AMD Radeon R9 M380 vs NVIDIA GeForce GTX 690 Comparison

Head-to-Head Benchmarks

The recorded database contains a single shared benchmark between these two GPUs, and the result is decisive. In the Geekbench OpenCL test, the NVIDIA GeForce GTX 690 scores 17,399 points, while the AMD Radeon R9 M380 scores 12,565 points. This translates to a 38.5% advantage for the GTX 690, a substantial margin that places the two cards in completely different performance tiers for compute workloads. The GTX 690 does not merely edge out the R9 M380; it outperforms it by more than a third, which is a category-level difference rather than a minor generational gap.

To put this single result into perspective, the GTX 690's average benchmark score across all recorded tests is 17,037, and it sits at the 60th percentile among all GPUs in the database. Its closest rivals in terms of average score include the AMD Radeon HD 7970M at 17,019 (a 0.1% difference), the NVIDIA Tesla M4 at 16,932 (0.6% ahead), and the NVIDIA GeForce RTX 3070 at 17,208 (where the GTX 690 trails by 1%). Notably, the GTX 690 is also within 0.3% of the AMD Radeon RX 7600 XT, which scores 17,083. This positioning is remarkable for a card from the GeForce 600 generation, as it holds its own against much newer hardware in aggregate compute scores.

The AMD Radeon R9 M380, by contrast, has an average benchmark score of 15,521, placing it at the 58th percentile. Its nearest rivals tell a different story: it trails the NVIDIA GeForce GTX 1080 Ti by 0.2% (15,548), sits 1% behind the AMD Radeon Pro W5500 (15,679), and leads the NVIDIA GeForce RTX 2060 by 1.5% (15,290) and the NVIDIA GeForce GTX 580 by 1.6% (15,283). The data shows that the R9 M380 operates in a performance band where it trades blows with older flagship cards, but it is nowhere near the absolute compute throughput of the GTX 690.

However, the benchmark picture is not one-sided. The R9 M380 has a recorded Geekbench Metal score of 18,476, which is its strongest result in the database. The GTX 690 has no Metal score recorded, so cross-platform API performance cannot be directly compared. Still, for OpenCL, which both cards support, the GTX 690's 38.5% lead is the definitive head-to-head data point. The wins column reflects this: the GTX 690 takes 1 win, and the R9 M380 takes 0.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 690 has an average benchmark score of 17,037, while the AMD Radeon R9 M380 averages 15,521. The GTX 690 is about 9.8% higher in aggregate, though the exact delta is not directly listed in the database.

Q: How does the GTX 690 compare to the RTX 3070 in average score?

A: The GTX 690's average score of 17,037 is 1% lower than the NVIDIA GeForce RTX 3070's average of 17,208. This places the older card within striking distance of a modern high-end GPU in the database's aggregate metric.

Q: Is the R9 M380 close to the GTX 1080 Ti in performance?

A: Yes. The R9 M380's average score of 15,521 is only 0.2% lower than the NVIDIA GeForce GTX 1080 Ti's average of 15,548. The data indicates they are effectively tied in aggregate compute performance.

Q: What is the single biggest benchmark win for either card?

A: In the Geekbench OpenCL test, the GTX 690 scores 17,399 versus the R9 M380's 12,565, a 38.5% advantage. This is the only direct head-to-head benchmark in the database, and it strongly favors the GTX 690.

Q: Does the R9 M380 have any benchmark where it wins?

A: The database records no direct benchmark wins for the R9 M380 against the GTX 690. It does have a high Geekbench Metal score of 18,476, but the GTX 690 has no Metal score recorded, so no direct comparison exists in that API.

Q: How does the GTX 690 rank against all GPUs?

A: The GTX 690 sits at the 60th percentile among all GPUs in the database. The R9 M380 is at the 58th percentile, showing that while both are above median, the GTX 690 ranks slightly higher overall.

Where Each One Wins

The use-case split follows the benchmark data closely, but with important nuances from the specification fields. The GTX 690 is the clear winner for raw compute throughput in OpenCL workloads. Its 38.5% lead in that specific test, combined with a higher average score across all tests, makes it the choice for applications that rely on general-purpose GPU compute, such as rendering, simulation, or data processing tasks that use OpenCL. The GTX 690 also holds a structural advantage in raw processing resources: it has 1,536 shading units, 128 texture mapping units, and 32 ROPs, compared to the R9 M380's 768 shading units, 48 TMUs, and 16 ROPs. The pixel rate of 32.61 GPixel/s and texture rate of 130.4 GTexel/s on the GTX 690 dwarf the R9 M380's 16.00 GPixel/s and 48.00 GTexel/s. For any workload that is fill-rate bound or shader-bound, the data points squarely at the GTX 690.

The R9 M380, however, has its own territory. It carries 4 GB of GDDR5 memory, double the GTX 690's 2 GB. This makes it better suited for workloads that need larger working sets, such as texture-heavy applications or datasets that exceed 2 GB. The R9 M380 also hits a higher DirectX feature level: it supports DirectX 12 (12_0), while the GTX 690 only supports DirectX 12 (11_0). For modern games or applications that leverage DirectX 12's full feature set, the R9 M380 has a compatibility edge. Additionally, the R9 M380's Geekbench Metal score of 18,476 is the highest single benchmark result recorded for either card, suggesting that in Metal-based environments (common on Apple platforms), it may outperform the GTX 690, though the GTX 690 has no Metal score for direct comparison.

In practical terms, the GTX 690 wins for users who need maximum compute performance and are willing to work within a 2 GB memory limit. The R9 M380 wins for users who need more memory capacity, better DirectX 12 feature support, or Metal API performance. The GTX 690's dual-slot design and 2x 8-pin power connectors indicate it is a desktop-focused card, while the R9 M380's lack of recorded dimensions and power details suggests it may target mobile or OEM configurations, where power and space constraints differ.

Specification Differences

The two cards differ on nearly every core specification. The NVIDIA GeForce GTX 690 uses the GK104 chip with 3,540 million transistors on a 294 mm² die, while the AMD Radeon R9 M380 uses the Strato chip with 2,080 million transistors on a 160 mm² die. The transistor density is slightly higher on the R9 M380 at 13.0M / mm² versus 12.0M / mm² for the GTX 690. Clock speeds are close: the GTX 690 runs at a base of 915 MHz and a boost of 1019 MHz, while the R9 M380 runs at 900 MHz base and 1000 MHz boost. Memory clocks are effectively identical at 1502 MHz (6 Gbps effective) for the GTX 690 and 1500 MHz (6 Gbps effective) for the R9 M380.

Memory configuration diverges sharply. The GTX 690 has 2 GB of GDDR5 on a 256-bit bus, yielding 192.3 GB/s of bandwidth. The R9 M380 has 4 GB of GDDR5 on a 128-bit bus, yielding only 96.00 GB/s. This means the GTX 690 has double the memory bandwidth, while the R9 M380 has double the capacity. Compute resources also favor the GTX 690: it has 1,536 shading units, 128 TMUs, and 32 ROPs, versus 768 shading units, 48 TMUs, and 16 ROPs on the R9 M380. Pixel and texture rates follow suit, with the GTX 690 at 32.61 GPixel/s and 130.4 GTexel/s, and the R9 M380 at 16.00 GPixel/s and 48.00 GTexel/s. FP32 performance is 3.130 TFLOPS for the GTX 690 and 1.536 TFLOPS for the R9 M380.

Power and physical specifications only exist for the GTX 690: it has a TDP of 300 W, a dual-slot width, 2x 8-pin power connectors, a suggested PSU of 700 W, and dimensions of 279 mm in length, 111 mm in height, and 38 mm in width. The R9 M380 has no recorded TDP, slot width, power connectors, suggested PSU, or dimensions. Both cards use a PCIe 3.0 x16 bus interface. The GTX 690 has display outputs of 3x DVI and 1x mini-DisplayPort 1.2, while the R9 M380 has no recorded display outputs.

Architecture Differences

The architectural split is fundamental. The GTX 690 is built on NVIDIA's Kepler architecture, while the R9 M380 uses AMD's GCN 2.0. Both are fabricated on a 28 nm process at TSMC, but the design philosophies diverge. Kepler, from the GeForce 600 generation, emphasizes high shader counts and clock efficiency. The GTX 690 packs 1,536 shading units into a 294 mm² die, achieving 3.130 TFLOPS of FP32 compute. Its memory subsystem uses a wide 256-bit bus to deliver 192.3 GB/s, which is critical for feeding those 128 TMUs at a texture rate of 130.4 GTexel/s. The GTX 690 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.

GCN 2.0, from AMD's R9 M300 generation, takes a different approach. The Strato chip is smaller at 160 mm² and uses 2,080 million transistors, but it runs at a similar clock range. The R9 M380 has half the shading units (768) and a quarter of the TMUs (48) relative to the GTX 690, resulting in a much lower texture rate of 48.00 GTexel/s and FP32 of 1.536 TFLOPS. Its memory system uses a narrow 128-bit bus, which halves bandwidth to 96.00 GB/s but allows for 4 GB of capacity. The R9 M380 supports DirectX 12 (12_0), a higher feature level than the GTX 690, and it also supports OpenGL 4.6 and Vulkan 1.2.170, slightly older than the GTX 690's Vulkan version.

The transistor density difference is notable: the R9 M380 packs 13.0M transistors per mm², versus 12.0M for the GTX 690, indicating a denser design despite the overall smaller chip. The GTX 690's release date is May 2, 2012, while the R9 M380's release date is May 4, 2015, making the AMD card a later design. The GTX 690 has a launch MSRP of 999 USD, while the R9 M380 has no recorded launch MSRP. The GTX 690's predecessor is the GeForce 500 series and its successor is the GeForce 700 series; the R9 M380's predecessor is the Solar System generation and its successor is Polaris Mobile. Both are end-of-life products. The GTX 690 is a dual-slot, high-power desktop card (300 W TDP), while the R9 M380's power profile is unrecorded, which may indicate a more power-efficient mobile or embedded design. The R9 M380's Metal score of 18,476 suggests strong compatibility with Apple's Metal API, a feature absent from the GTX 690's recorded benchmarks.