AMD Radeon RX 6600 vs NVIDIA GeForce GTX 690 Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive sweep for the AMD Radeon RX 6600 in the two shared benchmark tests. In Geekbench OpenCL, the RX 6600 scores 28,850 against the GTX 690’s 17,399, a 65.8% advantage. That is not a marginal lead; it represents a generational leap in compute throughput that shows up clearly in raw number crunching workloads.

The Geekbench Vulkan result is even more lopsided. The RX 6600 posts 67,623, while the GTX 690 manages just 16,675. That is a 305.5% delta, meaning the modern AMD card delivers roughly four times the Vulkan performance of the older NVIDIA flagship. This gap is unsurprising given the architectural gulf between the two, but the sheer magnitude underscores how far GPU compute has advanced in the interval between their releases.

In terms of average benchmark score, the RX 6600 sits at 19,036, placing it in the 63rd percentile of all GPUs in the database. The GTX 690’s average is 17,037, which puts it in the 60th percentile. While the percentile gap looks small, the raw score difference of 1,999 points is meaningful, especially considering that the RX 6600 achieves this with far lower power draw and a smaller memory bus.

The nearest rivals for the RX 6600 in the database are the NVIDIA Quadro K6000 (19,030, 0% delta), the NVIDIA GeForce RTX 4050 Mobile (19,049, -0.1%), and the NVIDIA Tesla K20m (19,089, -0.3%). The RX 6600 essentially trades blows with these cards, sitting within a fraction of a percent of each. For the GTX 690, its closest neighbors are the AMD Radeon HD 7970M (17,019, 0.1%), the AMD Radeon RX 7600 XT (17,083, -0.3%), and the NVIDIA Tesla M4 (16,932, 0.6%). Notably, the GTX 690 actually edges out the RX 7600 XT by 0.3%, a surprising result for a card from 2012 against a modern RDNA 3 part.

Where Each One Wins

The RX 6600 wins both head-to-head tests, so the use-case split is straightforward on paper: it dominates in OpenCL compute and in Vulkan graphics workloads. The OpenCL score of 28,850 versus 17,399 indicates strong performance in applications that leverage general-purpose GPU computing, such as rendering, physics simulation, and certain content creation tasks. The Vulkan score of 67,623 versus 16,675 shows a massive advantage in modern game engines and Vulkan-based applications, where the newer architecture’s feature set and driver maturity pay dividends.

The GTX 690, despite its loss in both shared tests, still holds relevance in one narrow sense: its average benchmark score of 17,037 is only 10.5% behind the RX 6600’s 19,036, despite being built on a process node two generations older. However, this aggregate figure masks the reality that the GTX 690 has no recorded DirectX 11, DirectX 12, or 3DMark Steel Nomad results in the database, whereas the RX 6600 has a full suite of scores across PassMark DX9 (197), DX10 (95), DX11 (152), DX12 (51), G2D (889), G3D (15,096), and GPU Compute (6,554). The GTX 690 simply lacks comparable data in those categories, so any claims about its performance there would be speculation.

For users prioritizing modern APIs and compute, the RX 6600 is the clear pick. For those looking at legacy DirectX 9 or 10 titles, the RX 6600’s PassMark scores suggest it handles those workloads capably, though the GTX 690’s absence from those tests means no direct comparison is possible. The data favors the RX 6600 across every measurable dimension.

Architecture Differences

The architectural gap between these two GPUs is vast, and the numbers in the database illustrate it clearly. The RX 6600 uses the Navi 23 chip built on RDNA 2.0 architecture, manufactured on TSMC’s 7 nm process. The GTX 690 uses the GK104 chip with Kepler architecture, fabricated on a 28 nm process at the same foundry. That process difference alone explains much of the efficiency and performance disparity: 7 nm allows for far higher transistor density and lower power consumption per unit of work.

Transistor counts tell the story. The RX 6600 packs 11,060 million transistors on a 237 mm² die, yielding a density of 46.7 million transistors per square millimeter. The GTX 690 has 3,540 million transistors on a larger 294 mm² die, giving it just 12.0 million transistors per square millimeter. The RX 6600 crams nearly four times as many transistors into a smaller physical area, which translates directly into superior compute throughput per clock and per watt.

Clock speeds reinforce this. The RX 6600 runs at a base clock of 1626 MHz and boosts to 2491 MHz, with a game clock of 2044 MHz. The GTX 690 operates at 915 MHz base and 1019 MHz boost. Even accounting for architectural differences, the RX 6600’s raw clock advantage is substantial. Memory clocks differ too: the RX 6600’s memory runs at 1750 MHz (14 Gbps effective) versus the GTX 690’s 1502 MHz (6 Gbps effective). The RX 6600 uses 8 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth, while the GTX 690 has 2 GB of GDDR5 on a 256-bit bus, providing 192.3 GB/s. The RX 6600 achieves higher bandwidth with half the bus width, a direct result of faster memory technology.

Feature support diverges sharply. The RX 6600 includes 28 ray tracing cores, a capability entirely absent from the GTX 690, which has no RT cores. The RX 6600 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the GTX 690 is limited to DirectX 12 (11_0) and Vulkan 1.2.175. Shader and pixel throughput figures underscore the gap: the RX 6600 delivers 8.928 TFLOPS FP32 and 17.86 TFLOPS FP16 (2:1 ratio), while the GTX 690 manages 3.130 TFLOPS FP32 with no recorded FP16 support. Pixel rate is 159.4 GPixel/s for the RX 6600 versus 32.61 GPixel/s for the GTX 690, and texture rate is 279.0 GTexel/s versus 130.4 GTexel/s.

Specification Differences

The two cards differ in nearly every specification category. The RX 6600 has 1792 shading units, 112 TMUs, and 64 ROPs, while the GTX 690 has 1536 shading units, 128 TMUs, and 32 ROPs. The RX 6600’s higher shading unit count and doubled ROP count give it an edge in pixel-heavy workloads, while the GTX 690’s higher TMU count is offset by its much lower clock speeds.

Power requirements diverge dramatically. The RX 6600 has a TDP of 132 W and requires a single 8-pin power connector with a 300 W suggested PSU. The GTX 690 draws 300 W, needs two 8-pin connectors, and demands a 700 W suggested PSU. The RX 6600 delivers superior performance while consuming less than half the power, evidence of the efficiency gains of RDNA 2.0 over Kepler.

Physical dimensions differ as well. The RX 6600 measures 190 mm in length, 110 mm in height, and 40 mm in width. The GTX 690 is 279 mm long, 111 mm tall, and 38 mm wide. Both are dual-slot cards, but the GTX 690 is significantly longer, which can affect case compatibility. The RX 6600 uses PCIe 4.0 x8, while the GTX 690 uses PCIe 3.0 x16. Display outputs also differ: the RX 6600 offers 1x HDMI 2.1 and 3x DisplayPort 1.4a, while the GTX 690 provides 3x DVI and 1x mini-DisplayPort 1.2. The RX 6600’s modern outputs support higher resolutions and refresh rates, while the GTX 690’s DVI-centric setup is dated.

The RX 6600 has a launch MSRP of 329 USD, while the GTX 690 launched at 999 USD. Both cards are end-of-life in production status. The RX 6600 released on 2021-10-12, while the GTX 690 released on 2012-05-02. The RX 6600’s predecessor is Navi and its successor is Navi III, while the GTX 690’s predecessor is GeForce 500 and its successor is GeForce 700.

FAQ

Q: Which card is faster in Vulkan workloads?

A: The AMD Radeon RX 6600 dominates, scoring 67,623 in Geekbench Vulkan against the GTX 690’s 16,675, a 305.5% advantage.

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

A: The RX 6600 scores 28,850 in Geekbench OpenCL, while the GTX 690 scores 17,399, giving the AMD card a 65.8% lead.

Q: What is the average benchmark score difference?

A: The RX 6600 has an average benchmark score of 19,036, while the GTX 690 sits at 17,037. The AMD card is 1,999 points higher.

Q: Does the GTX 690 support ray tracing?

A: No, the GTX 690 has no ray tracing cores. The RX 6600 includes 28 RT cores, a feature entirely absent from the older NVIDIA card.

Q: How do power requirements compare?

A: The RX 6600 has a TDP of 132 W with a suggested PSU of 300 W and a single 8-pin connector. The GTX 690 has a TDP of 300 W, requires a 700 W PSU, and uses two 8-pin connectors.

Q: What are the memory configurations?

A: The RX 6600 has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The GTX 690 has 2 GB of GDDR5 on a 256-bit bus with 192.3 GB/s bandwidth.