NVIDIA GeForce GTX 460 vs NVIDIA GeForce GTX 675MX Comparison

The NVIDIA GeForce GTX 675MX and the NVIDIA GeForce GTX 460 represent two distinct generations of NVIDIA mobile and desktop graphics, respectively. The data shows a clear performance hierarchy, with the newer Kepler-based mobile part taking a decisive lead over the older Fermi-based desktop card in the available benchmarks.

Head-to-Head Benchmarks

The single available head-to-head comparison is a Geekbench OpenCL test, and the result is a substantial victory for the GTX 675MX. The GTX 675MX scores 10,723 points, while the GTX 460 manages 7,925 points. This translates to a delta of 35.3%, meaning the GTX 675MX is more than a third faster than the GTX 460 in this compute-oriented workload. This is a significant margin that underscores the generational leap in compute capability.

Looking at the broader benchmark context, the GTX 675MX’s average benchmark score is 8,427, which is 6.3% higher than the GTX 460’s average of 7,925. While the head-to-head OpenCL test shows a much larger gap, the average scores suggest that in a wider variety of workloads, the difference might be less pronounced, though still firmly in favor of the GTX 675MX. The GTX 675MX also has a higher percentile ranking among all GPUs, sitting at the 43rd percentile compared to the GTX 460’s 41st percentile.

In terms of nearest rivals, the GTX 675MX’s average score of 8,427 is placed within a tight cluster. It is essentially tied with the AMD Radeon 880M, which scores 8,436, a delta of -0.1%. It is also nearly identical to the NVIDIA GeForce MX330 (8,458, -0.4%) and the AMD Radeon HD 8870M (8,462, -0.4%). Its closest competitor that it beats is the AMD Radeon R9 M375X, which scores 8,325, a delta of 1.2% in favor of the GTX 675MX. This shows that the GTX 675MX, despite its age, is competitive with much more recent entry-level and integrated-class solutions.

The GTX 460’s average score of 7,925 places it near a different set of rivals. It is slightly ahead of the NVIDIA Quadro K4100M, which scores 7,906, a delta of 0.2%. However, it trails the NVIDIA Quadro P5000 (8,039, -1.4%), the NVIDIA GeForce GTX 880M (8,040, -1.4%), and the NVIDIA GeForce GTX 650 Ti (8,053, -1.6%). This indicates that the GTX 460’s performance level is comparable to professional mobile GPUs from a later generation, but it is clearly outclassed by even mid-range mobile parts from subsequent generations.

The data shows that the GTX 675MX wins the only direct head-to-head benchmark, and it also holds a higher average score and percentile ranking. The margin of victory in the direct comparison is substantial, suggesting that for compute-heavy tasks, the GTX 675MX is the far superior option.

The Verdict

From the data, the choice is straightforward for compute performance: the NVIDIA GeForce GTX 675MX is the clear winner. It delivers a 35.3% higher score in the Geekbench OpenCL test and maintains a higher average benchmark score across the board. Users who prioritize raw computational throughput, such as for GPGPU tasks or certain types of rendering workloads, should unequivocally choose the GTX 675MX.

The GTX 460, while it was a capable card in its era, is simply outmatched here. Its performance, as reflected by its average score and percentile rank, places it below the GTX 675MX and even below several of the GTX 675MX’s rivals. The GTX 460’s only potential advantage lies in its desktop form factor and historical context, but from a pure performance-per-benchmark standpoint, the data does not support its selection over the GTX 675MX.

For someone who already owns a GTX 460, the benchmark data suggests that upgrading to a GTX 675MX-class part would provide a very significant performance uplift. For someone choosing between these two specific cards today, the GTX 675MX is the only logical choice based on the available evidence. The GTX 675MX’s higher percentile ranking (43 vs. 41) reinforces its position as the more capable GPU in the grand scheme of all graphics cards.

Architecture Differences

The two GPUs are built on fundamentally different architectures and manufacturing processes. The GTX 675MX is based on the GK104 chip and uses NVIDIA’s Kepler architecture, fabricated on a 28 nm process at TSMC. In contrast, the GTX 460 uses the GF104 chip and the older Fermi architecture, built on a larger 40 nm process, also at TSMC. This process shrink is a key factor in the performance and efficiency differences.

The GTX 675MX packs 3,540 million transistors into a die size of 294 mm², resulting in a transistor density of 12.0 million per mm². The GTX 460, on the other hand, has 1,950 million transistors on a larger 332 mm² die, giving it a much lower density of 5.9 million per mm². This highlights the significant advancement in manufacturing technology between the two generations.

The core configurations are also drastically different. The GTX 675MX features 960 shading units, 80 texture mapping units (TMUs), and 32 render output units (ROPs). The GTX 460 has only 336 shading units, 56 TMUs, and 24 ROPs. This difference in core count directly contributes to the GTX 675MX’s higher theoretical pixel rate of 13.08 GPixel/s and texture rate of 52.32 GTexel/s, compared to the GTX 460's 9.450 GPixel/s and 37.80 GTexel/s. The GTX 675MX also has a significantly higher FP32 performance rating at 1,255.7 GFLOPS versus the GTX 460's 907.2 GFLOPS.

Memory configurations differ as well. The GTX 675MX comes with 2 GB of GDDR5 memory on a 256-bit bus, providing a bandwidth of 115.2 GB/s. The GTX 460 has a smaller 768 MB of GDDR5 memory on a 192-bit bus, yielding a lower bandwidth of 86.40 GB/s. Both have the same effective memory clock of 3.6 Gbps.

Power and physical characteristics also diverge. The GTX 675MX is a mobile MXM module with a TDP of 100 W and no power connectors, as it relies on the host laptop for power. The GTX 460 is a dual-slot desktop card with a 160 W TDP, requiring two 6-pin power connectors and a suggested 450 W power supply. The GTX 460 has a length of 210 mm. The GTX 675MX uses an MXM-B (3.0) bus interface, while the GTX 460 uses the older PCIe 2.0 x16 interface. In terms of API support, both cards support DirectX 12 (11_0) and OpenGL 4.6, but only the GTX 675MX has Vulkan support (version 1.2.175).

FAQ

Q: Which GPU is faster in the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 675MX is significantly faster, scoring 10,723 compared to the GTX 460's 7,925, a 35.3% difference.

Q: What is the average benchmark score for each card?

A: The GTX 675MX has an average benchmark score of 8,427, while the GTX 460 has an average score of 7,925.

Q: How does the memory size differ between the two cards?

A: The GTX 675MX has 2 GB of GDDR5 memory, while the GTX 460 has 768 MB of GDDR5 memory.

Q: What are the TDP ratings for these two cards?

A: The GTX 675MX has a TDP of 100 W, while the GTX 460 has a higher TDP of 160 W.

Q: What is the difference in their transistor counts?

A: The GTX 675MX uses 3,540 million transistors, whereas the GTX 460 uses 1,950 million transistors.

Q: Which card has a higher pixel fill rate?

A: The GTX 675MX has a higher pixel rate of 13.08 GPixel/s, compared to the GTX 460's 9.450 GPixel/s.

Where Each One Wins

Based on the benchmark data, the NVIDIA GeForce GTX 675MX wins in all measured aspects of performance. It has a higher score in the direct OpenCL comparison, a higher average benchmark score, and a higher percentile ranking among all GPUs. The GTX 675MX is the undisputed winner for compute-intensive tasks like OpenCL workloads.

The GTX 460 has no benchmark wins in the provided data. Its performance, while respectable for its generation, is consistently lower than that of the GTX 675MX. The data shows that the GTX 460 sits at a performance level comparable to later professional mobile GPUs like the Quadro K4100M, but it is not competitive with the GTX 675MX.

The GTX 675MX’s victories are not just marginal; they are decisive. The 35.3% lead in the head-to-head OpenCL test indicates a massive advantage in parallel processing capabilities. This advantage is further supported by its superior theoretical specifications, including higher pixel rate, texture rate, and FP32 performance. The GTX 675MX is the clear winner in every scenario where performance is the primary criterion.

The GTX 460’s only potential realm of superiority would be in its desktop-specific attributes, such as its dual-slot form factor and standard display outputs, but these are not performance metrics and do not appear in the benchmark data. From the perspective of raw performance, the GTX 675MX wins across the board.