AMD Radeon RX 5500 XT vs NVIDIA GeForce GTX 690 Comparison

FAQ

Q: How does the GTX 690 compare to the RX 5500 XT in raw compute benchmarks?

A: The RX 5500 XT decisively wins both recorded head-to-head tests. In Geekbench OpenCL, the RX 5500 XT scores 46,965 versus the GTX 690's 17,399, a 63% advantage. In Geekbench Vulkan, the RX 5500 XT scores 44,191 versus 16,675, a 62.3% lead.

Q: Which card has the higher average benchmark score across all recorded tests?

A: The GTX 690 holds a higher average benchmark score of 17,037, while the RX 5500 XT averages 14,692. However, the RX 5500 XT has eleven recorded benchmarks compared to just two for the GTX 690, so the averages reflect different test sets.

Q: What is the percentile ranking for each GPU in the database?

A: The GTX 690 sits at the 60th percentile among all GPUs, while the RX 5500 XT ranks at the 57th percentile. This places both cards in the mid-range tier, with the GTX 690 marginally higher overall.

Q: How does the memory configuration differ between these two cards?

A: The GTX 690 uses 2 GB of GDDR5 on a 256-bit bus with 192.3 GB/s bandwidth. The RX 5500 XT uses 4 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The RX 5500 XT has double the capacity and higher total bandwidth despite the narrower bus.

Q: What are the power requirements for each card?

A: The GTX 690 has a TDP of 300 W and requires a 700 W suggested PSU with 2x 8-pin connectors. The RX 5500 XT has a TDP of 130 W, a 300 W suggested PSU, and a single 8-pin connector. The RX 5500 XT draws less than half the power.

Q: Which card supports newer API features?

A: The RX 5500 XT supports DirectX 12 (12_1) and Vulkan 1.4, while the GTX 690 supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The RX 5500 XT has the more modern API baseline.

Architecture Differences

The two cards represent fundamentally different eras of GPU design. The GTX 690 uses the GK104 chip built on Kepler architecture at TSMC's 28 nm process. It packs 3,540 million transistors into a 294 mm² die, yielding a transistor density of 12.0M per mm². The RX 5500 XT uses the Navi 14 chip on RDNA 1.0 architecture, manufactured at TSMC's 7 nm node. This newer process packs 6,400 million transistors into a smaller 158 mm² die, achieving a density of 40.5M per mm², more than triple the GTX 690's density.

Clock speeds show the generational leap clearly. The GTX 690 runs at a 915 MHz base with a 1019 MHz boost. The RX 5500 XT starts at 1607 MHz base and boosts to 1845 MHz, with a game clock of 1717 MHz. The RX 5500 XT's memory clock of 1750 MHz translates to 14 Gbps effective, versus the GTX 690's 1502 MHz memory clock at 6 Gbps effective.

Shader configuration differs in scale and efficiency. The GTX 690 has 1536 shading units, 128 TMUs, and 32 ROPs. The RX 5500 XT has 1408 shading units, 88 TMUs, and 32 ROPs. Despite fewer shading units, the RX 5500 XT achieves higher throughput: 5.196 TFLOPS FP32 versus 3.130 TFLOPS, 59.04 GPixel/s versus 32.61 GPixel/s, and 162.4 GTexel/s versus 130.4 GTexel/s. The RX 5500 XT also offers FP16 compute at 10.39 TFLOPS with a 2:1 ratio, a feature the GTX 690 lacks entirely.

Interface and connectivity also differ. The GTX 690 uses PCIe 3.0 x16, while the RX 5500 XT uses PCIe 4.0 x8. Display outputs: the GTX 690 provides 3x DVI and 1x mini-DisplayPort 1.2, while the RX 5500 XT offers 1x HDMI 2.0b and 3x DisplayPort 1.4a. Physical dimensions show the GTX 690 at 279 mm length, 111 mm height, and 38 mm width, while the RX 5500 XT measures 180 mm in length with unspecified height and width.

Production timelines reflect the gap: the GTX 690 released on May 2, 2012, as part of GeForce 600, succeeding GeForce 500 and preceding GeForce 700. The RX 5500 XT launched on December 11, 2019, in the Radeon RX 5000 series, succeeding Vega and preceding Navi II. Both are now end-of-life products.

The Verdict

The data points to a clear generational split. The RX 5500 XT wins both head-to-head benchmark tests by wide margins: 63% in OpenCL and 62.3% in Vulkan. These are not close contests. The RX 5500 XT delivers more than double the compute performance in both recorded workloads while consuming less than half the power (130 W TDP versus 300 W TDP) and requiring a smaller PSU (300 W versus 700 W).

The GTX 690 does hold a higher average benchmark score (17,037 versus 14,692) and a slightly better percentile ranking (60th versus 57th). However, this is misleading: the GTX 690's average comes from only two OpenCL and Vulkan tests, while the RX 5500 XT's average includes eleven diverse tests spanning DirectX 9 through DirectX 12, Metal, and compute workloads. The RX 5500 XT's PassMark G3D score of 9,083 and GPU compute score of 4,446 demonstrate broader capability.

For a user prioritizing modern API support, lower power draw, and faster compute in OpenCL and Vulkan workloads, the RX 5500 XT is the evident choice. For someone focused purely on the two recorded cross-card benchmarks, the GTX 690 cannot compete. The GTX 690's dual-GPU design (implied by its 300 W power draw and dual-slot footprint) does not translate into compute advantages in these tests.

The verdict from the recorded data: the RX 5500 XT wins on performance per watt, memory capacity, API modernity, and raw compute scores. The GTX 690 retains only a marginal overall percentile advantage and a higher average score from a limited benchmark set.

Specification Differences

| Field | NVIDIA GeForce GTX 690 | AMD Radeon RX 5500 XT |

|---|---|---|

| Chip | GK104 | Navi 14 |

| Architecture | Kepler | RDNA 1.0 |

| Process Node | 28 nm | 7 nm |

| Transistors | 3,540 million | 6,400 million |

| Die Size | 294 mm² | 158 mm² |

| Transistor Density | 12.0M / mm² | 40.5M / mm² |

| Base Clock | 915 MHz | 1607 MHz |

| Boost Clock | 1019 MHz | 1845 MHz |

| Game Clock | None | 1717 MHz |

| Memory Clock | 1502 MHz, 6 Gbps effective | 1750 MHz, 14 Gbps effective |

| Memory Size | 2 GB | 4 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus Width | 256 bit | 128 bit |

| Memory Bandwidth | 192.3 GB/s | 224.0 GB/s |

| Shading Units | 1536 | 1408 |

| TMUs | 128 | 88 |

| ROPs | 32 | 32 |

| Pixel Rate | 32.61 GPixel/s | 59.04 GPixel/s |

| Texture Rate | 130.4 GTexel/s | 162.4 GTexel/s |

| FP32 | 3.130 TFLOPS | 5.196 TFLOPS |

| FP16 | None | 10.39 TFLOPS (2:1) |

| TDP | 300 W | 130 W |

| Power Connectors | 2x 8-pin | 1x 8-pin |

| Suggested PSU | 700 W | 300 W |

| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 3x DVI, 1x mini-DisplayPort 1.2 | 1x HDMI 2.0b, 3x DisplayPort 1.4a |

| DirectX | 12 (11_0) | 12 (12_1) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | 1.2.175 | 1.4 |

| Length | 279 mm | 180 mm |

| Launch MSRP | 999 USD | 169 USD |

Head-to-Head Benchmarks

The only two directly comparable benchmarks in the database are Geekbench OpenCL and Geekbench Vulkan, and the RX 5500 XT dominates both.

In Geekbench OpenCL, the RX 5500 XT scores 46,965 against the GTX 690's 17,399. The delta is -63% from the RX 5500 XT's perspective, meaning the GTX 690 trails by 63%. This is a massive gap, reflecting the RX 5500 XT's higher FP32 throughput (5.196 TFLOPS versus 3.130 TFLOPS) and its FP16 capability, which OpenCL workloads can leverage.

In Geekbench Vulkan, the RX 5500 XT scores 44,191 versus 16,675 for the GTX 690, a 62.3% deficit for the older card. Vulkan's modern API design favors the RX 5500 XT's RDNA architecture, which was built for contemporary graphics APIs. The GTX 690's Kepler architecture, designed for DirectX 11-era workloads, cannot match this efficiency.

The GTX 690 has no benchmark wins in the head-to-head comparison. Its only edge in the broader data comes from the average benchmark score across all tests, where it leads 17,037 to 14,692, and the percentile ranking, where it sits 3 points higher. But these aggregate metrics do not reflect the two direct comparisons, where the RX 5500 XT wins by more than 60% in each.

Notably, the RX 5500 XT's nearest rivals include the GTX 770 (average score 14,747, delta -0.4%) and the Quadro M2000 (14,532, delta 1.1%). The GTX 690's nearest rivals include the RX 7600 XT (17,083, delta -0.3%) and the RTX 3070 (17,208, delta -1%). These groupings show the GTX 690 averaging near modern mid-range cards, while the RX 5500 XT averages near older high-end cards. The direct benchmark comparisons tell a different story than the averages.

Where Each One Wins

The RX 5500 XT wins in every direct comparison recorded. Its OpenCL and Vulkan scores are more than 2.5 times higher than the GTX 690's. This makes it the clear choice for compute-heavy workloads, modern API-based applications, and any task that can leverage FP16 processing. The RX 5500 XT also wins on memory capacity (4 GB versus 2 GB) and bandwidth (224.0 GB/s versus 192.3 GB/s), which matters for texture-heavy scenes and larger datasets.

Power efficiency is another decisive win for the RX 5500 XT. Its 130 W TDP versus 300 W means less heat, lower electricity draw, and a smaller PSU requirement (300 W versus 700 W). The single 8-pin connector simplifies installation compared to the GTX 690's dual 8-pin setup. The RX 5500 XT also wins on physical footprint at 180 mm length versus 279 mm, fitting in smaller cases.

The GTX 690's wins are narrower and more situational. Its average benchmark score of 17,037 exceeds the RX 5500 XT's 14,692, and its 60th percentile ranking beats the 57th percentile. The GTX 690 also has a wider memory bus (256 bit versus 128 bit), which historically helps at high resolutions, though the RX 5500 XT's higher bandwidth and larger capacity offset this in the recorded data. The GTX 690's dual-GPU configuration may have benefited multi-display setups, given its three DVI outputs, but no benchmark data supports this advantage.

For DirectX 9 through DirectX 12 legacy workloads, the RX 5500 XT's PassMark scores show broad competence: DirectX 9 at 133, DirectX 10 at 46, DirectX 11 at 56, DirectX 12 at 40, G2D at 774, G3D at 9,083, and GPU compute at 4,446. The GTX 690 lacks comparable recorded scores in these tests.

Use-case conclusions from the data: choose the RX 5500 XT for modern compute, low power draw, Vulkan and OpenCL applications, and larger memory demands. Choose the GTX 690 only if the higher average score across a smaller test set matters more than the direct benchmark results, or if the wider 256-bit memory bus is a priority. In every head-to-head measurement, the RX 5500 XT wins decisively.