Intel Arc A750 vs NVIDIA GeForce GTX 780 Ti Comparison

Where Each One Wins

The benchmark data splits cleanly along compute API lines. The Intel Arc A750 wins every recorded head-to-head comparison, and it does so by a wide margin. In the Geekbench OpenCL test, the Arc A750 scores 98,554 against the GTX 780 Ti’s 27,326, a 72.3% advantage. In the Geekbench Vulkan test, the Arc A750 scores 85,631 against 27,238, a 68.2% advantage. There is no recorded test in which the GTX 780 Ti comes out ahead.

Looking at the broader database picture, the GTX 780 Ti actually holds a higher overall percentile rank. It sits at the 70th percentile among all GPUs, while the Arc A750 sits at the 66th percentile. That seems contradictory at first, but the average benchmark scores explain the nuance. The GTX 780 Ti’s average score across all recorded tests is 24,236, while the Arc A750’s average is 20,582. The Arc A750 wins the compute-heavy workloads, but the GTX 780 Ti has a higher average because its benchmark profile is narrower and more consistent.

The Arc A750’s wins are concentrated in modern, low-level APIs. Its Vulkan score of 85,631 is more than three times the GTX 780 Ti’s 27,238. Its OpenCL score of 98,554 is more than 3.5 times the GTX 780 Ti’s 27,326. These are exactly the kinds of workloads that scale with shading unit count, raw FP32 throughput, and memory bandwidth, all areas where the Arc A750 has a structural advantage.

The GTX 780 Ti’s strength is not in any single head-to-head win, but in its overall consistency. Its three recorded benchmark scores, 18,144 in Geekbench Metal, 27,326 in OpenCL, and 27,238 in Vulkan, are tightly clustered. The Arc A750’s scores vary far more across its wider benchmark suite, from a low of 65 in PassMark DirectX 10 to a high of 98,554 in OpenCL. The GTX 780 Ti does not win any specific comparison, but it also does not have the dramatic swings that drag down the Arc A750’s average.

FAQ

Q: Which GPU wins in Geekbench OpenCL?

A: The Intel Arc A750 wins decisively with a score of 98,554 versus the GTX 780 Ti’s 27,326, a 72.3% margin.

Q: Which GPU wins in Geekbench Vulkan?

A: The Intel Arc A750 wins with 85,631 against the GTX 780 Ti’s 27,238, a 68.2% margin.

Q: Which GPU has the higher overall percentile rank?

A: The GTX 780 Ti sits at the 70th percentile among all GPUs, while the Intel Arc A750 sits at the 66th percentile.

Q: How do the average benchmark scores compare?

A: The GTX 780 Ti has an average benchmark score of 24,236, which is higher than the Arc A750’s average of 20,582.

Q: What is the closest rival to the GTX 780 Ti?

A: The NVIDIA GeForce GTX 1630 is the closest, with an average score of 24,277, just 0.2% above the GTX 780 Ti’s 24,236.

Q: What is the closest rival to the Intel Arc A750?

A: The Intel Arc B570 is the closest, with an average score of 20,556, just 0.1% below the Arc A750’s 20,582.

Head-to-Head Benchmarks

The recorded head-to-head data contains exactly two comparisons, and both go to the Intel Arc A750. The first is Geekbench OpenCL. The Arc A750 produces 98,554 points, the GTX 780 Ti produces 27,326 points. The delta is 72.3% in favor of Intel. That is not a marginal win; it is a near quadrupling of the score. OpenCL is a general-purpose compute API, and the Arc A750’s 17.20 TFLOPS of FP32 throughput against the GTX 780 Ti’s 5.345 TFLOPS explains the scale of the gap.

The second comparison is Geekbench Vulkan. The Arc A750 scores 85,631, the GTX 780 Ti scores 27,238. The delta is 68.2% in favor of Intel. Vulkan is a low-overhead graphics and compute API, and the Arc A750’s newer architecture, Xe-HPG, is designed to handle this workload efficiently. The GTX 780 Ti’s Kepler architecture predates Vulkan’s mainstream adoption, and its 1.2.175 Vulkan support is older than the Arc A750’s 1.4.

The GTX 780 Ti has no wins in the head-to-head table. Its wins, such as they are, come from the aggregate database metrics. Its average score of 24,236 beats the Arc A750’s 20,582 by roughly 17.8%. Its percentile rank of 70 beats the Arc A750’s 66. These aggregate numbers reflect the fact that the GTX 780 Ti was benchmarked in fewer, more favorable tests, while the Arc A750’s wider test suite includes very low DirectX 10 and DirectX 9 scores that pull its average down.

The Arc A750’s PassMark scores illustrate this unevenness. Its DirectX 9 score is 181, DirectX 10 is 65, DirectX 11 is 72, and DirectX 12 is 70. Its PassMark G3D score is 12,534, and its GPU compute score is 5,368. These are mixed results, but the modern API scores, OpenCL and Vulkan, are the ones that matter in the head-to-head table, and there the Arc A750 dominates.

Specification Differences

The two cards differ in nearly every measurable specification. Memory capacity: the GTX 780 Ti has 3 GB of GDDR5, the Arc A750 has 8 GB of GDDR6. Memory bus width: 384 bit versus 256 bit. Memory bandwidth: 336.6 GB/s versus 512.0 GB/s. The Arc A750 has less physical bus width but more than makes up for it with faster memory and a wider effective transfer rate.

Clock speeds: the GTX 780 Ti runs at 875 MHz base and 928 MHz boost. The Arc A750 runs at 2050 MHz base and 2400 MHz boost. That is more than double the base clock and more than double the boost clock. Memory clocks: the GTX 780 Ti runs at 1753 MHz, 7 Gbps effective. The Arc A750 runs at 2000 MHz, 16 Gbps effective.

Shading units: 2880 on the GTX 780 Ti versus 3584 on the Arc A750. Texture mapping units: 240 versus 224, a rare category where the GTX 780 Ti has more. Raster output units: 48 versus 112, a massive difference in favor of Intel. The Arc A750 also has 28 ray tracing cores, while the GTX 780 Ti has none.

Compute throughput: the GTX 780 Ti delivers 5.345 TFLOPS of FP32, the Arc A750 delivers 17.20 TFLOPS, more than three times as much. The Arc A750 also delivers 34.41 TFLOPS of FP16 with a 2:1 ratio, a capability the GTX 780 Ti does not record. Pixel rate: 55.68 GPixel/s versus 268.8 GPixel/s. Texture rate: 222.7 GTexel/s versus 537.6 GTexel/s.

Power and physical specs: the GTX 780 Ti has a TDP of 250 W and a suggested PSU of 600 W. The Arc A750 has a TDP of 225 W and a suggested PSU of 550 W. Both are dual-slot cards with 1x 6-pin and 1x 8-pin power connectors. The GTX 780 Ti is 267 mm long, 111 mm tall, and 38 mm wide. The Arc A750 has no recorded dimensions.

Interface and outputs: the GTX 780 Ti uses PCIe 3.0 x16, the Arc A750 uses PCIe 4.0 x16. Display outputs: the GTX 780 Ti has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The Arc A750 has 1x HDMI 2.1 and 3x DisplayPort 2.0.

Architecture Differences

The GTX 780 Ti is built on NVIDIA’s Kepler architecture, specifically the GK110B chip, and belongs to the GeForce 700 generation. It is fabricated on a 28 nm process at TSMC, with 7,080 million transistors on a 561 mm² die. That works out to a transistor density of 12.6 million per square millimeter. Kepler is a mature, fixed-function design from 2013. It supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.175. It has no ray tracing cores and no tensor cores. Its production status is end-of-life, and its predecessor is GeForce 600, its successor GeForce 900.

The Arc A750 is built on Intel’s Xe-HPG architecture, specifically the DG2-512 chip, and belongs to the Alchemist generation, Arc 7. It is fabricated on a 6 nm process at TSMC, with 21,700 million transistors on a 406 mm² die. That works out to a transistor density of 53.4 million per square millimeter, more than four times the density of the Kepler chip. The Arc A750 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. It has 28 ray tracing cores. Its production status is end-of-life, and its predecessor is Xe Graphics, its successor Battlemage.

The architectural gap is enormous. The Kepler chip is a 28 nm design from 2013 with no ray tracing support and a limited DirectX 12 feature level. The Xe-HPG chip is a 6 nm design from 2022 with full DirectX 12 Ultimate support, hardware ray tracing, and a much higher transistor density. The Arc A750’s 17.20 TFLOPS of FP32 is more than triple the GTX 780 Ti’s 5.345 TFLOPS, and its 537.6 GTexel/s texture rate is more than double the GTX 780 Ti’s 222.7 GTexel/s.

The memory architectures also differ fundamentally. The GTX 780 Ti uses 3 GB of GDDR5 on a 384 bit bus. The Arc A750 uses 8 GB of GDDR6 on a 256 bit bus. The Arc A750’s 512.0 GB/s bandwidth is 52% higher than the GTX 780 Ti’s 336.6 GB/s. That bandwidth advantage matters for the OpenCL and Vulkan workloads where the Arc A750 dominates.

The Verdict

The data points to a clear split between compute capability and aggregate consistency. For anyone running OpenCL or Vulkan workloads, the Intel Arc A750 is the obvious choice. It beats the GTX 780 Ti by 72.3% in OpenCL and 68.2% in Vulkan. Those are not close margins, and they reflect the Arc A750’s fundamental architectural advantages: more shading units, more than triple the FP32 throughput, more than triple the pixel rate, and 52% more memory bandwidth.

For anyone looking at the aggregate database picture, the GTX 780 Ti holds its own. Its average benchmark score of 24,236 exceeds the Arc A750’s 20,582, and its 70th percentile rank beats the Arc A750’s 66th. The GTX 780 Ti’s nearest rivals, the GTX 1630 at 24,277 and the RX 6600 XT at 24,442, bracket it within 1%. The Arc A750’s nearest rivals, the Arc B570 at 20,556 and the RTX 3070 Mobile at 20,534, are similarly close.

The GTX 780 Ti is the more consistent card in the database, but the Arc A750 is the more capable card in the two tests that actually pit them against each other. That is the verdict the recorded data supports. If the workload is modern compute or ray tracing capable graphics, the Arc A750 wins outright. If the metric is overall average score across all recorded benchmarks, the GTX 780 Ti edges ahead. The Arc A750 is the stronger performer in the head-to-head record, while the GTX 780 Ti is the steadier presence in the broader database.