AMD Radeon RX Vega 11 vs NVIDIA GeForce GTX 690 Comparison

Head-to-Head Benchmarks

The benchmark data is unambiguous: the NVIDIA GeForce GTX 690 wins both recorded head-to-head tests, and it does so by substantial margins. In Geekbench OpenCL, the GTX 690 scores 17,399 against the AMD Radeon RX Vega 11's 12,525, a delta of 38.9%. That is not a small edge; it is a commanding lead that places the two cards in different performance tiers despite their overlapping average scores in the broader database.

The Vulkan result tells a similar story, though with a tighter gap. The GTX 690 posts 16,675 in Geekbench Vulkan, while the RX Vega 11 manages 13,543. The delta here is 23.1%, still a comfortable win for the older discrete card. What makes this notable is that Vulkan is a modern API, and the RX Vega 11 supports a newer version of it (Vulkan 1.3 versus 1.2.175 on the GTX 690). The newer API support does not translate into a performance advantage in this workload.

Context from the database's nearest rival comparisons reinforces the picture. The GTX 690's average benchmark score is 17,037, placing it at the 60th percentile of all GPUs. Its nearest rivals include the AMD Radeon HD 7970M (17,019, delta 0.1%), the AMD Radeon RX 7600 XT (17,083, delta -0.3%), the NVIDIA Tesla M4 (16,932, delta 0.6%), and the NVIDIA GeForce RTX 3070 (17,208, delta -1%). The GTX 690 sits within 1% of the RTX 3070 in average score, which is remarkable for a card released years earlier. The RX Vega 11, by contrast, has an average score of 14,385, at the 56th percentile. Its nearest rivals are the NVIDIA GeForce GTX TITAN (14,373, delta 0.1%), the NVIDIA GeForce GTX 965M (14,404, delta -0.1%), the AMD Radeon Vega 11 (14,352, delta 0.2%), and the Intel Iris Xe MAX Graphics (14,315, delta 0.5%). The RX Vega 11 is effectively tied with those parts, none of which approach the GTX 690's average.

The head-to-head deltas are the cleanest evidence: 38.9% in OpenCL and 23.1% in Vulkan, both in favor of the GTX 690. The RX Vega 11 has a Geekbench Metal score of 17,086, but the GTX 690 has no Metal benchmark recorded, so that result cannot be compared directly. In the two shared tests, the older discrete GPU wins both, and the wins are not close.

Architecture Differences

The two GPUs come from different eras and entirely different design philosophies. The NVIDIA GeForce GTX 690 is a dual-GPU discrete card built on the GK104 chip using the Kepler architecture, part of the GeForce 600 generation. It uses a 28 nm process at TSMC and packs 3,540 million transistors on a 294 mm² die, giving a transistor density of 12.0M per mm². The AMD Radeon RX Vega 11 is an integrated graphics processor (IGP) built on the Picasso chip using GCN 5.0, part of the Vega IGP (Picasso) generation. It uses a 12 nm process at GlobalFoundries and contains 4,940 million transistors on a 210 mm² die, for a transistor density of 23.5M per mm². The RX Vega 11 actually has more transistors but on a smaller die, which explains its higher density.

The compute configurations diverge sharply. The GTX 690 has 1,536 shading units, 128 texture mapping units, and 32 ROPs. The RX Vega 11 has 704 shading units, 44 TMUs, and only 8 ROPs. These are not comparable numbers in any simple ratio; the GTX 690 is built for throughput, with four times the TMUs and four times the ROPs of the RX Vega 11. Pixel rate tells the story: 32.61 GPixel/s for the GTX 690 versus 11.20 GPixel/s for the RX Vega 11. Texture rate is 130.4 GTexel/s versus 61.60 GTexel/s. FP32 compute is 3.130 TFLOPS versus 1.971 TFLOPS. The RX Vega 11 does have a recorded FP16 figure of 3.942 TFLOPS (2:1), but the GTX 690 has no FP16 data in the database.

Clocks are another differentiator. The GTX 690 runs at a 915 MHz base and 1019 MHz boost. The RX Vega 11 has a 300 MHz base and a 1400 MHz boost. The low base clock on the IGP reflects power constraints; the higher boost shows it can scale up when thermals and power allow. Memory is where the architectures fundamentally diverge: the GTX 690 has 2 GB of GDDR5 on a 256 bit bus with 192.3 GB/s bandwidth, while the RX Vega 11 uses system shared memory, with system dependent bandwidth and no dedicated memory bus. The GTX 690's memory clock is 1502 MHz (6 Gbps effective), while the RX Vega 11's memory clock is simply "System Shared."

Power draws are in different universes. The GTX 690 has a TDP of 300 W, requires a dual-slot cooler, and needs two 8-pin power connectors plus a 700 W suggested PSU. The RX Vega 11 has a TDP of 15 W, is an IGP with no power connectors, and no suggested PSU. The GTX 690 is 279 mm long, 111 mm tall, and 38 mm wide; the RX Vega 11 has no recorded dimensions because it lives on the motherboard. API support favors the newer part: the RX Vega 11 supports DirectX 12 (12_1) and Vulkan 1.3, while the GTX 690 supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6.

The Verdict

The data points to a clear conclusion: the NVIDIA GeForce GTX 690 is the faster GPU in every shared benchmark, and the margins are decisive. A 38.9% lead in OpenCL and a 23.1% lead in Vulkan are not edge cases; they represent a consistent performance advantage across different API workloads. The GTX 690 also sits at the 60th percentile of all GPUs, with an average score of 17,037, while the RX Vega 11 sits at the 56th percentile with 14,385. The GTX 690's nearest rivals include the RTX 3070 within 1%, which puts its performance in a different conversation entirely.

Who should pick the GTX 690? Anyone who needs discrete GPU performance, has the power budget for a 300 W card, and can accommodate a dual-slot, 279 mm long card that needs two 8-pin connectors and a 700 W PSU. It delivers the higher pixel rate, texture rate, and FP32 compute, and it wins both recorded benchmarks outright. It is end-of-life, but its recorded performance remains competitive.

Who should pick the RX Vega 11? Anyone who needs an integrated solution with a 15 W TDP, no power connectors, and no dedicated card dimensions. It is a motherboard-dependent IGP, so it fits in systems where a discrete card cannot. It supports a newer DirectX feature level (12_1 versus 11_0) and Vulkan 1.3, and it has FP16 capabilities that the GTX 690 does not record. But the performance data shows it is closer to a GTX TITAN or GTX 965M than to the GTX 690. In the two shared tests, it loses by 23.1% and 38.9%, respectively.

The verdict is straightforward: the GTX 690 wins on raw performance, the RX Vega 11 wins on efficiency and integration. Neither card is currently produced; both are end-of-life. The choice depends entirely on whether the use case demands discrete performance or integrated simplicity.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 690 scores 17,399 versus the AMD Radeon RX Vega 11's 12,525, a delta of 38.9% in favor of the GTX 690.

Q: Which GPU wins in Geekbench Vulkan?

A: The NVIDIA GeForce GTX 690 scores 16,675 versus the AMD Radeon RX Vega 11's 13,543, a delta of 23.1% in favor of the GTX 690.

Q: How do their average benchmark scores compare?

A: The GTX 690 has an average benchmark score of 17,037 and sits at the 60th percentile of all GPUs. The RX Vega 11 has an average of 14,385 and sits at the 56th percentile.

Q: Does the RX Vega 11 have any benchmark where it wins?

A: The RX Vega 11 has a Geekbench Metal score of 17,086, but the GTX 690 has no Metal benchmark recorded, so no direct comparison is possible. In the two shared tests, the GTX 690 wins both.

Q: Which GPU has the higher power draw?

A: The GTX 690 has a TDP of 300 W and requires two 8-pin power connectors, a dual-slot cooler, and a 700 W suggested PSU. The RX Vega 11 has a TDP of 15 W, no power connectors, and no suggested PSU.

Q: What are the memory configurations?

A: The GTX 690 has 2 GB of GDDR5 on a 256 bit bus with 192.3 GB/s bandwidth. The RX Vega 11 uses system shared memory with system dependent bandwidth.

Where Each One Wins

The NVIDIA GeForce GTX 690 wins in every workload where a direct comparison exists. In OpenCL, it is 38.9% ahead. In Vulkan, it is 23.1% ahead. Its pixel rate of 32.61 GPixel/s is nearly three times the RX Vega 11's 11.20 GPixel/s, which matters for fill-rate-bound scenarios. Its texture rate of 130.4 GTexel/s is more than double the RX Vega 11's 61.60 GTexel/s, which matters for games that rely on heavy texturing. Its FP32 output of 3.130 TFLOPS exceeds the RX Vega 11's 1.971 TFLOPS, which matters for compute workloads that scale with shader throughput. The GTX 690 also has dedicated GDDR5 memory with 192.3 GB/s of bandwidth, eliminating the system dependent variability of shared memory.

The AMD Radeon RX Vega 11 wins where the GTX 690 cannot compete: power efficiency and physical integration. Its 15 W TDP versus 300 W is a 20x difference in rated power draw. It needs no power connectors, no expansion slot, and no PSU upgrade, since it is an IGP. It supports DirectX 12 (12_1) versus the GTX 690's 12 (11_0), and Vulkan 1.3 versus 1.2.175, so it has a newer API feature set. It also records FP16 compute at 3.942 TFLOPS (2:1), a capability the GTX 690 does not list. For systems where a discrete GPU is physically impossible or power budgets are tight, the RX Vega 11 is the only option of the two.

The GTX 690 is the choice for performance-critical tasks on a desktop with adequate power delivery. The RX Vega 11 is the choice for low-power, integrated systems where motherboard-dependent output and shared memory are acceptable trade-offs.

Specification Differences

The two GPUs differ in nearly every recorded specification. The GTX 690 uses the GK104 chip on Kepler architecture at 28 nm from TSMC; the RX Vega 11 uses the Picasso chip on GCN 5.0 at 12 nm from GlobalFoundries. The GTX 690 has 3,540 million transistors on a 294 mm² die; the RX Vega 11 has 4,940 million transistors on a 210 mm² die. Transistor density is 12.0M per mm² versus 23.5M per mm². Base clocks are 915 MHz versus 300 MHz; boost clocks are 1019 MHz versus 1400 MHz. The GTX 690's memory clock is 1502 MHz (6 Gbps effective); the RX Vega 11's is system shared.

Memory size is 2 GB GDDR5 versus system shared; bus width is 256 bit versus system shared; bandwidth is 192.3 GB/s versus system dependent. Shading units are 1,536 versus 704; TMUs are 128 versus 44; ROPs are 32 versus 8. Pixel rate is 32.61 GPixel/s versus 11.20 GPixel/s; texture rate is 130.4 GTexel/s versus 61.60 GTexel/s; FP32 is 3.130 TFLOPS versus 1.971 TFLOPS. The RX Vega 11 has FP16 at 3.942 TFLOPS (2:1); the GTX 690 has no recorded FP16. TDP is 300 W versus 15 W. Slot width is dual-slot versus IGP; power connectors are two 8-pin versus none; suggested PSU is 700 W versus none. Bus interface is PCIe 3.0 x16 versus IGP. Display outputs are 3x DVI and 1x mini-DisplayPort 1.2 versus motherboard dependent. DirectX support is 12 (11_0) versus 12 (12_1); OpenGL is 4.6 for both; Vulkan is 1.2.175 versus 1.3. Dimensions are 279 mm x 111 mm x 38 mm for the GTX 690; the RX Vega 11 has none recorded. The GTX 690's launch MSRP was 999 USD; the RX Vega 11 has no launch MSRP recorded.