AMD Radeon RX 9060 XT LP vs Intel Arc Pro B70 Comparison

Where Each One Wins

The AMD Radeon RX 9060 XT LP and Intel Arc Pro B70 occupy distinctly different positions in the database. The AMD card has recorded benchmark results, while the Intel card has none in the current dataset. This immediately shapes any comparison: the RX 9060 XT LP can be evaluated against measured performance, whereas the Arc Pro B70 can only be assessed through its architectural specifications and theoretical throughput values.

The RX 9060 XT LP delivers 24.99 TFLOPS of FP32 compute, which is 8.9% higher than the Arc Pro B70's 22.94 TFLOPS. In FP16 workloads, the situation reverses dramatically: the Arc Pro B70 outputs 45.88 TFLOPS at a 2:1 ratio, while the RX 9060 XT LP manages 24.99 TFLOPS at a 1:1 ratio. This means the Intel card offers 83.6% more FP16 throughput, making it the clear winner for workloads that leverage half-precision arithmetic.

Memory capacity heavily favors the Arc Pro B70, which carries 32 GB across a 256-bit bus, delivering 608.0 GB/s of bandwidth. The RX 9060 XT LP provides 16 GB on a 128-bit bus, yielding 322.3 GB/s. That is a 1.89x advantage in bandwidth and 2x in capacity for Intel. For datasets that exceed 16 GB, the Arc Pro B70 is the only viable option between the two.

Rasterization throughput also splits the pair. The Arc Pro B70 achieves 358.4 GPixel/s pixel fill and 716.8 GTexel/s texture fill, compared to 195.2 GPixel/s and 390.4 GTexel/s for the RX 9060 XT LP. Intel holds a 83.6% lead in both metrics, which suggests an advantage in geometry-heavy or fill-rate-bound scenes. The RX 9060 XT LP counters with higher boost clocks (3050 MHz vs 2800 MHz) and a more efficient process node (4 nm vs 5 nm), though both are fabricated by TSMC.

The AMD card sits at the 89th percentile among all GPUs in the database, while the Intel card sits at the 50th percentile with an average benchmark score of zero due to missing measurements. The RX 9060 XT LP's average benchmark score of 63830 places it within 0.6% of several established workstation and mobile parts, including the NVIDIA CMP 30HX, AMD Radeon RX 7600M, and AMD Radeon Pro Vega 56.

Architecture Differences

The two cards use fundamentally different GPU architectures. AMD's Navi 44 chip relies on RDNA 4.0, part of the Navi IV (RX 9000) generation. Intel's BMG-G31 chip uses Xe2-HPG, from the Battlemage (Pro Series) generation. Both target the same DirectX 12 Ultimate (12_2) feature level, OpenGL 4.6, and Vulkan 1.4 APIs, so software compatibility at the API level is identical.

Process technology differs: the RX 9060 XT LP uses TSMC's 4 nm node, while the Arc Pro B70 uses TSMC's 5 nm node. The AMD chip packs 29,700 million transistors into a 199 mm² die, yielding a transistor density of 149.2 million per square millimeter. Intel's die is substantially larger at 368 mm², but the transistor count is listed as unknown, making density calculations impossible.

Shader resources diverge sharply. The Arc Pro B70 contains 4096 shading units, 256 TMUs, and 128 ROPs. The RX 9060 XT LP has exactly half of each: 2048 shading units, 128 TMUs, and 64 ROPs. Both cards feature 32 ray tracing cores, so ray tracing hardware counts are equal, though architectural efficiency may differ.

Memory subsystems reflect different design priorities. Intel pairs 32 GB of GDDR6 with a 256-bit bus and 608.0 GB/s bandwidth. AMD pairs 16 GB of GDDR6 with a 128-bit bus and 322.3 GB/s bandwidth. Both use GDDR6, but Intel's wider bus doubles the bandwidth and capacity.

Clock behavior also differs. The RX 9060 XT LP runs at 1380 MHz base, 2450 MHz game clock, and 3050 MHz boost. The Arc Pro B70 runs at 2280 MHz base and 2800 MHz boost, with no game clock specified. AMD's 250 MHz boost advantage comes with a lower base clock, suggesting different power and thermal management strategies.

Power envelopes are not equal: the RX 9060 XT LP has a 140 W TDP and suggests a 300 W power supply, while the Arc Pro B70 has a 230 W TDP and suggests a 550 W power supply. Both are dual-slot cards with a single 8-pin power connector, and both use a PCIe 5.0 x16 bus interface.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results between these two cards. The RX 9060 XT LP has two recorded measurements: 88183 in Geekbench OpenCL and 39476 in Geekbench Vulkan. The Arc Pro B70 has no benchmark entries at all. This absence of comparative data means the analysis must rely on theoretical specifications and the AMD card's nearest rivals.

The RX 9060 XT LP's average benchmark score of 63830 places it in a tight cluster. Its closest rival, the NVIDIA CMP 30HX, scores 63842, a delta of 0%. The AMD Radeon RX 7600M scores 63775, putting the RX 9060 XT LP 0.1% ahead. The AMD Radeon Pro Vega 56 scores 63693, a 0.2% gap. The AMD Radeon Pro WX 9100 scores 64212, meaning the RX 9060 XT LP trails by 0.6%. These deltas are negligible in real-world terms, indicating that the RX 9060 XT LP performs on par with a known set of mid-range workstation and mobile GPUs.

Without benchmark data for the Arc Pro B70, its 50th percentile ranking appears provisional. The FP32 throughput comparison (24.99 vs 22.94 TFLOPS) suggests the AMD card has a 8.9% compute advantage in single-precision tasks. The FP16 comparison (24.99 vs 45.88 TFLOPS) gives Intel a 83.6% advantage, assuming software can exploit the 2:1 ratio. Pixel and texture fill rates favor Intel by 83.6%, which may translate to better performance in certain rendering paths.

The RX 9060 XT LP's Vulkan score of 39476 is notably lower than its OpenCL score of 88183. This large discrepancy suggests the card's Vulkan drivers or hardware scheduling may be less optimized for that API, or that the workload characteristics differ substantially. No comparable data exists for the Arc Pro B70, so cross-API behavior cannot be assessed.

FAQ

Q: Which card has more memory bandwidth?

A: The Intel Arc Pro B70 has 608.0 GB/s of bandwidth, while the AMD Radeon RX 9060 XT LP has 322.3 GB/s. Intel's advantage is 1.89x, driven by a 256-bit bus versus a 128-bit bus.

Q: What is the FP32 performance difference?

A: The AMD Radeon RX 9060 XT LP delivers 24.99 TFLOPS of FP32 compute, which is 8.9% higher than the Arc Pro B70's 22.94 TFLOPS.

Q: Do both cards support the same graphics APIs?

A: Yes, both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: How does the Radeon RX 9060 XT LP compare to its nearest rivals?

A: Its average benchmark score of 63830 is essentially tied with the NVIDIA CMP 30HX (63842, 0% delta), 0.1% ahead of the AMD Radeon RX 7600M, 0.2% ahead of the AMD Radeon Pro Vega 56, and 0.6% behind the AMD Radeon Pro WX 9100.

Q: Which card has more shading units?

A: The Intel Arc Pro B70 has 4096 shading units, exactly double the 2048 shading units found in the AMD Radeon RX 9060 XT LP.

Q: What is the launch MSRP of the Intel Arc Pro B70?

A: The launch MSRP is 949 USD. The AMD Radeon RX 9060 XT LP has no listed launch MSRP.

Specification Differences

| Specification | AMD Radeon RX 9060 XT LP | Intel Arc Pro B70 |

|---|---|---|

| Architecture | RDNA 4.0 | Xe2-HPG |

| Generation | Navi IV (RX 9000) | Battlemage (Pro Series) |

| Process node | 4 nm | 5 nm |

| Transistors | 29,700 million | unknown |

| Die size | 199 mm² | 368 mm² |

| Transistor density | 149.2M / mm² | null |

| Base clock | 1380 MHz | 2280 MHz |

| Boost clock | 3050 MHz | 2800 MHz |

| Game clock | 2450 MHz | null |

| Memory clock | 2518 MHz, 20.1 Gbps effective | 2375 MHz, 19 Gbps effective |

| Memory size | 16 GB | 32 GB |

| Memory bus | 128 bit | 256 bit |

| Memory bandwidth | 322.3 GB/s | 608.0 GB/s |

| Shading units | 2048 | 4096 |

| TMUs | 128 | 256 |

| ROPs | 64 | 128 |

| RT cores | 32 | 32 |

| Pixel rate | 195.2 GPixel/s | 358.4 GPixel/s |

| Texture rate | 390.4 GTexel/s | 716.8 GTexel/s |

| FP32 | 24.99 TFLOPS | 22.94 TFLOPS |

| FP16 | 24.99 TFLOPS (1:1) | 45.88 TFLOPS (2:1) |

| TDP | 140 W | 230 W |

| Suggested PSU | 300 W | 550 W |

| Display outputs | 1x HDMI 2.1b, 2x DisplayPort 2.1a | 1x HDMI 2.1a, 3x DisplayPort 2.1 |

| Dimensions | null | 267 mm x 110 mm x 39 mm |

| Release date | 2025-12-16 | 2026-03-25 |

| Launch MSRP | null | 949 USD |

| Percentile vs all GPUs | 89 | 50 |

| Average benchmark score | 63830 | 0 |

The Verdict

The recorded data separates these two cards by purpose and workload. The AMD Radeon RX 9060 XT LP is a measured performer, sitting at the 89th percentile with an average benchmark score of 63830. It trades blows within 0.6% of four established GPUs, confirming it as a known quantity. Its strengths lie in FP32 compute, higher boost clocks, and a smaller 199 mm² die that operates within a 140 W TDP.

The Intel Arc Pro B70 is an unmeasured quantity in the database, with zero benchmark scores and a 50th percentile placeholder. Its specifications tell a different story: 32 GB of memory, 608.0 GB/s of bandwidth, double the shading units, TMUs, and ROPs, and FP16 throughput of 45.88 TFLOPS that far exceeds the AMD card. These numbers point toward memory-heavy and half-precision workloads, such as large model inference or data-parallel compute, where capacity and bandwidth dominate.

For users who need verified performance in OpenCL or Vulkan, the RX 9060 XT LP has the data to back its claims. Its 88183 OpenCL score and 39476 Vulkan score are concrete reference points. For users who need 32 GB of memory or maximum FP16 throughput, the Arc Pro B70 is the only option between the two, though its performance remains unverified. The 230 W TDP and 550 W suggested power supply indicate a more demanding platform requirement.

The architectural split is clean: AMD wins on FP32 density and efficiency per watt, Intel wins on raw resources and memory capacity. The 4 nm process gives AMD a 149.2M transistors per mm² density, while Intel's 368 mm² die offers more silicon for compute units. Neither card has a tensor core count listed, so AI acceleration beyond FP16 depends on driver and software support.

The database records no head-to-head benchmarks, no wins for either card, and no direct comparisons. This means the verdict rests on specification deltas. The RX 9060 XT LP appears suited for general-purpose rendering and compute where FP32 precision matters and power draw is a constraint. The Arc Pro B70 appears suited for memory-intensive workloads and FP16-heavy pipelines, provided the 949 USD launch MSRP fits the project budget.

Both cards use PCIe 5.0 x16, dual-slot designs, and a single 8-pin power connector. Both support the same API feature levels. The decision hinges on whether measured performance (AMD) or raw specifications (Intel) matter more for the target application.