490 against the Radeon Pro 455's 10,336. That is a delta of 407.8% — the NVIDIA card is over five times faster in this compute workload. The margin is slightly narrower but still overwhelming in Geekbench Vulkan, where the GTX 1660 SUPER posts 57,102 versus 12,240 for the AMD card, a 366.5% advantage.

These are not close contests. The Geekbench OpenCL result is particularly telling, as it reflects general-purpose compute throughput that scales with raw shading power and memory bandwidth. The GTX 1660 SUPER's FP32 rating of 5.027 TFLOPS dwarfs the Radeon Pro 455's 1,313.3 GFLOPS, and its 336.0 GB/s of memory bandwidth is more than four times the AMD card's 81.28 GB/s. The Vulkan result similarly reflects the NVIDIA card's architectural efficiency and higher clock speeds.

The average benchmark scores tell a slightly different story, though. The GTX 1660 SUPER has an average benchmark score of 12,986, while the Radeon Pro 455 sits at 12,831. That is a difference of only 1.2%. This apparent contradiction is explained by the test suites: the NVIDIA card's average includes PassMark DirectX 9, 10, 11, and 12 scores plus G2D and G3D tests, while the AMD card's average is drawn from a different set of workloads. The Radeon Pro 455's nearest rival, the NVIDIA GeForce GTX 590, is within 0% delta, and the AMD FirePro W5100 trails by just 0.1%. Meanwhile, the GTX 1660 SUPER's closest competitor, the RTX 3050 Ti Mobile, is only 0.4% behind.

The head-to-head data is unambiguous: in shared tests, the GTX 1660 SUPER wins both, with deltas of 407.8% and 366.5%. The Radeon Pro 455 claims zero wins in head-to-head comparisons.

The Verdict

The data points to a simple conclusion: the GeForce GTX 1660 SUPER is the superior performer in every shared benchmark. Its Geekbench OpenCL score of 52,490 is not just higher — it is in a different performance class entirely, given the 407.8% delta over the Radeon Pro 455. Anyone selecting a GPU for raw compute or Vulkan rendering should choose the NVIDIA card without hesitation.

The Radeon Pro 455, however, is not without a niche. Its 35 W TDP is dramatically lower than the GTX 1660 SUPER's 125 W, and it requires no external power connectors, drawing everything from the PCIe slot. It is an MXM Module, designed for portable devices, whereas the GTX 1660 SUPER is a dual-slot desktop card with a 1x 8-pin power connector. The AMD card's display outputs are "Portable Device Dependent," confirming its role inside laptops or all-in-one systems.

The percentile rankings are nearly identical — the GTX 1660 SUPER sits at the 53rd percentile of all GPUs, the Radeon Pro 455 at the 52nd — which reflects that both cards land in the midrange of the overall GPU landscape. But within their shared test workloads, the NVIDIA card is the clear winner. The Radeon Pro 455's only advantage is its power envelope and form factor, not performance.

Architecture Differences

The architectural gap between these two cards is fundamental. The GeForce GTX 1660 SUPER is built on NVIDIA's Turing architecture, fabricated on a 12 nm process at TSMC. The chip, codenamed TU116, packs 6,600 million transistors onto a 284 mm² die, yielding a transistor density of 23.2M per mm². Turing brings features like concurrent floating-point and integer execution, which helps explain the card's strong compute scores.

The Radeon Pro 455 uses AMD's GCN 4.0 architecture, manufactured on a 14 nm process at GlobalFoundries. Its Baffin chip is far smaller, with 3,000 million transistors on a 123 mm² die, achieving a slightly higher transistor density of 24.4M per mm². GCN 4.0 is an older design that emphasizes scalar throughput, but it lacks the scheduling and cache optimizations of newer architectures.

The FP16 capabilities highlight a key difference. The GTX 1660 SUPER achieves 10.05 TFLOPS of FP16 performance at a 2:1 ratio relative to FP32, meaning it can double its throughput on half-precision workloads. The Radeon Pro 455 offers FP16 at a 1:1 ratio, delivering 1,313.3 GFLOPS — the same as its FP32 figure. This makes the NVIDIA card more versatile for mixed-precision compute.

Both cards lack dedicated ray tracing cores and tensor cores, as those fields are null in the data. The API support differs slightly: the GTX 1660 SUPER supports DirectX 12_1 and Vulkan 1.4, while the Radeon Pro 455 supports DirectX 12_0 and Vulkan 1.3. OpenGL 4.6 is common to both.

Specification Differences

The specification sheets diverge sharply across nearly every measurable field. Memory is a primary differentiator: the GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s of bandwidth. The Radeon Pro 455 has 2 GB of GDDR5 on a 128-bit bus, with 81.28 GB/s. The NVIDIA card's memory clock is 1750 MHz (14 Gbps effective), while the AMD card runs at 1270 MHz (5.1 Gbps effective).

Compute resources tell a similar story. The GTX 1660 SUPER has 1,408 shading units, 88 texture mapping units, and 48 ROPs. The Radeon Pro 455 has 768 shading units, 48 TMUs, and only 16 ROPs. This translates to a pixel rate of 85.68 GPixel/s for the NVIDIA card versus 13.68 GPixel/s for the AMD card, and a texture rate of 157.1 GTexel/s versus 41.04 GTexel/s.

Clock speeds are only listed for the NVIDIA card: a base of 1530 MHz and a boost of 1785 MHz. The Radeon Pro 455's base and boost clocks are not provided in the data. Power consumption is a major differentiator, with the GTX 1660 SUPER rated at 125 W TDP and the Radeon Pro 455 at just 35 W.

The bus interface also differs: the GTX 1660 SUPER uses PCIe 3.0 x16, while the Radeon Pro 455 uses PCIe 3.0 x8. The NVIDIA card's dimensions are 229 mm in length, 111 mm in height, and 35 mm in width, whereas the AMD card lists no physical dimensions. The GTX 1660 SUPER has a launch MSRP of 229 USD and a suggested PSU of 300 W; the Radeon Pro 455 has no MSRP or PSU requirement listed.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 1660 SUPER scores 52,490 versus the AMD Radeon Pro 455's 10,336, a 407.8% advantage for the NVIDIA card.

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

A: The GTX 1660 SUPER scores 57,102 in Geekbench Vulkan, while the Radeon Pro 455 scores 12,240. The NVIDIA card leads by 366.5%.

Q: What are the memory specifications for each card?

A: The GTX 1660 SUPER has 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The Radeon Pro 455 has 2 GB of GDDR5 on a 128-bit bus with 81.28 GB/s bandwidth.

Q: Which card has a lower power draw?

A: The AMD Radeon Pro 455 is rated at 35 W TDP, compared to 125 W for the NVIDIA GeForce GTX 1660 SUPER. The AMD card also requires no external power connectors.

Q: What are the average benchmark scores for each GPU?

A: The GTX 1660 SUPER has an average benchmark score of 12,986, placing it at the 53rd percentile of all GPUs. The Radeon Pro 455 averages 12,831, at the 52nd percentile.

Q: What is the transistor count and die size difference?

A: The GTX 1660 SUPER's TU116 chip has 6,600 million transistors on a 284 mm² die. The Radeon Pro 455's Baffin chip has 3,000 million transistors on a 123 mm² die.