AMD Radeon R7 350 vs NVIDIA GeForce GTX 460 SE Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon R7 350 records an average benchmark score of 7425, while the NVIDIA GeForce GTX 460 SE records 6389. The R7 350 sits at the 40th percentile of all GPUs, compared to the GTX 460 SE at the 37th percentile.

Q: What is the memory configuration difference between the two cards?

A: The AMD Radeon R7 350 offers 2 GB of GDDR5 on a 128-bit bus with 72.00 GB/s bandwidth. The NVIDIA GeForce GTX 460 SE offers 1024 MB of GDDR5 on a 256-bit bus with 108.8 GB/s bandwidth. The GTX 460 SE has the wider bus and higher bandwidth despite the smaller capacity.

Q: Which card has a higher pixel fill rate?

A: The AMD Radeon R7 350 achieves 12.80 GPixel/s, while the NVIDIA GeForce GTX 460 SE achieves 7.800 GPixel/s. The R7 350 leads by a substantial margin in this metric.

Q: What is the difference in power requirements?

A: The AMD Radeon R7 350 has a TDP of 55 W, requires no power connectors, and suggests a 250 W PSU. The NVIDIA GeForce GTX 460 SE has a TDP of 150 W, needs two 6-pin connectors, and suggests a 450 W PSU.

Q: Which GPU supports Vulkan?

A: Only the AMD Radeon R7 350 lists Vulkan support, at version 1.2.170. The NVIDIA GeForce GTX 460 SE does not list Vulkan support in the database.

Q: How do the two cards compare in compute performance (FP32)?

A: The AMD Radeon R7 350 delivers 819.2 GFLOPS, while the NVIDIA GeForce GTX 460 SE delivers 748.8 GFLOPS. The R7 350 leads by roughly 9% in raw FP32 throughput.

Where Each One Wins

The benchmark data splits clearly along generational lines. The AMD Radeon R7 350 wins the only direct head-to-head test, the Geekbench OpenCL benchmark, with a score of 7792 against 6389, a 22% advantage. This is the sole recorded benchmark where both cards appear, so the R7 350 takes the single win in the matchup.

The NVIDIA GeForce GTX 460 SE does not win any recorded benchmark against the R7 350. However, the older card holds advantages in specific hardware specifications that do not translate to the recorded compute test. The GTX 460 SE has a wider 256-bit memory bus versus 128-bit, higher memory bandwidth (108.8 GB/s versus 72.00 GB/s), more texture mapping units (48 versus 32), and more ROPs (32 versus 16). These features could favor certain legacy workloads or bandwidth-sensitive tasks, but the database contains no benchmark results to confirm such an advantage.

The R7 350 also wins on efficiency metrics that matter for deployment scenarios. Its 55 W TDP versus 150 W, single-slot versus dual-slot design, and lack of power connectors make it the more flexible option for compact or low-power systems. The GTX 460 SE, with its 2x 6-pin connectors and 450 W suggested PSU, targets a different class of desktop build.

Architecture Differences

The two cards come from different architectural eras and foundry processes. The AMD Radeon R7 350 uses the Cape Verde chip built on GCN 1.0 architecture, fabricated on a 28 nm TSMC process. It packs 1,500 million transistors into a 123 mm² die, yielding a transistor density of 12.2M per mm². The NVIDIA GeForce GTX 460 SE uses the GF104 chip based on Fermi architecture, also fabricated by TSMC but on an older 40 nm node. It contains 1,950 million transistors on a much larger 332 mm² die, with a density of 5.9M per mm².

The GCN 1.0 design on the R7 350 allocates resources differently: 512 shading units, 32 TMUs, and 16 ROPs. The Fermi design on the GTX 460 SE counters with 288 shading units, 48 TMUs, and 32 ROPs. This means the R7 350 relies on a higher shader count for compute throughput, while the GTX 460 SE balances more texture and pixel processing hardware.

API support also diverges. The R7 350 lists DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The GTX 460 SE lists DirectX 12 (11_0) and OpenGL 4.6 but no Vulkan support. Both are end-of-life products, but the R7 350 comes from the Pirate Islands (R7 300) generation with a 2016 release date, while the GTX 460 SE belongs to the GeForce 400 generation with a 2010 release date.

Specification Differences

The memory subsystem shows the clearest divergence. The R7 350 uses 2 GB of GDDR5 at 1125 MHz (4.5 Gbps effective) on a 128-bit bus, delivering 72.00 GB/s. The GTX 460 SE uses 1024 MB of GDDR5 at 850 MHz (3.4 Gbps effective) on a 256-bit bus, delivering 108.8 GB/s. The GTX 460 SE wins bandwidth, the R7 350 wins capacity.

Compute specifications favor the R7 350 in shader count and FP32 throughput: 512 shading units and 819.2 GFLOPS versus 288 units and 748.8 GFLOPS. The GTX 460 SE leads in texture rate (31.20 GTexel/s versus 25.60 GTexel/s) and ROP count (32 versus 16), while the R7 350 leads in pixel rate (12.80 GPixel/s versus 7.800 GPixel/s).

Physical and power specifications differ sharply. The R7 350 is a single-slot, 168 mm card with no power connectors and a 55 W TDP. The GTX 460 SE is a dual-slot, 210 mm card with 2x 6-pin connectors and a 150 W TDP. The R7 350 uses PCIe 3.0 x16; the GTX 460 SE uses PCIe 2.0 x16. Display outputs also differ: the R7 350 offers 1x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the GTX 460 SE offers 2x DVI and 1x mini-HDMI 1.3a.

Head-to-Head Benchmarks

The only direct comparison in the database is the Geekbench OpenCL test. The AMD Radeon R7 350 scores 7792, and the NVIDIA GeForce GTX 460 SE scores 6389. The delta is 22% in favor of the R7 350. This is a decisive margin for a compute-oriented workload, reflecting the R7 350's higher FP32 throughput (819.2 GFLOPS versus 748.8 GFLOPS) and newer architecture.

The R7 350 also records a Geekbench Vulkan score of 7057, a test the GTX 460 SE cannot run due to lacking Vulkan support. While this is not a head-to-head result, it indicates the R7 350 has access to a modern API workload that is entirely unavailable to the older Fermi card.

Looking at the broader rival landscape, the R7 350's average score of 7425 places it near several competing parts. It trails the Intel Arc A310 (7550) by 1.7%, sits close to the NVIDIA GeForce GTX 1650 (7472) at a 0.6% deficit, and is nearly even with the AMD Radeon HD 8850M (7447, 0.3% lower) and Intel UHD Graphics 750 (7441, 0.2% lower). The GTX 460 SE's average of 6389 matches the NVIDIA GeForce GTX 580M exactly (0% delta), trails the NVIDIA RTX PRO 5000 72 GB Blackwell (6407) by 0.3%, and leads the AMD Radeon Pro WX 4100 (6330) by 0.9% and the AMD Radeon R7 M350 (6327) by 1%.

These percentile positions reinforce the head-to-head result. The R7 350 sits at the 40th percentile of all GPUs, while the GTX 460 SE sits at the 37th. The three-point percentile gap aligns with the 22% OpenCL delta, suggesting the R7 350 is the stronger compute part across the database's broader GPU population.

The Verdict

The data points to a clear winner for compute-focused workloads. The AMD Radeon R7 350 wins the only direct benchmark by 22%, holds a higher average score (7425 versus 6389), and reaches a higher percentile (40 versus 37). Its newer GCN 1.0 architecture, 28 nm process, and higher shader count translate directly into superior OpenCL performance.

The NVIDIA GeForce GTX 460 SE retains some specification-level advantages, namely memory bandwidth (108.8 GB/s versus 72.00 GB/s), texture rate (31.20 GTexel/s versus 25.60 GTexel/s), and ROP count (32 versus 16). These could matter for specific legacy workloads or older game engines that favor fill-rate-heavy operations, but no recorded benchmark confirms such a scenario.

For system builders prioritizing low power and flexibility, the R7 350 is the practical choice: 55 W TDP, no power connectors, single-slot footprint, and a 250 W suggested PSU versus the GTX 460 SE's 150 W TDP, 2x 6-pin connectors, dual-slot design, and 450 W suggested PSU. The R7 350 also offers modern connectivity with DisplayPort 1.2 and HDMI 1.4a, plus Vulkan support.

The GTX 460 SE makes sense only for scenarios where its wider memory bus and higher bandwidth are essential, and where the older Fermi feature set is acceptable. Its lack of Vulkan support and lower compute scores limit its relevance in modern workloads. The database's recorded results favor the AMD Radeon R7 350 as the more capable and versatile GPU for compute tasks, while the GTX 460 SE remains a historical part with niche specification strengths.