AMD Radeon RX 6700S vs Intel Arc A750 Comparison

AMD
RADEON

AMD Radeon RX 6700S

CORE STATE Navi 23
VRAM 8 GB
CLOCK SPEED 2000 MHz
TDP 80 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2022
VS
Intel
GPU

Arc A750

CORE STATE DG2-512
VRAM 8 GB
CLOCK SPEED 2400 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE Xe-HPG
nm
PROCESS 6 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,451
2,612
geekbench_metal
72,864
N/A
geekbench_opencl
70,965
98,554
geekbench_vulkan
76,150
85,631
passmark_directx_10
87
65
passmark_directx_11
134
72
passmark_directx_12
58
70
passmark_directx_9
195
181
passmark_g2d
739
732
passmark_g3d
15,066
12,534
passmark_gpu_compute
5,990
5,368

Analysis: AMD Radeon RX 6700S vs Intel Arc A750

The AMD Radeon RX 6700S and Intel Arc A750 are two very different graphics cards that end up near each other in average benchmark scores, but they achieve that status through opposite strategies. The RX 6700S is a mobile-first, power-sipping part from the Radeon RX 6000 series, while the Arc A750 is a desktop-focused, power-hungry card from Intel’s Alchemist generation. The data shows the AMD card wins 6 of the 10 head-to-head benchmark comparisons, yet the Intel card takes the more demanding modern workloads. For a builder prioritizing a compact, low-power system with strong legacy API performance, the RX 6700S is the pick. For someone with a standard desktop PSU and a focus on DirectX 12 or compute-heavy tasks, the Arc A750 offers higher raw throughput.

The Verdict

The benchmark results indicate a split decision based on your system constraints and workload. The AMD Radeon RX 6700S is the better choice for portable or small-form-factor builds. Its 80 W TDP and IGP slot width mean it needs no power connectors and fits into the tightest chassis. It wins 6 out of 10 head-to-head tests, including a dominant 86.1% lead in Passmark DirectX 11 and a 20.2% lead in Passmark G3D. Its average benchmark score is 22154, which places it in the 67th percentile of all GPUs, slightly ahead of the Arc A750’s 20582 average and 66th percentile ranking.

The Intel Arc A750 is the better choice for a conventional desktop tower with a 550 W suggested PSU and a dual-slot slot width. It wins the most important future-facing test, 3DMark Steel Nomad DX12, by a massive 44.4% margin (2612 vs 1451). It also leads in Geekbench OpenCL by 28% and Vulkan by 11.1%. If your software leverages DirectX 12 or compute APIs, the Arc A750 is clearly the stronger performer, despite losing the overall head-to-head count. The RX 6700S is end-of-life, but the Arc A750 is also marked end-of-life, with a successor named Battlemage.

Where Each One Wins

The AMD Radeon RX 6700S dominates in legacy and 2D workloads. It wins Passmark DirectX 10 by 33.8%, DirectX 11 by 86.1%, DirectX 9 by 7.7%, and G2D by a narrow 1% (739 vs 732). Its Passmark G3D score of 15066 is 20.2% higher than the Arc A750’s 12534, suggesting better overall rasterization performance in older or less optimized game engines. It also wins Passmark GPU Compute by 11.6% (5990 vs 5368), which is surprising given the Intel card’s much higher theoretical FP32 output.

The Intel Arc A750 wins in modern, compute-oriented benchmarks. The 3DMark Steel Nomad DX12 result is its biggest victory, with a 44.4% higher score. It also takes Geekbench OpenCL with 98554 vs 70965, a 28% advantage, and Geekbench Vulkan with 85631 vs 76150, an 11.1% lead. The Passmark DirectX 12 test also goes to Intel, with a 17.1% margin (70 vs 58). This pattern shows Intel’s architecture is optimized for newer APIs and compute shaders, while AMD’s card excels in the older DirectX feature levels.

Architecture Differences

The two cards come from fundamentally different design philosophies. The AMD Radeon RX 6700S uses the Navi 23 chip built on RDNA 2.0 architecture, fabricated on a 7 nm process at TSMC. It packs 11,060 million transistors into a 237 mm² die, giving a transistor density of 46.7 million per square millimeter. The Intel Arc A750 uses the DG2-512 chip with Xe-HPG architecture, made on a more advanced 6 nm TSMC process. It contains 21,700 million transistors on a much larger 406 mm² die, with a higher density of 53.4 million per square millimeter.

The compute resources are starkly different. The RX 6700S has 1792 shading units, 112 TMUs, and 64 ROPs, while the Arc A750 has exactly double the shading units at 3584, double the TMUs at 224, and double the ROPs at 112. Both have 28 ray tracing cores. The FP32 throughput reflects this: the Arc A750 delivers 17.20 TFLOPS versus 7.168 TFLOPS for the RX 6700S, and FP16 is 34.41 TFLOPS vs 14.34 TFLOPS. Memory configurations also differ: both have 8 GB of GDDR6, but the AMD card uses a 128-bit bus for 224.0 GB/s bandwidth, while the Intel card uses a 256-bit bus for 512.0 GB/s bandwidth. The Arc A750 also has a higher boost clock of 2400 MHz versus 2000 MHz, and a base clock of 2050 MHz versus 1700 MHz.

Power and interface requirements are the biggest practical difference. The RX 6700S is rated at 80 W TDP, requires no power connectors, and uses a PCIe 4.0 x8 interface. The Arc A750 is rated at 225 W TDP, needs a 1x 6-pin plus 1x 8-pin power connection, and uses a full PCIe 4.0 x16 slot. Display outputs also differ: the AMD card is “Portable Device Dependent,” while the Intel card offers 1x HDMI 2.1 and 3x DisplayPort 2.0.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon RX 6700S has an average benchmark score of 22154, which is 7.6% higher than the Intel Arc A750’s 20582. The AMD card also sits in the 67th percentile of all GPUs versus the Intel card’s 66th.

Q: Is the Intel Arc A750 better for DirectX 12 gaming?

A: Yes, the data supports that. The Arc A750 wins 3DMark Steel Nomad DX12 with a score of 2612 vs 1451, a 44.4% difference, and also wins Passmark DirectX 12 with 70 vs 58, a 17.1% margin.

Q: Does the AMD card win any compute benchmarks?

A: Yes, the RX 6700S wins Passmark GPU Compute with a score of 5990 versus 5368, an 11.6% lead. However, the Intel card wins Geekbench OpenCL by 28% and Vulkan by 11.1%.

Q: What is the TDP difference between the two?

A: The AMD Radeon RX 6700S is rated at 80 W, while the Intel Arc A750 is rated at 225 W. This makes the AMD card far more suitable for low-power or mobile builds.

Q: Which card has more memory bandwidth?

A: The Intel Arc A750 has exactly double the bandwidth of the AMD card: 512.0 GB/s versus 224.0 GB/s, due to a 256-bit bus versus a 128-bit bus.

Q: Are both cards end-of-life?

A: Yes, the production status for both the AMD Radeon RX 6700S and the Intel Arc A750 is listed as “End-of-life.” The Intel card’s successor is listed as Battlemage, while the AMD card has no successor listed.

Head-to-Head Benchmarks

The single biggest win for the Intel Arc A750 is in 3DMark Steel Nomad DX12. The Intel card scores 2612, which is 44.4% higher than the AMD card’s 1451. This is a decisive victory in a modern API test and suggests the Arc A750 has a significant architectural advantage in DirectX 12 workloads. The Geekbench OpenCL result follows a similar pattern, with Intel scoring 98554 versus AMD’s 70965, a 28% lead. Geekbench Vulkan is closer but still favors Intel, with 85631 vs 76150, an 11.1% margin. Passmark DirectX 12 also goes to Intel, with 70 vs 58, a 17.1% advantage.

The AMD Radeon RX 6700S has its largest win in Passmark DirectX 11, scoring 134 versus the Arc A750’s 72, a massive 86.1% difference. This is the most lopsided result in either direction. Passmark DirectX 10 also favors AMD, with 87 vs 65, a 33.8% win. Passmark G3D is another strong AMD result: 15066 vs 12534, a 20.2% margin. The AMD card also wins Passmark GPU Compute with 5990 vs 5368, an 11.6% lead, and Passmark DirectX 9 with 195 vs 181, a 7.7% edge. Passmark G2D is nearly tied, with AMD winning 739 vs 732, just a 1% difference.

Overall, the pattern is clear: Intel wins the modern, high-level API tests by large margins, while AMD wins the legacy DirectX 9/10/11 tests and the overall G3D score. The wins are split 6 for AMD and 4 for Intel, but the Intel wins are often larger in magnitude, particularly the 44.4% Steel Nomad and 28% OpenCL victories.

Specification Differences

The most obvious difference is in the process node and die size. The AMD Radeon RX 6700S uses a 7 nm process with an 11,060 million transistor count on a 237 mm² die. The Intel Arc A750 uses a 6 nm process with 21,700 million transistors on a 406 mm² die. The transistor density is 46.7 million per mm² for AMD and 53.4 million per mm² for Intel.

Clock speeds differ significantly. The RX 6700S has a base clock of 1700 MHz, a game clock of 1890 MHz, and a boost clock of 2000 MHz. The Arc A750 has a base clock of 2050 MHz and a boost clock of 2400 MHz, with no game clock listed. The memory clock is 1750 MHz (14 Gbps effective) for AMD and 2000 MHz (16 Gbps effective) for Intel.

Core counts are doubled on the Intel card: 3584 shading units vs 1792, 224 TMUs vs 112, and 112 ROPs vs 64. Both have 28 ray tracing cores. The pixel rate is 268.8 GPixel/s for Intel versus 128.0 GPixel/s for AMD, and the texture rate is 537.6 GTexel/s versus 224.0 GTexel/s. FP32 is 17.20 TFLOPS for Intel versus 7.168 TFLOPS for AMD, with FP16 at 34.41 TFLOPS vs 14.34 TFLOPS.

Power and physical specs are the biggest differentiators for real-world use. The RX 6700S has an 80 W TDP, an IGP slot width, and no power connectors. The Arc A750 has a 225 W TDP, a dual-slot width, and requires a 1x 6-pin + 1x 8-pin power connector, with a suggested PSU of 550 W. The bus interface is PCIe 4.0 x8 for AMD versus 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. The release dates are also different: January 2022 for the AMD card and October 2022 for the Intel card. The Intel Arc A750 has a launch MSRP of 289 USD, while the AMD card has no listed launch MSRP.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6700S
A750
Core Specs
Shading Units
1,792
3,584 +100.0%
Shaders
1,792
3,584 +100.0%
TMUs
112
224 +100.0%
ROPs
64
112 +75.0%
Compute Units
28
Execution Units
448
Clocks
Base Clock
1700 MHz
2050 MHz
Boost Clock
2000 MHz
2400 MHz
Game Clock
1890 MHz
Memory Clock
1750 MHz 14 Gbps effective
2000 MHz 16 Gbps effective
Memory
Memory Size
8 GB
8 GB
VRAM (MB)
8,192
8,192 0.0%
Memory Type
GDDR6
GDDR6
Memory Bus
128 bit
256 bit
Bandwidth
224.0 GB/s
512.0 GB/s
Cache
L1 Cache
128 KB per Array
L2 Cache
2 MB
16 MB
L3 Cache
32 MB
L0 Cache
32 KB per WGP
Performance
Pixel Rate
128.0 GPixel/s
268.8 GPixel/s
Texture Rate
224.0 GTexel/s
537.6 GTexel/s
FP32 (TFLOPS)
7.168 TFLOPS
17.20 TFLOPS
FP64 (TFLOPS)
448.0 GFLOPS (1:16)
2.150 TFLOPS (1:8)
FP16 (TFLOPS)
14.34 TFLOPS (2:1)
34.41 TFLOPS (2:1)
AI/RT
RT Cores
28
28 0.0%
XMX Cores
448
Power
TDP
80 W
225 W
TDP (W)
80
225 +181.3%
Suggested PSU
550 W
Power Connectors
None
1x 6-pin + 1x 8-pin
Architecture
Architecture
RDNA 2.0
Xe-HPG
GPU Name
Navi 23
DG2-512
Generation
Navi Mobile (RX 6000M)
Alchemist (Arc 7)
Process Size
7 nm
6 nm
Transistors
11,060 million
21,700 million
Die Size
237 mm²
406 mm²
Foundry
TSMC
TSMC
Density
46.7M / mm²
53.4M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
Shader Model
6.8
6.6
Physical
Slot Width
IGP
Dual-slot
Outputs
Portable Device Dependent
1x HDMI 2.13x DisplayPort 2.0
Bus Interface
PCIe 4.0 x8
PCIe 4.0 x16
Other
Launch Price
289 USD
Production
End-of-life
End-of-life
Predecessor
Polaris Mobile
Xe Graphics
Successor
Battlemage
View Radeon RX 6700S Details View Arc A750 Details