AMD Radeon RX 6800S vs Intel Arc A750 Comparison

Head-to-Head Benchmarks

The recorded data shows a clear split between these two GPUs depending on the workload. Across the ten shared benchmark tests, the AMD Radeon RX 6800S takes six wins while the Intel Arc A750 takes four, but the margins tell a more nuanced story than the raw win count.

The Intel Arc A750 delivers its largest victory in the 3DMark Steel Nomad DX12 test, scoring 2612 against the RX 6800S's 1689, a delta of 35.3% in Intel's favor. This is a substantial lead in a modern DirectX 12 workload and represents the single biggest performance gap in either direction. The Arc A750 also wins the Geekbench OpenCL test with 98554 versus 73202, a 25.7% advantage, and the Geekbench Vulkan test with 85631 versus 81272, a narrower 5.1% edge. In the Passmark DirectX 12 test, the Arc A750 wins by a slim 7.1% margin, scoring 70 against 65.

The AMD Radeon RX 6800S counters with equally decisive wins in several older DirectX tests. Its largest victory comes in Passmark DirectX 11, where it scores 139 against the Arc A750's 72, a commanding 93.1% advantage. In Passmark DirectX 10, the RX 6800S wins by 40%, scoring 91 versus 65. The Passmark G3D test also favors AMD, with the RX 6800S scoring 15908 against 12534, a 26.9% lead. The RX 6800S wins Passmark DirectX 9 by 10.5% (200 versus 181) and Passmark GPU Compute by 14.5% (6144 versus 5368). The Passmark G2D test is a perfect tie at 732 for both cards.

Looking at aggregate scores, the RX 6800S posts an average benchmark score of 24063, which is 17% higher than the Arc A750's 20582. The RX 6800S also sits at the 69th percentile among all GPUs, while the Arc A750 sits at the 66th percentile. The rival comparison data reinforces this positioning: the RX 6800S sits within 0.9% of cards like the GeForce RTX 2080 SUPER, GTX 780 Ti, and RX 9070, while the Arc A750 clusters with the Arc B570, RTX 3070 Mobile, R9 M390X, and Quadro M4000M, all within 0.5% of each other.

Architecture Differences

The two GPUs come from entirely different design philosophies and process technologies. The AMD Radeon RX 6800S uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated on a 7 nm TSMC process. The chip contains 11,060 million transistors on a 237 mm² die, yielding a transistor density of 46.7 million per square millimeter. The Intel Arc A750 uses the DG2-512 chip built on Xe-HPG architecture, fabricated on a 6 nm TSMC process. This chip is substantially larger, with 21,700 million transistors on a 406 mm² die, giving a density of 53.4 million per square millimeter.

The compute resources differ significantly. The RX 6800S has 2048 shading units, 128 texture mapping units, and 64 render output units, with 32 ray tracing cores. The Arc A750 has 3584 shading units, 224 TMUs, and 112 ROPs, with 28 ray tracing cores. Despite having fewer shading units, the RX 6800S still manages competitive performance in many tests, which points to architectural efficiency differences rather than raw unit counts.

Clock speeds also diverge. The RX 6800S runs at a base clock of 1800 MHz, a boost clock of 2100 MHz, and a game clock of 1975 MHz. The Arc A750 runs higher, with a base clock of 2050 MHz and a boost clock of 2400 MHz, but it does not list a game clock. Memory clocks are identical at 2000 MHz with 16 Gbps effective speed, and both cards have 8 GB of GDDR6 memory. However, the memory buses differ: the RX 6800S uses a 128 bit bus yielding 256.0 GB/s of bandwidth, while the Arc A750 uses a 256 bit bus yielding 512.0 GB/s, exactly double the bandwidth.

The compute throughput figures reflect these architectural differences. The RX 6800S delivers 8.602 TFLOPS of FP32 performance and 17.20 TFLOPS of FP16 (2:1 ratio). The Arc A750 delivers exactly 17.20 TFLOPS of FP32, which is double the AMD card, and 34.41 TFLOPS of FP16. Pixel rates differ as well: the RX 6800S achieves 134.4 GPixel/s while the Arc A750 achieves 268.8 GPixel/s, again double. Texture rates are 268.8 GTexel/s for AMD and 537.6 GTexel/s for Intel.

Power and form factor present a stark contrast. The RX 6800S has a TDP of 100 W, uses no power connectors, and is listed as an IGP (integrated graphics package) with a bus interface of PCIe 4.0 x8. The Arc A750 has a TDP of 225 W, requires one 6 pin and one 8 pin power connector, suggests a 550 W power supply, is a dual slot card, and uses PCIe 4.0 x16. The AMD card is portable device dependent for display outputs, while the Intel card offers 1x HDMI 2.1 and 3x DisplayPort 2.0.

Where Each One Wins

The benchmark data suggests that the AMD Radeon RX 6800S is the stronger choice for legacy DirectX workloads and general compute tasks. Its wins in Passmark DirectX 9, 10, and 11 are decisive, with the DirectX 11 margin being particularly large at 93.1%. The Passmark G3D win of 26.9% and the GPU Compute win of 14.5% further cement its position for older game titles and compute-oriented tasks. The RX 6800S also has a significant aggregate score advantage, posting 24063 average versus 20582 for Intel.

The Intel Arc A750 wins in modern DirectX 12 and compute API workloads. Its 35.3% lead in 3DMark Steel Nomad DX12 is the standout result, indicating that the Xe-HPG architecture scales better with the latest graphics API. The OpenCL win of 25.7% and the Vulkan win of 5.1% show that the Intel card handles modern compute interfaces well. The DirectX 12 Passmark win, though small at 7.1%, adds to the pattern of Intel strength in newer APIs.

The tie in Passmark G2D at 732 for both cards indicates that 2D graphics performance is identical, which is unsurprising given that both are modern GPUs with similar display capabilities.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 6800S has an average benchmark score of 24063, which is 17% higher than the Intel Arc A750's 20582.

Q: What is the largest single benchmark margin between the two cards?

A: The largest margin is in Passmark DirectX 11, where the RX 6800S scores 139 against the Arc A750's 72, a 93.1% advantage for AMD.

Q: Does the Intel Arc A750 win any tests by a large margin?

A: Yes, the Arc A750 wins 3DMark Steel Nomad DX12 by 35.3% and Geekbench OpenCL by 25.7%, both substantial leads.

Q: How do the memory bandwidths compare?

A: The Intel Arc A750 has a 256 bit memory bus with 512.0 GB/s bandwidth, while the AMD RX 6800S has a 128 bit bus with 256.0 GB/s bandwidth. Intel's bandwidth is exactly double.

Q: Are there any tests where the two cards perform identically?

A: Yes, the Passmark G2D test shows a tie at 732 for both cards.

Q: Which card has a higher percentile ranking among all GPUs?

A: The AMD Radeon RX 6800S sits at the 69th percentile, while the Intel Arc A750 sits at the 66th percentile.

The Verdict

The data presents a clear choice based on workload priorities. The AMD Radeon RX 6800S is the better all around performer, with a higher average benchmark score of 24063 versus 20582, a higher percentile ranking, and wins in six of ten head to head tests. Its dominance in DirectX 9, 10, and 11 makes it the stronger option for anyone running older software or games that rely on legacy graphics APIs. The 93.1% lead in DirectX 11 is particularly striking and suggests that AMD's RDNA 2.0 architecture retains compatibility advantages that Intel's Xe-HPG does not match.

However, the Intel Arc A750 is the clear winner for modern DirectX 12 workloads. The 35.3% lead in 3DMark Steel Nomad DX12 indicates that Intel's architecture is better optimized for current and future API requirements. The OpenCL advantage of 25.7% and the Vulkan win of 5.1% also point to Intel being the stronger choice for compute intensive applications that use these interfaces. The Arc A750 also offers double the memory bandwidth and double the FP32 throughput, which are significant architectural advantages.

For users who prioritize legacy game compatibility and overall benchmark averages, the RX 6800S is the data backed choice. For users who focus on the latest DirectX 12 titles and modern compute workloads, the Arc A750 has the stronger case. The RX 6800S also operates at a much lower TDP of 100 W versus 225 W, making it suitable for integrated or low power systems, while the Arc A750 requires a dual slot card with external power connectors and a 550 W power supply recommendation.

Specification Differences

The two GPUs differ in nearly every major specification category. The process nodes differ, with AMD using 7 nm and Intel using 6 nm, both from TSMC. Transistor counts are 11,060 million for AMD versus 21,700 million for Intel, and die sizes are 237 mm² versus 406 mm². Transistor density favors Intel at 53.4M per mm² versus 46.7M per mm².

Clock speeds favor Intel in both base and boost, with 2050 MHz base and 2400 MHz boost against AMD's 1800 MHz base and 2100 MHz boost. AMD lists a game clock of 1975 MHz, while Intel does not list one. Memory is identical in size (8 GB) and type (GDDR6), but the bus width differs at 128 bit for AMD and 256 bit for Intel, resulting in bandwidth of 256.0 GB/s versus 512.0 GB/s.

Compute resources favor Intel: 3584 shading units versus 2048, 224 TMUs versus 128, 112 ROPs versus 64. Ray tracing cores are 28 for Intel versus 32 for AMD. FP32 performance is exactly double for Intel at 17.20 TFLOPS versus 8.602 TFLOPS, and FP16 is also double at 34.41 TFLOPS versus 17.20 TFLOPS. Pixel rate is double for Intel at 268.8 GPixel/s versus 134.4 GPixel/s, and texture rate is double at 537.6 GTexel/s versus 268.8 GTexel/s.

Power and physical specifications differ greatly. AMD has a 100 W TDP, is an IGP form factor, uses no power connectors, and has no suggested PSU. Intel has a 225 W TDP, is dual slot, requires one 6 pin and one 8 pin power connector, and suggests a 550 W PSU. Bus interfaces are PCIe 4.0 x8 for AMD and PCIe 4.0 x16 for Intel. Display outputs are portable device dependent for AMD, while Intel offers 1x HDMI 2.1 and 3x DisplayPort 2.0. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RX 6800S was released on January 3, 2022, while the Arc A750 was released on October 11, 2022.