AMD Ryzen Z2 Extreme GPU vs Intel Arc Pro B65 Comparison

# Where Each One Wins

The recorded data shows two very different products with almost no benchmark overlap. The AMD Ryzen Z2 Extreme GPU has one measured result in the database: a 3DMark Steel Nomad DX12 score of 516. That places it at the 1st percentile among all GPUs, meaning it sits near the bottom of the performance distribution. The Intel Arc Pro B65 has no benchmark entries at all, so its average benchmark score is recorded as 0, and the database shows no head-to-head benchmark results between the two items. Wins A and B are both 0.

The AMD part wins in the context of its nearest rivals. Against the Intel HD Graphics P4000, which scores 534, the AMD part trails by 3.4 percent. Against the AMD Radeon HD 6870, which scores 536, it trails by 3.7 percent. Against the AMD Radeon HD 6750M, which scores 484, the Ryzen Z2 Extreme GPU leads by 6.6 percent. Against the AMD Radeon HD 6770M, which scores 569, it trails by 9.3 percent. So the AMD product is competitive with a narrow band of older integrated and discrete GPUs, but it does not break into a higher performance class.

The Intel Arc Pro B65 has no nearest rivals listed, no benchmark scores, and no percentile data beyond its 50th percentile placement among all GPUs. That percentile indicates it sits near the middle of the entire GPU distribution, which is a far stronger position than the AMD part's 1st percentile. However, without a recorded benchmark score, the database cannot quantify how much faster the Intel part is in any specific test.

The use-case split is therefore stark. The AMD Ryzen Z2 Extreme GPU is a low-power, low-footprint part with a single USB Type-C display output, designed for compact or mobile contexts where power draw is minimal. The Intel Arc Pro B65 is a dual-slot, 200 W card with an 8-pin power connector, four DisplayPort 2.1 outputs, and a PCIe 5.0 x16 interface, aimed at workstation or professional display configurations. The data indicates the Intel part occupies a higher performance percentile, while the AMD part is positioned at the very low end of the performance spectrum.

# Architecture Differences

The two GPUs come from different manufacturers and use entirely different architectures. The AMD Ryzen Z2 Extreme GPU is built on the Strix Point chip, using the RDNA 3.5 architecture, and is categorized as a Console GPU from AMD. It is fabricated on a 4 nm process at TSMC. The transistor count is 34,000 million, and the die size is 233 mm², giving a transistor density of 145.9 million transistors per square millimeter.

The Intel Arc Pro B65 uses the BMG-G21 chip, based on the Xe2-HPG architecture, and belongs to the Battlemage Pro Series generation. It is fabricated on a 5 nm process, also at TSMC. The transistor count is 19,600 million, and the die size is 272 mm², resulting in a transistor density of 72.1 million transistors per square millimeter. The Intel die is physically larger, but the AMD die packs far more transistors per area.

Memory configurations differ substantially. The AMD part uses 16 GB of LPDDR5X with a 128-bit bus and 128.0 GB/s of bandwidth. The Intel part uses 32 GB of GDDR6 with a 256-bit bus and 608.0 GB/s of bandwidth. That is a 4.75 times difference in raw memory bandwidth, which matters for texture-heavy workloads and large frame buffers.

Clock speeds also separate the two. The AMD GPU runs at a base clock of 800 MHz and boosts to 2700 MHz, with memory clocked at 1000 MHz (8 Gbps effective). The Intel GPU has a base clock of 2400 MHz and a boost clock of 2400 MHz, meaning it does not boost beyond its base clock, with memory at 2375 MHz (19 Gbps effective).

Compute resources differ by a wide margin. The AMD part has 1024 shading units, 64 texture mapping units, 48 ROPs, and 16 ray tracing cores. The Intel part has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The shading unit count is 2.5 times higher on the Intel side, and the TMU count is 2.5 times higher as well.

Pixel and texture rates confirm the gap. The AMD GPU delivers 129.6 GPixel/s and 172.8 GTexel/s. The Intel GPU delivers 192.0 GPixel/s and 384.0 GTexel/s. The Intel part is roughly 48 percent ahead in pixel rate and 122 percent ahead in texture rate.

Floating-point throughput shows a similar pattern. The AMD part delivers 5.530 TFLOPS for both FP32 and FP16, meaning a 1:1 ratio. The Intel part delivers 12.29 TFLOPS for FP32 and 24.58 TFLOPS for FP16, a 2:1 ratio. The Intel part is roughly 2.2 times ahead in FP32 and 4.4 times ahead in FP16.

Power consumption is the reverse story. The AMD GPU has a TDP of 28 W. The Intel GPU has a TDP of 200 W. The Intel part draws over 7 times more power. The AMD part requires no power connectors, while the Intel part requires one 8-pin connector and a suggested PSU of 550 W. The AMD part is a single USB Type-C output device, while the Intel part offers four DisplayPort 2.1 outputs.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD part is fabricated on a smaller 4 nm node, while the Intel part uses a larger 5 nm node. The Intel part has a higher transistor count per die due to its larger area, but the AMD part has a much higher density.

# The Verdict

The database paints a clear picture: the Intel Arc Pro B65 is in a different performance class. Its 50th percentile placement among all GPUs, combined with its 2560 shading units, 12.29 TFLOPS FP32 throughput, 384.0 GTexel/s texture rate, and 608.0 GB/s memory bandwidth, indicates a mid-range desktop card. The AMD Ryzen Z2 Extreme GPU, at the 1st percentile, with 1024 shading units, 5.530 TFLOPS FP32, and 128.0 GB/s memory bandwidth, is a low-power integrated-class part.

The AMD part wins only on power efficiency and compactness. Its 28 W TDP and lack of power connectors make it suitable for systems without discrete power delivery. Its single USB Type-C output suggests a mobile or handheld form factor. The Intel part, at 200 W with an 8-pin connector and dual-slot design, requires a proper desktop power supply and chassis space.

For users who need raw rendering performance, the Intel part is the only logical choice from the recorded data. Its FP32 throughput is 2.2 times higher, its texture rate is 2.2 times higher, and its memory bandwidth is 4.75 times higher. The 32 GB frame buffer is double the AMD part's 16 GB, and the 256-bit bus provides far more memory throughput.

For users constrained by power or physical size, the AMD part is the only option. No other data in the database suggests the Intel part can operate at 28 W or without external power. The AMD part also has a smaller die at 233 mm² versus 272 mm², and a more advanced 4 nm process node.

The verdict is not a close call. The Intel Arc Pro B65 is the faster GPU by every measurable compute and memory metric in the database. The AMD Ryzen Z2 Extreme GPU is the lower-power, lower-performance part. The choice depends entirely on whether the system can accommodate a 200 W dual-slot card or must operate within a 28 W envelope.

# FAQ

Q: Which GPU has more shading units?

A: The Intel Arc Pro B65 has 2560 shading units, while the AMD Ryzen Z2 Extreme GPU has 1024 shading units.

Q: What is the memory bandwidth difference?

A: The Intel Arc Pro B65 delivers 608.0 GB/s, while the AMD Ryzen Z2 Extreme GPU delivers 128.0 GB/s.

Q: How do the FP32 performance figures compare?

A: The Intel Arc Pro B65 delivers 12.29 TFLOPS, while the AMD Ryzen Z2 Extreme GPU delivers 5.530 TFLOPS.

Q: What is the power consumption of each part?

A: The AMD Ryzen Z2 Extreme GPU has a TDP of 28 W, while the Intel Arc Pro B65 has a TDP of 200 W.

Q: Which GPU has more display outputs?

A: The Intel Arc Pro B65 has four DisplayPort 2.1 outputs, while the AMD Ryzen Z2 Extreme GPU has one USB Type-C output.

Q: What is the transistor density of each chip?

A: The AMD Ryzen Z2 Extreme GPU has 145.9 million transistors per mm², while the Intel Arc Pro B65 has 72.1 million transistors per mm².

# Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between the AMD Ryzen Z2 Extreme GPU and the Intel Arc Pro B65. The headToHeadBenchmarks array is empty, and both winsA and winsB are recorded as 0. This means no single test pits these two parts against each other with measured scores.

However, the available data allows for indirect comparisons based on specification-derived metrics. The Intel Arc Pro B65 shows a 2.2 times higher FP32 throughput (12.29 TFLOPS versus 5.530 TFLOPS). The Intel part also shows a 2.2 times higher texture rate (384.0 GTexel/s versus 172.8 GTexel/s). The pixel rate favors Intel at 192.0 GPixel/s versus 129.6 GPixel/s, a 48 percent advantage.

Memory bandwidth is the largest specification gap. The Intel part's 608.0 GB/s is 4.75 times the AMD part's 128.0 GB/s. The memory bus width is 256 bits on Intel versus 128 bits on AMD. The memory type differs as well: GDDR6 on Intel versus LPDDR5X on AMD.

The AMD part has one measured benchmark score: 516 in 3DMark Steel Nomad DX12. That score places it at the 1st percentile overall. Its nearest rivals are all older or lower-end parts. The Intel HD Graphics P4000 scores 534, which is 3.4 percent higher. The AMD Radeon HD 6870 scores 536, 3.7 percent higher. The AMD Radeon HD 6750M scores 484, which the Ryzen Z2 Extreme GPU beats by 6.6 percent. The AMD Radeon HD 6770M scores 569, 9.3 percent higher.

The Intel Arc Pro B65 has no benchmark score, but its 50th percentile placement suggests it outperforms the vast majority of GPUs, including the entire cluster of rivals surrounding the AMD part. The AMD part's 1st percentile means it sits below nearly every other GPU in the database.

The biggest wins for the Intel part are in raw compute, memory bandwidth, and output configuration. The biggest win for the AMD part is power draw, at 28 W versus 200 W. The AMD part also wins on transistor density, with 145.9M per mm² versus 72.1M per mm², and on process node, with 4 nm versus 5 nm.

No benchmark data exists to show the Intel part in any specific test, so the database cannot quantify its exact performance advantage in a given workload. The specification data, however, consistently favors the Intel Arc Pro B65 across every performance-related metric recorded. The AMD Ryzen Z2 Extreme GPU's sole benchmark score of 516 is its only concrete performance data point, and it is a low score relative to the database population.