NVIDIA GeForce GTX 690 vs NVIDIA GeForce RTX 2060 SUPER Comparison

The NVIDIA GeForce RTX 2060 SUPER and the NVIDIA GeForce GTX 690 represent two distinct eras of GPU design, separated by seven years of architectural evolution. The data shows a decisive performance gap, but the comparison reveals more than just a generational leap; it highlights how core design philosophies—from multi-GPU complexity to single-chip efficiency—affect real-world benchmark outcomes.

Head-to-Head Benchmarks

The only direct benchmark data available for both cards are the Geekbench compute tests, and they paint a stark picture. In Geekbench OpenCL, the RTX 2060 SUPER scores 76,957, while the GTX 690 manages 17,399. This yields a delta of 342.3% in favor of the newer card. The pattern repeats in Geekbench Vulkan, where the RTX 2060 SUPER scores 77,402 against the GTX 690’s 16,675, a delta of 364.2%. The RTX 2060 SUPER wins both head-to-head tests, with a total of 2 wins to 0.

Interpreting these deltas requires context. A 342% lead in OpenCL is not merely a modest improvement; it indicates a fundamental difference in compute throughput. The RTX 2060 SUPER’s FP32 performance is listed at 7.181 TFLOPS, while the GTX 690’s is 3.130 TFLOPS. Even though the GTX 690 is a dual-GPU card, its per-GPU architecture and older Kepler design cannot match the raw shading throughput of the Turing-based RTX 2060 SUPER. The Vulkan result is even more telling, as Vulkan is a modern low-overhead API that scales well with architectural efficiency; the 364.2% delta suggests the GTX 690 is severely bottlenecked by its 2012-era design in this workload.

It is also worth noting the broader benchmark context. The RTX 2060 SUPER has an average benchmark score of 18,093 across all its tested workloads, placing it at the 62nd percentile of all GPUs. Its nearest rival is the NVIDIA GeForce RTX 3060 Mobile with an average score of 18,159, a delta of -0.4% (meaning the RTX 2060 SUPER is essentially tied). The GTX 690, by contrast, has an average score of 17,037, which puts it at the 60th percentile. Its nearest rival is the AMD Radeon HD 7970M with a score of 17,019, a delta of 0.1%. The 1,056-point gap in average scores between the two cards is substantial, but the head-to-head deltas are the primary evidence of dominance.

The Verdict

Based strictly on the data, the NVIDIA GeForce RTX 2060 SUPER is the clear choice for any user prioritizing modern compute performance. It wins both available head-to-head benchmarks by enormous margins (342.3% and 364.2%), and it achieves a higher average benchmark score (18,093 vs. 17,037). The GTX 690, while still at a respectable 60th percentile, is outperformed in every measurable category presented.

The RTX 2060 SUPER is also the only one of the two with a full suite of benchmark results, including Passmark tests (DirectX 9/10/11/12, G2D, G3D, and GPU Compute) and 3DMark Steel Nomad. The GTX 690 only has Geekbench OpenCL and Vulkan results listed, which limits its comparative footprint. The RTX 2060 SUPER’s score of 16,462 in Passmark G3D, for instance, is a strong indicator of general 3D rendering capability that the GTX 690 simply cannot be measured against in this data set.

The GTX 690’s only statistical advantage is its launch MSRP of 999 USD, but that is a historical figure from 2012. The RTX 2060 SUPER’s launch MSRP was 399 USD. For a user choosing between these two today, the performance data does not support selecting the GTX 690. The RTX 2060 SUPER is the superior product in every benchmark metric available.

Where Each One Wins

The RTX 2060 SUPER wins decisively in compute-heavy APIs. Its Vulkan score of 77,402 is more than four times higher than the GTX 690’s 16,675, making it the obvious choice for modern games and applications that utilize Vulkan or DirectX 12 Ultimate (which the RTX 2060 SUPER supports). Its OpenCL score of 76,957 similarly dominates, indicating strong performance in GPU-accelerated computing tasks like rendering or scientific workloads.

The GTX 690, however, has no benchmark wins in this comparison. It is notably its 2 GB of memory per GPU (for a total of 2 GB in the data set) and 32 ROPs are significantly lower than the RTX 2060 SUPER’s 8 GB and 64 ROPs. While the GTX 690 was designed as a dual-GPU flagship, the data shows that its architecture does not translate to wins in the tested workloads. The GTX 690’s nearest rival, the AMD Radeon RX 7600 XT (avg score 17,083, delta -0.3%), shows it is competitive with older mid-range cards, but not with the RTX 2060 SUPER.

The RTX 2060 SUPER also holds an advantage in feature support. Its API list includes DirectX 12 Ultimate (12_2) and Vulkan 1.4, whereas the GTX 690 only supports DirectX 12 (11_0) and Vulkan 1.2.175. This means the RTX 2060 SUPER is compatible with the latest graphics features like hardware ray tracing (34 RT cores) and tensor-based AI processing (272 Tensor Cores), which the GTX 690 lacks entirely.

FAQ

Q: Which card is faster in Geekbench OpenCL?

A: The NVIDIA GeForce RTX 2060 SUPER scores 76,957, while the NVIDIA GeForce GTX 690 scores 17,399. The RTX 2060 SUPER is 342.3% faster.

Q: What is the average benchmark score for each card?

A: The RTX 2060 SUPER has an average benchmark score of 18,093, while the GTX 690 has an average score of 17,037.

Q: Does the GTX 690 support ray tracing?

A: No. The GTX 690 has no RT cores listed in the data, while the RTX 2060 SUPER has 34 RT cores.

Q: What is the memory size difference?

A: The RTX 2060 SUPER has 8 GB of GDDR6 memory, while the GTX 690 has 2 GB of GDDR5 memory.

Q: Which card has a higher pixel rate?

A: The RTX 2060 SUPER has a pixel rate of 105.6 GPixel/s, compared to the GTX 690’s 32.61 GPixel/s.

Q: What is the process node difference?

A: The RTX 2060 SUPER is built on a 12 nm process, while the GTX 690 is built on a 28 nm process.

Architecture Differences

The architectural divide between these two cards is profound. The RTX 2060 SUPER uses the TU106 chip based on the Turing architecture, fabricated on a 12 nm process at TSMC. It contains 10,800 million transistors on a 445 mm² die, yielding a transistor density of 24.3 million per mm². The GTX 690 uses the GK104 chip based on the Kepler architecture, also from TSMC but on a 28 nm process. It contains 3,540 million transistors on a 294 mm² die, with a density of 12.0 million per mm².

The RTX 2060 SUPER’s Turing architecture introduces dedicated hardware features that the Kepler-based GTX 690 does not have. Specifically, the RTX 2060 SUPER is equipped with 34 RT cores for ray tracing and 272 Tensor cores for AI acceleration. The GTX 690 has no RT or Tensor cores, meaning it cannot accelerate these workloads. The RTX 2060 SUPER also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the GTX 690 supports older DirectX 12 (11_0) and Vulkan 1.2.175.

The GTX 690 is actually a dual-GPU card, as indicated by its dual 8-pin power connectors and 300 W TDP. However, the data lists it with 1,536 shading units, 128 TMUs, and 32 ROPs, which appears to be per-GPU. Even with two GPUs, its combined shading power is lower than the RTX 2060 SUPER’s 2,176 shading units operating at higher clocks (boost 1650 MHz vs 1019 MHz). The RTX 2060 SUPER’s texture rate of 224.4 GTexel/s and pixel rate of 105.6 GPixel/s dwarf the GTX 690’s 130.4 GTexel/s and 32.61 GPixel/s.

Specification Differences

The two cards differ across nearly every core specification. The RTX 2060 SUPER has a base clock of 1470 MHz and a boost clock of 1650 MHz, compared to the GTX 690’s 915 MHz base and 1019 MHz boost. Memory configurations are entirely different: the RTX 2060 SUPER uses 8 GB of GDDR6 on a 256-bit bus with 448.0 GB/s bandwidth, while the GTX 690 uses 2 GB of GDDR5 on a 256-bit bus with 192.3 GB/s bandwidth.

The compute units also differ. The RTX 2060 SUPER has 2,176 shading units, 136 TMUs, and 64 ROPs. The GTX 690 has 1,536 shading units, 128 TMUs, and 32 ROPs. The RTX 2060 SUPER’s FP32 performance is 7.181 TFLOPS, and it supports FP16 at 14.36 TFLOPS (2:1); the GTX 690 has no listed FP16 support and only 3.130 TFLOPS FP32.

Power and physical dimensions diverge as well. The RTX 2060 SUPER has a TDP of 175 W and requires a single 8-pin power connector with a suggested PSU of 450 W. The GTX 690 has a 300 W TDP, requires two 8-pin connectors, and suggests a 700 W PSU. The RTX 2060 SUPER is shorter at 229 mm (9 inches) versus the GTX 690’s 279 mm (11 inches), though both are dual-slot and similar in height. Display outputs differ: the RTX 2060 SUPER offers 1x DVI, 1x HDMI 2.0, 2x DisplayPort 1.4a, and 1x USB Type-C, while the GTX 690 offers 3x DVI and 1x mini-DisplayPort 1.2. The RTX 2060 SUPER was released in 2019, while the GTX 690 was released in 2012.