NVIDIA GeForce GTX 690 vs NVIDIA GeForce RTX 2070 SUPER Comparison

FAQ

Q: Which GPU is faster based on the recorded benchmark data?

A: The NVIDIA GeForce RTX 2070 SUPER wins both head-to-head benchmarks. In Geekbench OpenCL, it scores 83,358 versus the GTX 690's 17,399, a 379.1% difference. In Geekbench Vulkan, it scores 90,637 versus 16,675, a 443.6% difference.

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

A: The RTX 2070 SUPER has an average benchmark score of 20,282, while the GTX 690 has an average benchmark score of 17,037. The RTX 2070 SUPER also sits at the 65th percentile of all GPUs, compared to the GTX 690's 60th percentile.

Q: Do both cards support the same DirectX version?

A: No. The RTX 2070 SUPER supports DirectX 12 Ultimate (12_2), while the GTX 690 supports DirectX 12 (11_0). The RTX 2070 SUPER also supports Vulkan 1.4, whereas the GTX 690 supports Vulkan 1.2.175.

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

A: The RTX 2070 SUPER's closest rivals are the NVIDIA Quadro M4000M (1% behind), the RTX 3070 Mobile (1.2% behind), the Intel Arc B570 (1.3% behind), and the Intel Arc A750 (1.5% behind). The GTX 690's closest rivals are the AMD Radeon HD 7970M (0.1% ahead), the AMD Radeon RX 7600 XT (0.3% behind), the NVIDIA Tesla M4 (0.6% ahead), and the RTX 3070 (1% behind).

Q: What are the memory specifications of each card?

A: The RTX 2070 SUPER has 8 GB of GDDR6 memory on a 256-bit bus with 448.0 GB/s bandwidth. The GTX 690 has 2 GB of GDDR5 memory on a 256-bit bus with 192.3 GB/s bandwidth.

Q: Which card has a higher pixel rate?

A: The RTX 2070 SUPER has a pixel rate of 113.3 GPixel/s, while the GTX 690 has a pixel rate of 32.61 GPixel/s. The RTX 2070 SUPER also has a texture rate of 283.2 GTexel/s versus the GTX 690's 130.4 GTexel/s.

Architecture Differences

The two cards come from different NVIDIA generations and are built on entirely different architectures. The RTX 2070 SUPER uses the Turing architecture with the TU104 chip, fabricated on a 12 nm process at TSMC. The GTX 690 uses the Kepler architecture with the GK104 chip, fabricated on a 28 nm process, also at TSMC. This process difference is substantial: the RTX 2070 SUPER packs 13,600 million transistors into a 545 mm² die, achieving a transistor density of 25.0M per mm². The GTX 690 contains 3,540 million transistors on a 294 mm² die, for a density of 12.0M per mm².

The RTX 2070 SUPER belongs to the GeForce 20-series and its predecessor is the GeForce 10, with the GeForce 30 as its successor. The GTX 690 belongs to the GeForce 600 series, with the GeForce 500 as its predecessor and GeForce 700 as its successor. Both cards are now end-of-life production.

Feature support diverges sharply. The RTX 2070 SUPER includes 40 RT cores and 320 tensor cores, hardware that the GTX 690 completely lacks. The RTX 2070 SUPER also has a much larger shader array: 2,560 shading units, 160 TMUs, and 64 ROPs. The GTX 690 has 1,536 shading units, 128 TMUs, and 32 ROPs. The RTX 2070 SUPER reaches 9.062 TFLOPS FP32 performance, while the GTX 690 manages 3.130 TFLOPS. The RTX 2070 SUPER also supports FP16 at 18.12 TFLOPS (2:1), while the GTX 690 has no listed FP16 capability.

Memory technology is another clear divider. The RTX 2070 SUPER uses 8 GB of GDDR6 at 1750 MHz (14 Gbps effective), producing 448.0 GB/s bandwidth. The GTX 690 uses 2 GB of GDDR5 at 1502 MHz (6 Gbps effective), producing 192.3 GB/s bandwidth. Both use a 256-bit bus, but the newer memory standard and higher capacity give the RTX 2070 SUPER a decisive edge.

Head-to-Head Benchmarks

The database contains two direct benchmark comparisons between these cards, and the RTX 2070 SUPER dominates both.

In Geekbench OpenCL, the RTX 2070 SUPER scores 83,358 against the GTX 690's 17,399. That is a 379.1% advantage, meaning the newer card delivers nearly five times the compute performance in this workload. This is not a marginal generational gain; it is a complete redefinition of what the card can do in general-purpose compute.

In Geekbench Vulkan, the gap is even wider. The RTX 2070 SUPER scores 90,637, while the GTX 690 scores 16,675. The delta is 443.6%. This indicates that the RTX 2070 SUPER's architecture scales much better under the Vulkan API, likely due to its newer feature set and driver maturity.

The average benchmark scores tell a similar story, though with a smaller gap. The RTX 2070 SUPER averages 20,282 across its recorded tests, while the GTX 690 averages 17,037. The RTX 2070 SUPER's score places it at the 65th percentile of all GPUs, whereas the GTX 690 sits at the 60th percentile. The GTX 690's nearest rivals include the AMD Radeon RX 7600 XT, which is only 0.3% behind, and the AMD Radeon HD 7970M, which is 0.1% ahead. This suggests the GTX 690 is competitive with mid-range cards from much later generations, but it is not in the same league as the RTX 2070 SUPER.

The RTX 2070 SUPER wins both head-to-head tests, giving it a 2-0 record in direct comparisons. The GTX 690 has no wins in the recorded head-to-head data.

Specification Differences

The following specifications differ between the two cards:

• Process node: 12 nm (RTX 2070 SUPER) versus 28 nm (GTX 690)
• Transistors: 13,600 million versus 3,540 million
• Die size: 545 mm² versus 294 mm²
• Transistor density: 25.0M per mm² versus 12.0M per mm²
• Base clock: 1605 MHz versus 915 MHz
• Boost clock: 1770 MHz versus 1019 MHz
• Memory clock: 1750 MHz (14 Gbps effective) versus 1502 MHz (6 Gbps effective)
• Memory size: 8 GB versus 2 GB
• Memory type: GDDR6 versus GDDR5
• Memory bandwidth: 448.0 GB/s versus 192.3 GB/s
• Shading units: 2560 versus 1536
• TMUs: 160 versus 128
• ROPs: 64 versus 32
• RT cores: 40 versus none
• Tensor cores: 320 versus none
• Pixel rate: 113.3 GPixel/s versus 32.61 GPixel/s
• Texture rate: 283.2 GTexel/s versus 130.4 GTexel/s
• FP32 performance: 9.062 TFLOPS versus 3.130 TFLOPS
• FP16 performance: 18.12 TFLOPS (2:1) versus none listed
• TDP: 215 W versus 300 W
• Power connectors: 1x 6-pin + 1x 8-pin versus 2x 8-pin
• Suggested PSU: 550 W versus 700 W
• Display outputs: 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C versus 3x DVI, 1x mini-DisplayPort 1.2
• DirectX support: 12 Ultimate (12_2) versus 12 (11_0)
• Vulkan support: 1.4 versus 1.2.175
• Dimensions: 267 mm length, 116 mm height, 35 mm width versus 279 mm length, 111 mm height, 38 mm width
• Release date: 2019-07-08 versus 2012-05-02
• Launch MSRP: 499 USD versus 999 USD

Both cards are dual-slot designs, use PCIe 3.0 x16, and support OpenGL 4.6.

Where Each One Wins

The RTX 2070 SUPER wins every recorded benchmark comparison. In Geekbench OpenCL, it is 379.1% ahead, and in Geekbench Vulkan, it is 443.6% ahead. Its higher average score, larger memory pool, and modern feature set make it the clear choice for compute-heavy workloads, ray tracing (thanks to its 40 RT cores), and tensor-based tasks (thanks to its 320 tensor cores). Its 8 GB of GDDR6 memory at 448.0 GB/s bandwidth also positions it for modern game textures and higher resolutions.

The GTX 690, by contrast, has no benchmark wins in the recorded data. Its strengths are relative rather than absolute: it sits close to newer mid-range cards like the AMD Radeon RX 7600 XT, which trails it by only 0.3%, and the AMD Radeon HD 7970M, which is just 0.1% ahead. The GTX 690 also has a lower TDP than the RTX 2070 SUPER in terms of absolute draw, but it requires a higher suggested PSU (700 W versus 550 W), so this is not a practical advantage. Its 2 GB memory capacity and 192.3 GB/s bandwidth severely limit its usefulness in modern scenarios.

For users who need modern API support, the RTX 2070 SUPER's DirectX 12 Ultimate (12_2) and Vulkan 1.4 support are decisive. The GTX 690's DirectX 12 (11_0) and Vulkan 1.2.175 support are older and less capable. The RTX 2070 SUPER also offers a USB Type-C output, which the GTX 690 lacks, alongside modern HDMI and DisplayPort connections.

The Verdict

The data is unambiguous. The NVIDIA GeForce RTX 2070 SUPER outperforms the NVIDIA GeForce GTX 690 in every recorded benchmark, with margins ranging from 379.1% to 443.6% in head-to-head tests. Its average benchmark score of 20,282 versus 17,037 confirms that this is not a workload-specific anomaly but a general performance gap.

The RTX 2070 SUPER is the card to choose for anyone who needs modern compute features, ray tracing, tensor operations, or simply the highest frame rates. Its 8 GB GDDR6 memory, 40 RT cores, 320 tensor cores, and 9.062 TFLOPS FP32 performance make it suitable for contemporary workloads. Its 65th percentile ranking places it above the majority of GPUs in the database, and its nearest rivals are all within 1.5% of its average score, meaning it sits in a competitive but strong position.

The GTX 690, while historically significant as a dual-GPU flagship with a 999 USD launch MSRP, is now firmly a legacy product. Its 60th percentile ranking and closest rival being the AMD Radeon RX 7600 XT (0.3% behind) show that it still trades blows with some modern mid-range cards, but its 2 GB memory and lack of RT and tensor cores exclude it from modern feature-rich workloads. Its 300 W TDP and 700 W suggested PSU also make it less efficient in absolute terms than the RTX 2070 SUPER's 215 W TDP and 550 W suggested PSU.

For a buyer choosing between these two today, the RTX 2070 SUPER is the only rational pick. The GTX 690 remains a curiosity for collectors or those with very specific legacy requirements, but the benchmark data, memory capacity, and API support all point in one direction.