NVIDIA GeForce GTX 460 vs NVIDIA GeForce GTX 650 Ti Boost Comparison

NVIDIA GeForce GTX 650 Ti Boost and NVIDIA GeForce GTX 460 represent two distinct generations of mid-range graphics hardware, separated by nearly three years of architectural evolution. The benchmark data shows a clear overall winner, but the GTX 460 still holds relevance in specific legacy contexts. The GTX 650 Ti Boost delivers an average benchmark score of 8067, placing it in the 42nd percentile of all GPUs, while the GTX 460 scores 7925, sitting at the 41st percentile. The head-to-head Geekbench OpenCL result demonstrates a 17.4% advantage for the newer card, scoring 9302 versus 7925, which translates to a single win for the GTX 650 Ti Boost and none for the GTX 460 in direct comparisons.

The Verdict

The data points decisively toward the NVIDIA GeForce GTX 650 Ti Boost for nearly all modern use cases. Its average benchmark score of 8067 surpasses the GTX 460's 7925 by roughly 1.8%, and in the sole head-to-head benchmark, it wins by a substantial 17.4% margin. The GTX 650 Ti Boost also benefits from a significantly more modern feature set, including support for Vulkan 1.2.175, which the GTX 460 lacks entirely. For anyone building a system from used parts or upgrading an older rig, the GTX 650 Ti Boost is the superior choice, offering higher raw performance, better API support, and lower power consumption. The GTX 460, however, is not without merit; its 768 MB memory configuration and older architecture make it a niche option for retro builds or systems with legacy PCIe 2.0 slots. The GTX 650 Ti Boost is the clear winner for general-purpose gaming and compute tasks, while the GTX 460 should only be considered when compatibility with older motherboards or a specific aesthetic is paramount.

Where Each One Wins

The GTX 650 Ti Boost dominates in every measurable category from the data. In the head-to-head Geekbench OpenCL test, it scores 9302 against the GTX 460's 7925, a 17.4% lead that indicates markedly better compute throughput. This advantage extends to theoretical specifications: the GTX 650 Ti Boost delivers 1.585 TFLOPS of FP32 performance versus 907.2 GFLOPS for the GTX 460, a 74.7% difference. Its texture rate of 66.05 GTexel/s more than doubles the GTX 460's 37.80 GTexel/s, and its pixel rate of 16.51 GPixel/s compares favorably to 9.450 GPixel/s. Memory bandwidth also favors the newer card at 144.2 GB/s versus 86.40 GB/s, a 66.9% increase. The GTX 460 has no benchmark wins in this comparison, but its strengths lie in compatibility rather than performance; it uses a PCIe 2.0 x16 interface, which may be the only option on older motherboards, and its 210 mm length is shorter than the GTX 650 Ti Boost's 241 mm, potentially fitting in smaller cases. The GTX 460 also requires two 6-pin power connectors instead of one, which could be a drawback or a benefit depending on PSU availability.

Architecture Differences

The two cards are built on fundamentally different architectures that explain their performance gap. The GTX 650 Ti Boost uses the GK106 chip based on the Kepler architecture, manufactured on TSMC's 28 nm process. This chip contains 2,540 million transistors packed into a 221 mm² die, yielding a transistor density of 11.5M per mm². In contrast, the GTX 460 uses the GF104 chip from the Fermi architecture, built on a 40 nm process with 1,950 million transistors spread across a much larger 332 mm² die, resulting in only 5.9M transistors per mm². The smaller, denser process of the Kepler chip allows for higher clock speeds and better efficiency, reflected in the GTX 650 Ti Boost's 134 W TDP versus the GTX 460's 160 W TDP. The GTX 650 Ti Boost also features a base clock of 980 MHz with a boost clock of 1032 MHz, while the GTX 460 has no listed base or boost clocks, indicating a fixed clock architecture. The newer card houses 768 shading units, 64 texture mapping units, and 24 ROPs, compared to the GTX 460's 336 shading units, 56 TMUs, and 24 ROPs. Memory configurations differ significantly: the GTX 650 Ti Boost offers 2 GB of GDDR5 at 1502 MHz (6 Gbps effective) on a 192-bit bus, while the GTX 460 provides only 768 MB of GDDR5 at 900 MHz (3.6 Gbps effective) on the same 192-bit bus width. This memory disparity alone accounts for the massive bandwidth difference. Feature support also diverges: the GTX 650 Ti Boost supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175, whereas the GTX 460 supports DirectX 12 (11_0) and OpenGL 4.6 but has no Vulkan support. Display outputs reflect their eras, with the GTX 650 Ti Boost offering 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, while the GTX 460 provides 2x DVI and 1x mini-HDMI 1.3a.

FAQ

Q: Which card has higher raw compute performance?

A: The GeForce GTX 650 Ti Boost delivers 1.585 TFLOPS of FP32 compute, which is 74.7% higher than the GTX 460's 907.2 GFLOPS. This translates directly to a 17.4% lead in the Geekbench OpenCL head-to-head test.

Q: Is the GTX 460 still viable for modern gaming?

A: The data suggests limited viability. Its 768 MB memory and 86.40 GB/s bandwidth are severely constrained compared to the GTX 650 Ti Boost's 2 GB and 144.2 GB/s. Additionally, it lacks Vulkan support, which many modern titles require for optimal performance.

Q: What are the power requirements for each card?

A: The GTX 650 Ti Boost has a 134 W TDP and requires a 300 W suggested PSU with a single 6-pin connector. The GTX 460 has a 160 W TDP, needs a 450 W suggested PSU, and uses two 6-pin connectors.

Q: How do these cards compare in terms of memory bandwidth?

A: The GTX 650 Ti Boost offers 144.2 GB/s of bandwidth, a 66.9% improvement over the GTX 460's 86.40 GB/s. This is due to both higher memory clock speeds (6 Gbps effective versus 3.6 Gbps) and the same 192-bit bus width.

Q: Which card has better driver and API support going forward?

A: The GTX 650 Ti Boost supports Vulkan 1.2.175, while the GTX 460 has no Vulkan support at all. Both cards support DirectX 12 (11_0) and OpenGL 4.6, but the Vulkan capability gives the newer card a significant longevity advantage.

Q: Is the GTX 460 ever the better choice?

A: Only in very specific legacy scenarios. Its PCIe 2.0 x16 interface and shorter 210 mm length might be necessary for older motherboards or compact cases. It also has a lower transistor density, which may appeal to collectors of Fermi-era hardware.

Head-to-Head Benchmarks

The only direct benchmark comparison in the data is Geekbench OpenCL, where the GeForce GTX 650 Ti Boost scores 9302 against the GTX 460's 7925. This 17.4% margin is substantial and reflects the architectural gulf between the two cards. Breaking down the score, the GTX 650 Ti Boost's advantage is rooted in its 2.54 billion transistors, 768 shading units, and 144.2 GB/s of memory bandwidth, all of which accelerate compute workloads. The GTX 460, with its 1.95 billion transistors and 336 shading units, simply cannot keep pace in parallel processing tasks. The GTX 650 Ti Boost's texture rate of 66.05 GTexel/s versus 37.80 GTexel/s shows a 74.7% advantage in fill-rate-heavy operations, while its pixel rate of 16.51 GPixel/s versus 9.450 GPixel/s demonstrates a 74.7% lead in rasterization throughput. In gaming scenarios, this means the GTX 650 Ti Boost can handle higher resolutions and more demanding visual effects before hitting the same performance ceiling as the GTX 460. The memory clock difference is also stark: the GTX 650 Ti Boost runs at 1502 MHz (6 Gbps effective) compared to the GTX 460's 900 MHz (3.6 Gbps effective), a 66.7% clock advantage. When all these factors combine, the 17.4% OpenCL score gap seems almost conservative—in real-world compute tasks, the GTX 650 Ti Boost should feel dramatically faster. The GTX 460's only consolation is its higher TDP of 160 W, which suggests it draws more power but delivers less performance, making it strictly inferior on an efficiency basis. For the GTX 460 to win any workload, that workload would need to be heavily dependent on its specific Fermi architecture quirks, which the data does not support. The GTX 650 Ti Boost wins the head-to-head benchmark by a clear margin, and the underlying specifications confirm this is not a close contest.