AMD Radeon AI PRO 9600D vs Intel Arc B570 Comparison

Head-to-Head Benchmarks

The Intel Arc B570 enters the database with a recorded average benchmark score of 20556, placing it in the 65th percentile of all GPUs tested. The AMD Radeon AI PRO 9600D, by contrast, holds a 50th percentile position with an average benchmark score of zero, as no benchmark entries are recorded for it in the database. This absence of recorded scores for the AMD part makes direct numerical comparison impossible in most tests, but the available data for the Intel card still provides a reference frame.

The Arc B570's nearest rival in the database is the NVIDIA GeForce RTX 3070 Mobile, which scores 20534, a delta of 0.1 percent. That places the Intel card essentially level with that laptop GPU. The Intel Arc A750 trails by a hair at 20582, a delta of -0.1 percent, meaning the B570 sits slightly below the A750 in aggregate performance. Against the NVIDIA Quadro M4000M, which scores 20480, the B570 leads by 0.4 percent. The AMD Radeon R9 M390X posts 20662, putting the B570 0.5 percent behind it.

Since the Radeon AI PRO 9600D has no recorded benchmark scores in the database, the head-to-head section relies on the Intel card's measured results alone. In 3DMark Steel Nomad DX12, the Arc B570 delivers a score of 2649. Its Geekbench OpenCL score reaches 83514, while the Vulkan result climbs to 96844. Passmark results show a G3D score of 14195, a GPU compute score of 7281, and legacy DirectX tests ranging from 65 in DirectX 10 to 164 in DirectX 9. The G2D score sits at 661.

The AMD card's specifications, however, suggest a different performance tier. Its FP32 throughput is listed at 24.82 TFLOPS, more than double the Arc B570's 11.52 TFLOPS. The Radeon's texture rate of 387.8 GTexel/s exceeds the Intel card's 360.0 GTexel/s. Pixel rates are close: 193.9 GPixel/s for AMD versus 200.0 GPixel/s for Intel, with the Intel part actually ahead there. Memory bandwidth heavily favors AMD at 576.0 GB/s versus 380.0 GB/s. These are the only quantifiable comparisons available, as the database contains no head-to-head benchmark entries for the two cards.

Where Each One Wins

The Intel Arc B570 wins in every category where recorded data exists, simply because it is the only card with benchmark results. Its 3DMark Steel Nomad DX12 score of 2649 indicates solid DirectX 12 rasterization performance. Geekbench Vulkan at 96844 shows strong compute and graphics workload handling under Vulkan, while OpenCL at 83514 confirms comparable compute capability. Passmark G3D at 14195 places it in a mid-range tier, and the GPU compute score of 7281 reflects its compute throughput in that specific suite.

The AMD Radeon AI PRO 9600D wins on raw hardware specifications. Its FP32 compute of 24.82 TFLOPS is more than double the Intel card's 11.52 TFLOPS, which suggests significantly higher shader throughput in FP32-bound workloads. Memory capacity is 32 GB versus 10 GB, a 3.2x advantage that matters for large datasets or high-resolution textures. Memory bandwidth of 576.0 GB/s versus 380.0 GB/s gives AMD a 51.6 percent lead in data transfer rates. The Radeon also uses a 256-bit memory bus versus Intel's 160-bit bus, and it has 48 RT cores versus 18, indicating more ray tracing hardware. Shading units number 3072 versus 2304, TMUs 192 versus 144, and ROPs 96 versus 80.

The process node differs: AMD uses a 4 nm process, Intel a 5 nm process, both from TSMC. Transistor counts are 53,900 million for AMD versus 19,600 million for Intel, and the die size is 357 mm² versus 272 mm². Transistor density is 151.0M per mm² for AMD and 72.1M per mm² for Intel. The AMD card is built on RDNA 4.0 architecture, while Intel uses Xe2-HPG. PCIe interface also differs: AMD uses PCIe 5.0 x16, Intel uses PCIe 4.0 x8, which could affect bandwidth in certain workloads.

The Verdict

The data indicates two products aimed at different use cases. The Intel Arc B570 is the only card with recorded benchmark scores, and those scores place it in the 65th percentile of all GPUs, with an average score of 20556. Its nearest rivals, the RTX 3070 Mobile and Arc A750, are within 0.1 percent, so the B570 sits in a tightly contested mid-range segment. The card's 150 W TDP, dual-slot design, and 8-pin power connector align with a mainstream desktop GPU. Its 10 GB memory and 380.0 GB/s bandwidth are modest, but the recorded scores show it performs competitively in that class.

The AMD Radeon AI PRO 9600D, with no recorded benchmarks, cannot be placed relative to the Intel card in measured performance. Its specifications, however, describe a workstation-oriented part: 32 GB of GDDR6 memory, 576.0 GB/s bandwidth, 24.82 TFLOPS FP32, and a single-slot design with a 16-pin power connector. The 150 W TDP matches the Intel card, but the memory capacity and compute throughput suggest it targets compute, AI, or large-frame-buffer workloads rather than gaming. Its release date of December 2025 is later than the Intel card's January 2025 release.

Who should pick which depends entirely on the workload. For users with recorded benchmarks to reference, the Arc B570 has verified performance data across DX12, Vulkan, OpenCL, and Passmark suites. For users whose priority is memory capacity, FP32 throughput, and bandwidth, the Radeon AI PRO 9600D offers specifications that the Intel card cannot match, but without recorded scores to confirm real-world behavior. The absence of benchmark data for the AMD card is a significant gap in the database, and any performance claim for it must rely solely on its listed specifications.

FAQ

Q: What is the average benchmark score for the Intel Arc B570?

A: The Arc B570 has an average benchmark score of 20556, placing it in the 65th percentile of all GPUs.

Q: What is the average benchmark score for the AMD Radeon AI PRO 9600D?

A: The Radeon AI PRO 9600D has an average benchmark score of zero, with no benchmark entries recorded in the database.

Q: How does the Intel Arc B570 compare to its nearest rivals?

A: It is 0.1 percent ahead of the NVIDIA GeForce RTX 3070 Mobile, 0.1 percent behind the Intel Arc A750, 0.4 percent ahead of the NVIDIA Quadro M4000M, and 0.5 percent behind the AMD Radeon R9 M390X.

Q: Which card has more memory?

A: The AMD Radeon AI PRO 9600D has 32 GB of GDDR6 memory, while the Intel Arc B570 has 10 GB of GDDR6 memory.

Q: What are the FP32 compute figures for each card?

A: The AMD Radeon AI PRO 9600D delivers 24.82 TFLOPS FP32, while the Intel Arc B570 delivers 11.52 TFLOPS FP32.

Q: What is the launch MSRP of the Intel Arc B570?

A: The Intel Arc B570 has a launch MSRP of 219 USD.

Architecture Differences

The AMD Radeon AI PRO 9600D uses the Navi 48 chip built on RDNA 4.0 architecture, fabricated on a 4 nm process at TSMC. The die measures 357 mm² and contains 53,900 million transistors, giving a transistor density of 151.0M per mm². It has 3072 shading units, 192 texture mapping units, 96 raster output units, and 48 ray tracing cores. The base clock is 1080 MHz, the boost clock is 2020 MHz, and the game clock is also 1080 MHz. Memory runs at 2250 MHz with 18 Gbps effective data rate across a 256-bit bus, yielding 576.0 GB/s bandwidth. The card uses a single-slot design with a 16-pin power connector and a 150 W TDP. It connects via PCIe 5.0 x16 and offers one DisplayPort 2.1a output. Its predecessor in the database is the Radeon Pro Vega, and it is listed as part of the Radeon Pro Navi (Navi IV Series) generation.

The Intel Arc B570 uses the BMG-G21 chip built on Xe2-HPG architecture, fabricated on a 5 nm process at TSMC. The die measures 272 mm² and contains 19,600 million transistors, giving a transistor density of 72.1M per mm². It has 2304 shading units, 144 texture mapping units, 80 raster output units, and 18 ray tracing cores. The base and boost clocks are both 2500 MHz. Memory runs at 2375 MHz with 19 Gbps effective data rate across a 160-bit bus, yielding 380.0 GB/s bandwidth. The card uses a dual-slot design with an 8-pin power connector and a 150 W TDP. It connects via PCIe 4.0 x8 and offers one HDMI 2.1a port plus three DisplayPort 2.1 outputs. Its predecessor is Alchemist, and it belongs to the Battlemage (Arc 5) generation.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are listed as Active production status. The Radeon AI PRO 9600D has no launch MSRP recorded, while the Arc B570 is listed at 219 USD. The AMD card's FP16 throughput matches its FP32 at 24.82 TFLOPS, indicating a 1:1 ratio. The Intel card's FP16 throughput is 23.04 TFLOPS, achieved at a 2:1 ratio relative to FP32. The AMD card's pixel rate is 193.9 GPixel/s and texture rate is 387.8 GTexel/s. The Intel card's pixel rate is 200.0 GPixel/s and texture rate is 360.0 GTexel/s. Dimensions differ: the AMD card measures 241 mm in length, 111 mm in height, and 19 mm in width; the Intel card measures 272 mm in length and 115 mm in height, with no width recorded. Both recommend a 450 W power supply.