AMD Radeon Vega 11 vs NVIDIA GeForce GTX 690 Comparison

Head-to-Head Benchmarks

In the recorded database, the NVIDIA GeForce GTX 690 faces the AMD Radeon Vega 11 across two shared benchmark tests. The results are unambiguous: the GTX 690 wins both, with a 2-0 record in head-to-head comparisons.

The first test, Geekbench OpenCL, shows the NVIDIA part scoring 17,399 points against the AMD part's 13,392 points. The delta of 29.9% is a decisive margin, placing the GTX 690 nearly a third ahead of the Vega 11 in this compute workload. The second test, Geekbench Vulkan, shows an even larger gap. The GTX 690 reaches 16,675 points, while the Vega 11 records 12,273 points, a 35.9% advantage. This suggests the Kepler architecture's driver and hardware scheduling hold up well in the Vulkan API, despite the NVIDIA card being from an older generation.

Looking at the broader average benchmark score, the GTX 690 sits at 17,037 points. Its nearest rivals in the database include the AMD Radeon HD 7970M at 17,019 (0.1% behind), the NVIDIA Tesla M4 at 16,932 (0.6% behind), the AMD Radeon RX 7600 XT at 17,083 (0.3% ahead), and the NVIDIA GeForce RTX 3070 at 17,208 (1% ahead). This places the GTX 690 in a tight cluster of mid-to-high range performers, with its average score falling within a narrow band of roughly 1% of its closest competitors.

The AMD Radeon Vega 11, in contrast, has an average benchmark score of 14,352 points. Its nearest rivals include the NVIDIA GeForce GTX TITAN at 14,373 (0.1% ahead), the AMD Radeon RX Vega 11 at 14,385 (0.2% ahead), the Intel Iris Xe MAX Graphics at 14,315 (0.3% behind), and the NVIDIA GeForce GTX 965M at 14,404 (0.4% ahead). The Vega 11's average score is therefore about 18.7% lower than the GTX 690's average, a substantial gap that aligns with the head-to-head deltas.

The Vulkan result is particularly telling. A 35.9% margin in that API indicates that the GTX 690's 1536 shading units and 128 texture mapping units provide a raw throughput advantage that the Vega 11's 704 shading units and 44 TMUs cannot overcome, even with the AMD part's higher boost clock (1400 MHz vs 1019 MHz). The OpenCL delta of 29.9% reinforces this pattern: the GTX 690's 3.130 TFLOPS of FP32 compute versus the Vega 11's 1.971 TFLOPS shows a 58.8% theoretical peak difference, though the real-world benchmark gap is smaller due to memory sharing and driver overhead on the integrated part.

The Verdict

The data points to a clear winner for users who need dedicated graphics performance. The NVIDIA GeForce GTX 690 is ahead in every recorded head-to-head benchmark, with deltas of 29.9% and 35.9% in OpenCL and Vulkan respectively. Its average benchmark score of 17,037 places it in the 60th percentile of all GPUs in the database, while the AMD Radeon Vega 11 sits at the 56th percentile with its average of 14,352.

For compute-heavy tasks such as OpenCL-based rendering or Vulkan gaming, the GTX 690 is the stronger choice. Its 2 GB of dedicated GDDR5 memory with 192.3 GB/s of bandwidth provides a stable memory subsystem, whereas the Vega 11 relies on system-shared memory with bandwidth that is system-dependent. The GTX 690's 32 ROPs and 32.61 GPixel/s pixel rate also give it a clear edge in fill-rate-bound scenarios compared to the Vega 11's 8 ROPs and 11.20 GPixel/s.

However, the Vega 11 has its own niche. As an integrated graphics processor (IGP) with a 15 W TDP, it consumes a fraction of the GTX 690's 300 W TDP. The GTX 690 requires a dual-slot cooler, two 8-pin power connectors, and a 700 W suggested PSU, while the Vega 11 needs no power connectors and draws from the motherboard. For a compact, low-power system where discrete graphics is not an option, the Vega 11 is the only viable choice in this comparison. Its FP16 capability, rated at 3.942 TFLOPS (2:1), also offers a path for workloads that can leverage half-precision math, a feature the GTX 690 lacks entirely.

The percentile difference, 60 vs 56, is modest, but the benchmark score gap is not. Users should pick the GTX 690 for any task where raw GPU throughput matters. Users who need an IGP with minimal power draw and no expansion slot should pick the Vega 11, accepting its lower scores.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 690 scores 17,399, beating the AMD Radeon Vega 11's 13,392 by 29.9%.

Q: How large is the Vulkan performance gap?

A: The GTX 690 scores 16,675 in Geekbench Vulkan, while the Vega 11 scores 12,273, a 35.9% advantage for the NVIDIA part.

Q: What are the average benchmark scores for each GPU?

A: The GTX 690 has an average benchmark score of 17,037, and the Vega 11 has an average of 14,352.

Q: Does the Vega 11 support any feature the GTX 690 does not?

A: Yes, the Vega 11 supports FP16 compute at 3.942 TFLOPS (2:1 ratio), while the GTX 690 has no listed FP16 capability. The Vega 11 also supports DirectX 12 (12_1) and Vulkan 1.3, whereas the GTX 690 supports DirectX 12 (11_0) and Vulkan 1.2.175.

Q: Which GPU has a higher transistor density?

A: The AMD Radeon Vega 11 has a transistor density of 23.5M per mm², compared to the GTX 690's 12.0M per mm², despite the Vega 11 having a smaller die size of 210 mm² versus 294 mm².

Q: What is the power consumption difference?

A: The GTX 690 has a 300 W TDP and requires a 700 W suggested PSU, while the Vega 11 has a 15 W TDP and needs no separate power connectors.

Specification Differences

The two GPUs differ across nearly every core specification. The NVIDIA GeForce GTX 690 uses the GK104 chip on a 28 nm process from TSMC, while the AMD Radeon Vega 11 uses the Picasso chip on a 12 nm process from GlobalFoundries. The GTX 690 contains 3,540 million transistors on a 294 mm² die, whereas the Vega 11 contains 4,940 million transistors on a 210 mm² die. This yields a transistor density of 12.0M per mm² for the NVIDIA part and 23.5M per mm² for the AMD part.

Clock speeds diverge sharply. The GTX 690 runs at a base clock of 915 MHz with a boost of 1019 MHz and a memory clock of 1502 MHz (6 Gbps effective). The Vega 11 runs at a base of 300 MHz and boosts to 1400 MHz, with system-shared memory. The GTX 690 has 2 GB of GDDR5 on a 256-bit bus with 192.3 GB/s of bandwidth, while the Vega 11 has system-shared memory with system-dependent bandwidth.

The compute units differ: the GTX 690 has 1536 shading units, 128 TMUs, and 32 ROPs, while the Vega 11 has 704 shading units, 44 TMUs, and 8 ROPs. Pixel rate is 32.61 GPixel/s for the GTX 690 versus 11.20 GPixel/s for the Vega 11. Texture rate is 130.4 GTexel/s versus 61.60 GTexel/s. FP32 performance is 3.130 TFLOPS versus 1.971 TFLOPS. The Vega 11 also lists FP16 at 3.942 TFLOPS, a field absent for the GTX 690.

Power and physical specifications are also distinct. The GTX 690 has a 300 W TDP, dual-slot width, two 8-pin power connectors, a 700 W suggested PSU, and PCIe 3.0 x16 interface. The Vega 11 has a 15 W TDP, IGP slot width, no power connectors, no suggested PSU, and an IGP bus interface. The GTX 690 measures 279 mm in length, 111 mm in height, and 38 mm in width, while the Vega 11 has no listed dimensions.

Architecture Differences

The architectural divide is fundamental. The NVIDIA GeForce GTX 690 is built on the Kepler architecture, part of the GeForce 600 generation, with a GK104 chip. The AMD Radeon Vega 11 is built on GCN 5.0, part of the Vega IGP (Picasso) generation, with a Picasso chip. Neither part has ray tracing cores or tensor cores, as both predate those features in their respective lineups.

The process nodes reflect their release eras. The GTX 690 uses TSMC's 28 nm node, while the Vega 11 uses GlobalFoundries' 12 nm node. The GTX 690 was released in May 2012, and the Vega 11 in September 2019, a gap of over seven years. The predecessor and successor chains also differ: the GTX 690 follows the GeForce 500 series and precedes the GeForce 700 series, while the Vega 11 follows GCN 3.0 IGP and precedes Vega II IGP.

API support shows a generational shift. The GTX 690 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The Vega 11 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The Vega 11's higher DirectX feature level and newer Vulkan version reflect its later design, though the GTX 690's older API levels still deliver higher benchmark scores in the recorded tests.

Memory architecture is a critical difference. The GTX 690 uses dedicated GDDR5 with a fixed 256-bit bus and fixed bandwidth of 192.3 GB/s. The Vega 11 uses system-shared memory, with the bus width and bandwidth listed as system-dependent. This means the Vega 11's memory performance varies with the host system's RAM configuration, while the GTX 690 has a predictable, fixed memory subsystem.

The Vega 11's FP16 capability, listed at 3.942 TFLOPS (2:1), indicates a packed math path that the GTX 690 does not expose. This is a feature difference that may matter for certain compute workloads, though the GTX 690's FP32 throughput remains higher in all recorded benchmarks.

Display outputs also differ: the GTX 690 offers 3x DVI and 1x mini-DisplayPort 1.2, while the Vega 11's outputs are motherboard-dependent, as expected for an integrated part. The GTX 690's production status is end-of-life, as is the Vega 11's, so neither is a current purchase recommendation, but the data remains relevant for legacy systems and used-market comparisons.