NVIDIA GeForce GTX 650 Ti Boost vs NVIDIA GeForce GTX 760 Comparison

NVIDIA GeForce GTX 760 vs NVIDIA GeForce GTX 650 Ti Boost: a comparison between two Kepler-based cards from adjacent generations. The database shows a clear split in their benchmark profiles: the GTX 760 dominates in compute-oriented workloads while the GTX 650 Ti Boost holds a surprising edge in one specific API test. This analysis walks through the recorded data to determine where each card excels, what architectural choices drive those results, and which card is the better pick for different use cases.

Where Each One Wins

The benchmark data splits the two cards cleanly along workload lines. The GTX 760 takes the majority of the wins, securing victory in two of the three recorded tests. Its strongest performance comes in the Vulkan API test, where it scores 12,551 against the GTX 650 Ti Boost's 10,041, a 25% advantage. The OpenCL test tells a similar story, with the GTX 760 scoring 11,299 versus 9,302, a 21.5% lead. These two wins point to a card that handles modern, low-level API workloads and general-purpose compute tasks with substantially more headroom.

The GTX 650 Ti Boost's single win comes in the Metal API test, where it outscores the GTX 760 by 6.9%, recording 4,858 versus 4,524. This is a notable result because it shows that in at least one specific environment, the smaller card outperforms its larger sibling. The Metal result is an outlier relative to the other two tests, but it is significant for users whose primary applications rely on that API.

Looking at the aggregate data, the GTX 760's average benchmark score of 9,458 places it at the 46th percentile of all GPUs, while the GTX 650 Ti Boost's average of 8,067 places it at the 42nd percentile. The gap in average scores is roughly 17%, which aligns with the OpenCL and Vulkan results rather than the Metal result. For users choosing between these two, the GTX 760 is the stronger all-around performer, but the GTX 650 Ti Boost has a specific niche where it leads.

Architecture Differences

Both cards are built on NVIDIA's Kepler architecture and use the same 28 nm process node from TSMC. The similarities end there, as they use different physical chips. The GTX 760 is built on the GK104 chip, a larger and more complex design with 3,540 million transistors on a 294 mm² die. The GTX 650 Ti Boost uses the GK106 chip, which packs 2,540 million transistors onto a 221 mm² die. The transistor density is slightly higher on the GTX 760 at 12.0 million per mm², compared to 11.5 million per mm² for the GTX 650 Ti Boost.

The compute resources differ substantially. The GTX 760 features 1,152 shading units, 96 texture mapping units, and 32 raster output units. The GTX 650 Ti Boost is cut down significantly, with 768 shading units, 64 TMUs, and 24 ROPs. This means the GTX 760 has exactly 50% more shading units, 50% more TMUs, and 33% more ROPs than its smaller counterpart. These are the core resources that drive both gaming performance and compute throughput, so the GTX 760's structural advantage is significant.

The memory subsystems also diverge. The GTX 760 uses a 256-bit memory bus with a bandwidth of 192.3 GB/s, while the GTX 650 Ti Boost uses a 192-bit bus with a bandwidth of 144.2 GB/s. Both cards carry 2 GB of GDDR5 memory and run their memory at the same effective speed of 6 Gbps. The wider bus on the GTX 760 gives it a 33% bandwidth advantage, which becomes relevant in high-resolution textures and compute workloads that are memory-bandwidth sensitive.

Both cards share identical API support, including DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. They also share the same display outputs, bus interface (PCIe 3.0 x16), and physical dimensions of 241 mm in length. The power requirements differ, with the GTX 760 rated at 170 W TDP and the GTX 650 Ti Boost at 134 W, a difference that shows up in their power connector requirements.

Head-to-Head Benchmarks

The three recorded benchmark tests provide a detailed picture of where each card stands. Starting with Geekbench Metal, the GTX 650 Ti Boost wins with a score of 4,858 against the GTX 760's 4,524. The delta is -6.9% from the GTX 760's perspective, meaning the GTX 650 Ti Boost is about 7% faster in this specific test. This is a narrow but meaningful victory, and it suggests that the GTX 650 Ti Boost's architecture, despite having fewer compute units, is better tuned for the Metal API's execution model.

In Geekbench OpenCL, the results flip decisively. The GTX 760 scores 11,299, which is 21.5% higher than the GTX 650 Ti Boost's 9,302. This is a substantial margin that reflects the GTX 760's larger shading unit count and wider memory bus. OpenCL workloads tend to scale well with raw compute resources, and the data confirms that the GTX 760 has a clear advantage in this area.

The Geekbench Vulkan test shows the largest gap between the two cards. The GTX 760 scores 12,551 against the GTX 650 Ti Boost's 10,041, a 25% delta. Vulkan is a low-overhead API that rewards cards with higher raw throughput, and the GTX 760's superior specifications translate directly into a 25% performance lead. This is the most lopsided of the three tests and reinforces the GTX 760's status as the more capable card for modern graphics workloads.

Looking at the nearest rival data for context, the GTX 760's average score of 9,458 sits just 0.2% below the NVIDIA GeForce GTX TITAN BLACK's 9,474, making it nearly identical to that much higher-tier card in average performance. It also leads the AMD Radeon R7 M380 by 1.6% and the NVIDIA GeForce GTX 850M by 1.7%. The GTX 650 Ti Boost's average of 8,067 is essentially tied with the NVIDIA GRID K2 at 8,080 (a 0.2% gap), and it leads the GTX 650 Ti by 0.2%. These comparisons place the GTX 760 in a higher performance tier overall.

Specification Differences

The recorded data shows several key specification differences between the two cards. The GTX 760 uses the GK104 chip while the GTX 650 Ti Boost uses the GK106 chip. The GTX 760 has a transistor count of 3,540 million versus 2,540 million for the GTX 650 Ti Boost, and a die size of 294 mm² versus 221 mm². The GTX 760's transistor density is 12.0M per mm², slightly higher than the GTX 650 Ti Boost's 11.5M per mm².

The shading unit count is 1,152 for the GTX 760 and 768 for the GTX 650 Ti Boost. TMUs are 96 versus 64, and ROPs are 32 versus 24. The GTX 760's pixel rate is 24.77 GPixel/s versus 16.51 GPixel/s for the GTX 650 Ti Boost, a 50% difference. The texture rate is 99.07 GTexel/s versus 66.05 GTexel/s, also a 50% difference. FP32 performance is 2.378 TFLOPS versus 1.585 TFLOPS, a 50% gap that carries across all the compute-related specs.

Memory specifications also differ. The GTX 760 has a 256-bit bus width with 192.3 GB/s bandwidth, while the GTX 650 Ti Boost has a 192-bit bus with 144.2 GB/s bandwidth. Both have 2 GB of GDDR5 memory running at 6 Gbps effective. Power consumption is 170 W for the GTX 760 and 134 W for the GTX 650 Ti Boost, with the GTX 760 requiring 2x 6-pin power connectors and a 450 W suggested PSU, while the GTX 650 Ti Boost needs only 1x 6-pin and a 300 W suggested PSU.

The GTX 760 belongs to the GeForce 700 generation and was released on June 24, 2013, while the GTX 650 Ti Boost belongs to the GeForce 600 generation and was released earlier, on March 25, 2013. The GTX 760's predecessor is the GeForce 600 series and its successor is the GeForce 900 series. The GTX 650 Ti Boost's predecessor is the GeForce 500 series and its successor is the GeForce 700 series. Both cards are end-of-life products. The GTX 760 launched with an MSRP of 249 USD, while the GTX 650 Ti Boost launched with an MSRP of 169 USD.

FAQ

Q: Which card has a higher average benchmark score?

A: The GTX 760 has a significantly higher average score of 9,458, while the GTX 650 Ti Boost averages 8,067. The GTX 760 sits at the 46th percentile of all GPUs, and the GTX 650 Ti Boost sits at the 42nd percentile.

Q: Does the GTX 650 Ti Boost win any benchmark test?

A: Yes, it wins the Geekbench Metal test with a score of 4,858, beating the GTX 760's 4,524 by 6.9%. This is the only test where it comes out ahead.

Q: How much of an advantage does the GTX 760 have in the OpenCL test?

A: The GTX 760 scores 11,299 in Geekbench OpenCL, which is 21.5% higher than the GTX 650 Ti Boost's 9,302. This is a substantial margin that reflects the GTX 760's larger compute resource pool.

Q: What is the biggest performance gap between the two cards?

A: The largest gap is in the Geekbench Vulkan test, where the GTX 760 scores 12,551 versus 10,041 for the GTX 650 Ti Boost, a 25% difference.

Q: Do both cards use the same amount of memory?

A: Yes, both cards have 2 GB of GDDR5 memory, but the GTX 760 uses a 256-bit bus with 192.3 GB/s bandwidth, while the GTX 650 Ti Boost uses a 192-bit bus with 144.2 GB/s bandwidth.

Q: How do the power requirements compare?

A: The GTX 760 has a 170 W TDP and requires 2x 6-pin power connectors and a 450 W suggested PSU. The GTX 650 Ti Boost has a 134 W TDP, needs only 1x 6-pin power connector, and has a 300 W suggested PSU.

The Verdict

The benchmark data makes the choice between these two cards clear for most use cases. The GTX 760 wins two of the three recorded tests, with a 21.5% lead in OpenCL and a 25% lead in Vulkan. Its average benchmark score of 9,458 is 17% higher than the GTX 650 Ti Boost's 8,067, and it sits just 0.2% below the GTX TITAN BLACK in average performance. For users running compute workloads, modern games with Vulkan support, or any application that leverages OpenCL, the GTX 760 is the stronger pick.

The GTX 650 Ti Boost does have a specific niche. Its 6.9% win in Geekbench Metal means that for applications built on that API, it is the faster card. It also draws less power, with a 134 W TDP versus 170 W, and requires a less robust power supply. For users with a 300 W PSU or those whose primary workload is Metal-based, the GTX 650 Ti Boost is a defensible choice. However, the GTX 760's wider memory bus, higher compute throughput, and superior performance in two of three tests make it the better all-around card. The data indicates that the GTX 760 is the appropriate selection for general gaming and compute, while the GTX 650 Ti Boost is only preferable in the specific case of Metal-centric applications.