Intel UHD Graphics 750 vs NVIDIA GeForce GTX 460 Comparison

The GeForce GTX 460 and Intel UHD Graphics 750 occupy similar positions in the overall GPU hierarchy, but their benchmark results reveal distinct performance characteristics. The GTX 460 holds a clear lead in raw compute workloads, while the UHD 750 offers a feature set that the older card cannot match. The data shows that the GTX 460 wins the only direct head-to-head comparison, yet the integrated Intel part counters with API support and efficiency that make it a more modern choice for specific use cases.

Head-to-Head Benchmarks

The sole direct comparison available in the data is the Geekbench OpenCL test, and the GTX 460 takes it decisively. The NVIDIA card scores 7,925 points against the UHD 750’s 6,743, which translates to a 17.5% advantage. This is a significant gap in a compute-oriented workload, indicating that the Fermi-based card is substantially stronger at general-purpose GPU tasks like OpenCL acceleration. The UHD 750’s 6,743 score places it within 0.1% of the AMD Radeon HD 8850M, while the GTX 460’s 7,925 score sits 0.2% above the NVIDIA Quadro K4100M. In practical terms, the GTX 460 outperforms the UHD 750 by a margin that is roughly equivalent to the difference between two adjacent tiers of rival mobile GPUs.

Looking at the broader benchmark landscape, the GTX 460’s average benchmark score is 7,925, while the UHD 750’s average is 7,441. That 484-point gap (about 6.5%) is smaller than the OpenCL delta because the Intel part also has a Geekbench Vulkan score of 8,138, which is higher than the GTX 460’s OpenCL result. However, the UHD 750’s Vulkan score cannot be directly compared to the GTX 460, since the NVIDIA card has no Vulkan benchmark in the data. The GTX 460’s percentile rank among all GPUs is 41, marginally above the UHD 750’s 40, confirming that despite the age difference, the discrete card holds a slight edge in overall standing.

The rival comparisons reinforce this picture. The GTX 460 is 1.4% behind the NVIDIA Quadro P5000 and 1.6% behind the GeForce GTX 650 Ti, while the UHD 750 is 0.4% behind the GeForce GTX 1650 and 1.4% behind the Intel Arc A310. Notably, the UHD 750 trails the GTX 1650 by a smaller margin than the GTX 460 trails the GTX 650 Ti, suggesting that the integrated part is closer to its nearest competitors than the older discrete card is to its own peers.

Where Each One Wins

The GTX 460 wins in raw compute throughput. Its OpenCL score of 7,925 is 17.5% higher than the UHD 750’s, which makes it the better choice for applications that rely on OpenCL acceleration, such as certain video encoding, physics simulation, and scientific workloads. The card’s FP32 performance of 907.2 GFLOPS versus the UHD 750’s 665.6 GFLOPS further underscores this advantage, with the NVIDIA part delivering 36% more single-precision compute power. Its texture rate of 37.80 GTexel/s is also 82% higher than the Intel part’s 20.80 GTexel/s, which benefits texture-heavy tasks.

The UHD 750 wins in API compatibility and modern feature support. It supports DirectX 12 (12_1), whereas the GTX 460 only reaches DirectX 12 (11_0). The Intel part also supports Vulkan 1.4, a capability the GTX 460 lacks entirely. This means the UHD 750 can run newer games and applications that require these APIs, even if its raw performance is lower. The UHD 750’s Vulkan score of 8,138 demonstrates it is capable of strong performance in that API, exceeding the GTX 460’s OpenCL score. Additionally, the Intel part has a much higher pixel rate at 10.40 GPixel/s versus 9.450 GPixel/s, which can help in fill-rate-bound scenarios, though the difference is modest.

For gaming, the UHD 750’s DirectX 12_1 and Vulkan support make it the more future-proof option. Older titles that rely on DirectX 11 or OpenGL will run on both cards, but newer releases that mandate DirectX 12_1 or Vulkan will only run on the Intel part. The GTX 460’s higher raw compute does it no good if the software refuses to launch.

Architecture Differences

The two GPUs come from different eras and entirely different design philosophies. The GTX 460 is built on NVIDIA’s Fermi architecture using a 40 nm process at TSMC, with a die size of 332 mm² and 1,950 million transistors. This yields a transistor density of 5.9 million per mm². The UHD 750 uses Intel’s Generation 12.1 architecture (Rocket Lake) on a 14 nm+++ process, with no transistor count or die size listed in the data. The process node difference is stark: 40 nm versus 14 nm+++, which explains the massive disparity in power consumption.

The GTX 460 has a TDP of 160 W and requires a dual-slot cooler with two 6-pin power connectors and a suggested 450 W power supply. The UHD 750 is an integrated graphics processor (IGP) with a TDP of just 15 W, drawing power from the system’s Ring Bus interface and requiring no dedicated connectors. This makes the Intel part viable for compact, low-power systems, while the GTX 460 demands a proper desktop PSU and case space.

Memory configuration also diverges completely. The GTX 460 features 768 MB of dedicated GDDR5 memory on a 192-bit bus, delivering 86.40 GB/s of bandwidth. The UHD 750 uses system shared memory, with its bandwidth listed as “System Dependent” and no fixed size or bus width. The GTX 460’s dedicated memory avoids contention with the CPU, but its 768 MB capacity is tiny by modern standards. The UHD 750’s shared memory can address far more capacity, but performance is tied to the host system’s RAM speed and configuration.

Shading resources differ as well. The GTX 460 has 336 shading units, 56 texture mapping units, and 24 ROPs. The UHD 750 has 256 shading units, 16 TMUs, and 8 ROPs. The GTX 460’s higher TMU and ROP counts contribute to its superior texture and pixel rates, while the UHD 750 compensates with a higher boost clock of 1300 MHz versus the GTX 460’s unspecified boost clock (its memory runs at 900 MHz, 3.6 Gbps effective). The UHD 750 also supports FP16 at 1,331.2 GFLOPS (2:1 ratio), whereas the GTX 460 has no FP16 capability listed.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 460 scores 7,925 in Geekbench OpenCL, which is 17.5% higher than the Intel UHD Graphics 750’s 6,743.

Q: Does the Intel UHD Graphics 750 support Vulkan?

A: Yes, the UHD 750 supports Vulkan 1.4 and has a Geekbench Vulkan score of 8,138. The GTX 460 has no Vulkan support listed.

Q: What is the power consumption difference between the two?

A: The GTX 460 has a TDP of 160 W and requires a dual-slot cooler with two 6-pin connectors, while the UHD 750 is an integrated GPU with a 15 W TDP and no power connectors.

Q: How much memory does each GPU have?

A: The GTX 460 has 768 MB of dedicated GDDR5 memory on a 192-bit bus with 86.40 GB/s bandwidth. The UHD 750 uses system shared memory with system-dependent bandwidth.

Q: Which GPU has higher DirectX support?

A: The UHD 750 supports DirectX 12 (12_1), while the GTX 460 only supports DirectX 12 (11_0).

Q: How do their average benchmark scores compare?

A: The GTX 460 has an average benchmark score of 7,925, and the UHD 750 has an average of 7,441, giving the GTX 460 a 6.5% lead.

Specification Differences

• Process Node: GTX 460 is 40 nm (TSMC); UHD 750 is 14 nm+++ (Intel).
• Transistors: GTX 460 has 1,950 million; UHD 750 has no listed transistor count.
• Die Size: GTX 460 is 332 mm²; UHD 750 has no listed die size.
• Memory Size: GTX 460 is 768 MB; UHD 750 is system shared.
• Memory Type: GTX 460 is GDDR5; UHD 750 is system shared.
• Memory Bus: GTX 460 is 192-bit; UHD 750 is system shared.
• Memory Bandwidth: GTX 460 is 86.40 GB/s; UHD 750 is system dependent.
• Shading Units: GTX 460 has 336; UHD 750 has 256.
• TMUs: GTX 460 has 56; UHD 750 has 16.
• ROPs: GTX 460 has 24; UHD 750 has 8.
• Boost Clock: UHD 750 has 1300 MHz; GTX 460 has none listed.
• FP32 Performance: GTX 460 is 907.2 GFLOPS; UHD 750 is 665.6 GFLOPS.
• FP16 Performance: UHD 750 is 1,331.2 GFLOPS (2:1); GTX 460 has none listed.
• Texture Rate: GTX 460 is 37.80 GTexel/s; UHD 750 is 20.80 GTexel/s.
• Pixel Rate: GTX 460 is 9.450 GPixel/s; UHD 750 is 10.40 GPixel/s.
• TDP: GTX 460 is 160 W; UHD 750 is 15 W.
• Slot Width: GTX 460 is dual-slot; UHD 750 is IGP.
• Power Connectors: GTX 460 has 2x 6-pin; UHD 750 has none.
• Suggested PSU: GTX 460 is 450 W; UHD 750 has none.
• Bus Interface: GTX 460 is PCIe 2.0 x16; UHD 750 is Ring Bus.
• Display Outputs: GTX 460 is 2x DVI, 1x mini-HDMI 1.3a; UHD 750 is motherboard dependent.
• DirectX: GTX 460 is 12 (11_0); UHD 750 is 12 (12_1).
• Vulkan: UHD 750 supports 1.4; GTX 460 has no support listed.
• Release Date: GTX 460 is 2010-07-11; UHD 750 is 2021-03-29.
• Launch MSRP: GTX 460 is 199 USD; UHD 750 has none listed.

The Verdict

Pick the NVIDIA GeForce GTX 460 if your priority is raw compute performance in OpenCL workloads. The data shows it is 17.5% faster than the UHD 750 in Geekbench OpenCL, has 36% higher FP32 throughput, and delivers 82% higher texture rate. It is the better choice for GPU-accelerated tasks that can use its dedicated 768 MB GDDR5 memory and 86.40 GB/s bandwidth. The GTX 460 also holds a slightly higher percentile rank (41 vs 40) and a higher average benchmark score (7,925 vs 7,441). Its launch MSRP was 199 USD, and it requires a 450 W PSU and dual-slot space.

Pick the Intel UHD Graphics 750 if you need modern API support or operate in a low-power, integrated environment. It is the only one of the two that supports Vulkan 1.4 and DirectX 12_1, making it compatible with newer software that the GTX 460 cannot run. Its 15 W TDP and lack of power connectors make it suitable for compact systems, and its 1300 MHz boost clock and 10.40 GPixel/s pixel rate are competitive. The UHD 750’s Vulkan score of 8,138 exceeds the GTX 460’s OpenCL score, showing it can perform well in modern APIs. It also supports FP16 at 1,331.2 GFLOPS, a capability entirely absent from the older NVIDIA card.

The verdict is clear: for legacy compute acceleration, the GTX 460 wins. For modern software compatibility and efficiency, the UHD 750 is the only viable option. The 11-year release gap between the two (2010 vs 2021) makes them complementary rather than direct competitors, with each excelling in its intended domain.