NVIDIA GeForce GTX 460 vs NVIDIA GeForce GTX 960 Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark in the database is Geekbench OpenCL, and the result is not close. The GTX 960 scores 18,925 points while the GTX 460 manages 7,925 points. That is a delta of 138.8% in favor of the GTX 960, meaning the newer card delivers more than double the compute throughput in this OpenCL workload. For context, the GTX 960's average benchmark score across all recorded tests is 9,273, while the GTX 460's average is 7,925, a gap of roughly 17% even when accounting for the GTX 960's other test results.

Looking at the broader database, the GTX 960 sits at the 45th percentile among all GPUs, while the GTX 460 is at the 41st percentile. That five-point percentile spread understates the raw performance difference, because the GTX 960 has additional benchmark data points (3DMark Steel Nomad DX12, Geekbench Metal, and Geekbench Vulkan) that the GTX 460 lacks. In those tests, the GTX 960 records 162 in 3DMark Steel Nomad DX12, 8,773 in Geekbench Metal, and 9,231 in Geekbench Vulkan, all of which are respectable scores for a card of its class.

The nearest rivals for each card further illustrate the gap. The GTX 960's closest competitor is the GTX 465, which scores 9,294 on average, a delta of -0.2% relative to the GTX 960. The GTX 460's nearest rival is the Quadro K4100M, which scores 7,906, a delta of +0.2% relative to the GTX 460. In other words, the GTX 960 competes in a performance tier roughly 17% higher than the GTX 460's tier, and its closest rivals reflect that positioning.

Where Each One Wins

The GTX 960 wins the only head-to-head benchmark outright, but its advantage extends beyond that single test. The database shows the GTX 960 with a win count of 1 in head-to-head comparisons versus 0 for the GTX 460, which is a direct result of the OpenCL result. However, the GTX 960 also demonstrates versatility across multiple API workloads: it posts a 3DMark Steel Nomad DX12 score of 162, a Geekbench Metal score of 8,773, and a Geekbench Vulkan score of 9,231. These numbers indicate that the GTX 960 can handle modern graphics APIs with reasonable efficiency, whereas the GTX 460 has no recorded results in those tests.

For the GTX 460, its sole benchmark result is the OpenCL score of 7,925, which places it below the GTX 960's OpenCL result by a massive margin. The GTX 460 does not have any recorded DirectX 12, Metal, or Vulkan scores, so its capabilities in those areas cannot be quantified from the database. What the data does show is that the GTX 460's average score of 7,925 is lower than every nearest rival of the GTX 960, including the AMD Radeon R7 M380 (9,313) and the AMD Radeon Vega 8 (9,221). The GTX 460 only edges out its own nearest rivals, and even then by slim margins: it is 0.2% ahead of the Quadro K4100M but 1.4% behind both the Quadro P5000 and the GTX 880M, and 1.6% behind the GTX 650 Ti.

In practical terms, the GTX 960 is the clear winner for any workload that leverages OpenCL compute, and its additional benchmark results suggest it can handle a wider range of tasks, from DX12 gaming to Vulkan-based applications. The GTX 460, by contrast, appears limited to older compute workloads, and its 41st percentile ranking indicates it struggles against even mid-range modern GPUs.

Architecture Differences

The architectural gap between these two cards is substantial and explains most of the performance delta. The GTX 960 uses the GM206 chip built on Maxwell 2.0 architecture, while the GTX 460 uses the GF104 chip built on Fermi architecture. Maxwell 2.0 represents a significant evolution in NVIDIA's GPU design, focusing on improved power efficiency and higher instruction-level parallelism, whereas Fermi was an earlier architecture that prioritized raw compute throughput at the cost of efficiency.

The manufacturing process differs as well: the GTX 960 is fabricated on a 28 nm process at TSMC, while the GTX 460 uses a 40 nm process, also at TSMC. This process shrink allows the GTX 960 to pack 2,940 million transistors into a 228 mm² die, yielding a transistor density of 12.9M per mm². The GTX 460, with 1,950 million transistors on a 332 mm² die, achieves only 5.9M transistors per mm². In other words, the GTX 960 fits 50% more transistors into a die that is 31% smaller, which is a direct consequence of the more advanced process node.

The API support also diverges. The GTX 960 supports DirectX 12 with feature level 12_1, OpenGL 4.6, and Vulkan 1.4. The GTX 460 supports DirectX 12 with feature level 11_0 (a lower tier), OpenGL 4.6, but has no Vulkan support listed. This means the GTX 960 can take advantage of newer rendering techniques and compute APIs that the GTX 460 simply cannot access, which is a critical differentiator for modern games and applications.

Memory architecture also reflects the generational leap. The GTX 960 uses a 128-bit memory bus with GDDR5 running at 7 Gbps effective, while the GTX 460 uses a 192-bit bus with GDDR5 at 3.6 Gbps effective. Interestingly, the GTX 460 has a wider bus, but the GTX 960's much higher memory clock speed results in higher bandwidth: 112.2 GB/s versus 86.40 GB/s. That is a 30% bandwidth advantage for the GTX 960, which is notable given the narrower bus.

Specification Differences

The specification tables reveal several clear differences between the two cards, beyond the architectural changes already discussed. The GTX 960 has 1,024 shading units, 64 texture mapping units (TMUs), and 32 raster operation units (ROPs). The GTX 460 has 336 shading units, 56 TMUs, and 24 ROPs. That means the GTX 960 has over three times the shading units, 14% more TMUs, and 33% more ROPs. These raw resource counts directly translate to higher pixel and texture throughput: the GTX 960 achieves 37.70 GPixel/s and 75.39 GTexel/s, while the GTX 460 manages 9.450 GPixel/s and 37.80 GTexel/s. The GTX 960 is roughly 4x faster in pixel fill rate and 2x faster in texture fill rate.

Compute performance follows a similar pattern. The GTX 960 delivers 2.413 TFLOPS of FP32 throughput, while the GTX 460 delivers 907.2 GFLOPS. That is a 2.66x advantage for the GTX 960, which is consistent with the OpenCL benchmark results. Neither card has recorded FP16 performance, and neither has ray tracing or tensor cores.

Power and cooling requirements differ significantly. The GTX 960 has a TDP of 120 W, requires a single 6-pin power connector, and a suggested PSU of 300 W. The GTX 460 has a TDP of 160 W, requires two 6-pin connectors, and a suggested PSU of 450 W. The GTX 960 delivers substantially more performance while consuming 25% less power, which reflects the efficiency gains of Maxwell 2.0 over Fermi.

Physical dimensions also differ: the GTX 960 is 241 mm (9.5 inches) long, while the GTX 460 is 210 mm (8.3 inches) long. Both are dual-slot cards. The GTX 960 offers more display outputs, including 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2, while the GTX 460 offers 2x DVI and 1x mini-HDMI 1.3a. The bus interface also differs: the GTX 960 uses PCIe 3.0 x16, while the GTX 460 uses PCIe 2.0 x16.

The GTX 960 has 2 GB of memory, while the GTX 460 has only 768 MB. That memory capacity difference is significant for modern workloads, as 768 MB is insufficient for many contemporary games and applications. The GTX 960 also has a higher launch MSRP of 199 USD, while the GTX 460 also launched at 199 USD, though the GTX 460's launch MSRP of 199 USD is the same value.

FAQ

Q: Which card has a higher average benchmark score?

A: The GTX 960 has an average benchmark score of 9,273, while the GTX 460 has an average of 7,925. That is a 17% difference in favor of the GTX 960.

Q: Does the GTX 960 support Vulkan?

A: Yes, the GTX 960 supports Vulkan 1.4. The GTX 460 has no Vulkan support listed in the database.

Q: How much memory does each card have?

A: The GTX 960 has 2 GB of GDDR5 memory, while the GTX 460 has 768 MB of GDDR5 memory. The GTX 960 also has higher memory bandwidth at 112.2 GB/s versus 86.40 GB/s.

Q: What is the TDP difference?

A: The GTX 960 has a TDP of 120 W, while the GTX 460 has a TDP of 160 W. The GTX 960 also requires only one 6-pin power connector and a 300 W PSU, compared to two 6-pin connectors and a 450 W PSU for the GTX 460.

Q: Which card has better DirectX 12 support?

A: The GTX 960 supports DirectX 12 with feature level 12_1, while the GTX 460 supports DirectX 12 with feature level 11_0. The GTX 960's higher feature level enables more advanced rendering features.

Q: How does the GTX 960 compare to the GTX 460 in OpenCL?

A: In Geekbench OpenCL, the GTX 960 scores 18,925, which is 138.8% higher than the GTX 460's score of 7,925. This is the only head-to-head benchmark available in the database.

The Verdict

The data is unambiguous: the GTX 960 is the superior card in every measurable dimension. It wins the only head-to-head benchmark by 138.8%, has a higher average score (9,273 versus 7,925), sits at a higher percentile (45th versus 41st), and offers more shading units, higher fill rates, more memory, and better API support. The GTX 960 also consumes less power (120 W versus 160 W) and requires a smaller PSU (300 W versus 450 W), making it an easier fit for most systems.

For a user choosing between these two cards today, the GTX 960 is the only sensible option if the workload involves anything modern: DirectX 12 gaming, Vulkan applications, or compute-heavy tasks like OpenCL. The GTX 460's 768 MB of memory and lack of Vulkan support make it ill-suited for contemporary software. However, if the use case is strictly legacy applications that predate 2010 and rely on OpenGL 4.6, the GTX 460 can still function, albeit with lower performance.

The GTX 960's nearest rivals include the GTX 465 (0.2% slower) and the GTX 850M (0.3% slower), which places it in a competitive mid-range tier. The GTX 460's nearest rivals are the Quadro K4100M (0.2% faster) and the Quadro P5000 (1.4% faster), which puts it at the very bottom of modern GPU performance. The verdict is straightforward: pick the GTX 960 for any serious use, and only consider the GTX 460 for historical or compatibility reasons.