AMD Radeon PRO W7900 vs Intel Arc Pro B60 Dual Comparison

Where Each One Wins

The AMD Radeon PRO W7900 and the Intel Arc Pro B60 Dual occupy very different positions in the professional GPU landscape, and the recorded database metrics make that split explicit. The AMD card posts an average benchmark score of 110,725 across its measured tests, while the Intel card currently has no recorded benchmark entries in the database, which places its average score at 0 and its percentile at 50. That gap is not a subtle margin; it is a fundamental difference in available measurement data.

Where the AMD card wins is in raw compute delivery. Its Geekbench OpenCL score of 84,379 and Geekbench Vulkan score of 137,070 stand as the only quantified performance points in this comparison. The Intel Arc Pro B60 Dual has no such measurements recorded, so every performance conclusion that can be drawn from the database favors the AMD side by default of data availability. The AMD part sits at the 94th percentile among all GPUs in the database, a strong position that places it among the higher-performing professional accelerators. The Intel card, at the 50th percentile with no scores, cannot be positioned relative to the same field.

The use-case split, then, is defined by what each card is built to do. The AMD Radeon PRO W7900 targets heavy compute workloads where high memory capacity and high bandwidth matter. Its 48 GB of GDDR6 memory and 864.0 GB/s bandwidth give it a clear role in large dataset handling. The Intel Arc Pro B60 Dual, with 24 GB of GDDR6 memory and 456.0 GB/s bandwidth, targets a different tier of workload, one where the memory footprint is smaller and the board occupies a different physical profile. The Intel card is a dual-slot design at 40 mm width, while the AMD card is a triple-slot design at 51 mm width. That physical difference points to different installation environments and different thermal design expectations.

The data shows that the AMD card is the only one of the two with verified benchmark output. Any workstation or server deployment that depends on quantifiable performance metrics would rely on the AMD card's recorded results. The Intel card's absence of scores means the database cannot confirm its real-world behavior, only its specifications.

Architecture Differences

The two cards come from different architectural lineages, and those differences show up across nearly every major component. The AMD Radeon PRO W7900 uses the Navi 31 chip built on RDNA 3.0 architecture, codenamed Plum Bonito, and belongs to the Radeon Pro Navi generation. The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on Xe2-HPG architecture and belongs to the Battlemage Pro Series generation. Both are fabricated on a 5 nm process at TSMC, so the underlying manufacturing node is shared, but the transistor counts and die sizes diverge sharply.

The AMD chip packs 57,700 million transistors on a 529 mm² die, yielding a transistor density of 109.1 million per square millimeter. The Intel chip contains 19,600 million transistors on a 272 mm² die, with a density of 72.1 million per square millimeter. That is a 38,100 million transistor difference and a 257 mm² die area difference, both in favor of the AMD part. The larger die and transistor budget give the AMD card substantially more hardware resources across the board.

Shader resource counts reinforce the architectural gap. The AMD card has 6,144 shading units, 384 texture mapping units, 192 render output units, and 96 ray tracing cores. The Intel card has 2,560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The AMD card more than doubles the Intel card in shading units and TMUs, and it nearly doubles the ROP count. The ray tracing core difference is even larger, with 96 versus 20, a 4.8x advantage for AMD. Neither card lists tensor cores, so AI accelerator hardware is not a distinguishing factor in this pairing.

Compute throughput follows the same pattern. The AMD card delivers 61.32 TFLOPS of FP32 performance and 61.32 TFLOPS of FP16 performance at a 1:1 ratio. The Intel card delivers 12.29 TFLOPS of FP32 and 24.58 TFLOPS of FP16 at a 2:1 ratio. In FP32, the AMD card is roughly 5x faster. In FP16, the AMD card still holds a 2.5x lead, even though the Intel card's 2:1 ratio means it processes FP16 at twice its FP32 rate.

Memory architecture also differs. The AMD card uses a 384-bit memory bus with 48 GB of GDDR6, while the Intel card uses a 192-bit bus with 24 GB of GDDR6. The AMD memory clock is 2250 MHz with 18 Gbps effective transfer, and the Intel memory clock is 2375 MHz with 19 Gbps effective. Despite the Intel card's slightly higher memory clock, the AMD card's double-wide bus produces 864.0 GB/s of bandwidth versus 456.0 GB/s, a 408 GB/s advantage. The pixel rate tells a similar story: 479.0 GPixel/s for AMD versus 192.0 GPixel/s for Intel. Texture rate is 958.1 GTexel/s for AMD versus 384.0 GTexel/s for Intel.

Head-to-Head Benchmarks

The database lists no direct head-to-head benchmark entries between the AMD Radeon PRO W7900 and the Intel Arc Pro B60 Dual, and the Intel card has no individual benchmark scores recorded at all. The only measured numbers available belong to the AMD card. Its Geekbench OpenCL result of 84,379 and Geekbench Vulkan result of 137,070 are the sole performance data points in this comparison.

The AMD card's average benchmark score of 110,725 places it near several professional rivals. The nearest rival by average score is the NVIDIA Tesla V100 SXM2 16 GB at 114,395, which is 3.2% higher, meaning the AMD card trails that part by 3.2%. The NVIDIA RTX A5500 Mobile sits at 113,944, which is 2.8% higher than the AMD card, so the AMD part trails by 2.8%. On the other side, the AMD Radeon Pro W6600X averages 107,342, which is 3.2% lower, so the AMD card leads that part by 3.2%. The AMD Radeon Pro Vega II averages 109,617, which is 1% lower, so the AMD card leads by 1%.

These delta values frame the AMD card's position in the professional GPU hierarchy. It is competitive with the Tesla V100 SXM2 and RTX A5500 Mobile, trailing both by small single-digit margins. It beats the Radeon Pro W6600X and Radeon Pro Vega II by similarly small margins. The performance neighborhood is consistent: the W7900 trades places with other high-end professional accelerators within a few percentage points.

For the Intel Arc Pro B60 Dual, there are no rival comparisons in the database and no benchmark scores, so no delta values can be established. The card's percentile rank of 50 places it at the median of all GPUs in the database, but that rank is based on no recorded measurements, which limits its interpretability. The only concrete performance indicators for the Intel card are its specification-derived rates: 12.29 TFLOPS FP32, 192.0 GPixel/s pixel rate, and 384.0 GTexel/s texture rate. Those figures are far below the AMD card's corresponding numbers, and they are the only basis for a performance estimate in the absence of actual test results.

Specification Differences

The two cards differ across nearly every specification field. The table below isolates the fields where the two parts diverge.

| Specification | AMD Radeon PRO W7900 | Intel Arc Pro B60 Dual |

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

| Chip | Navi 31 | BMG-G21 |

| Architecture | RDNA 3.0 | Xe2-HPG |

| Generation | Radeon Pro Navi (Navi III Series) | Battlemage (Pro Series) |

| Transistors | 57,700 million | 19,600 million |

| Die size | 529 mm² | 272 mm² |

| Transistor density | 109.1M / mm² | 72.1M / mm² |

| Base clock | 1760 MHz | 2000 MHz |

| Boost clock | 2495 MHz | 2400 MHz |

| Memory clock | 2250 MHz, 18 Gbps effective | 2375 MHz, 19 Gbps effective |

| Memory size | 48 GB | 24 GB |

| Memory bus width | 384 bit | 192 bit |

| Memory bandwidth | 864.0 GB/s | 456.0 GB/s |

| Shading units | 6144 | 2560 |

| TMUs | 384 | 160 |

| ROPs | 192 | 80 |

| Ray tracing cores | 96 | 20 |

| Pixel rate | 479.0 GPixel/s | 192.0 GPixel/s |

| Texture rate | 958.1 GTexel/s | 384.0 GTexel/s |

| FP32 | 61.32 TFLOPS | 12.29 TFLOPS |

| FP16 | 61.32 TFLOPS (1:1) | 24.58 TFLOPS (2:1) |

| TDP | 295 W | 400 W |

| Slot width | Triple-slot | Dual-slot |

| Power connectors | 2x 8-pin | 1x 16-pin |

| Suggested PSU | 600 W | 800 W |

| Bus interface | PCIe 4.0 x16 | PCIe 5.0 x8 |

| Display outputs | 3x DisplayPort 2.1, 1x mini-DisplayPort 2.1 | 4x mini-DisplayPort 2.1 |

| Length | 280 mm | 300 mm |

| Width | 51 mm | 40 mm |

| Release date | 2023-05-25 | 2025-09-04 |

| Launch MSRP | 3,999 USD | 1,199 USD |

The release dates place the AMD card in 2023 and the Intel card in 2025. Both are active production parts. The AMD card's predecessor is the Radeon Pro Vega, while the Intel card has no predecessor listed. Neither card has a successor listed. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are 5 nm TSMC parts, and both have a height of 110 mm.

FAQ

Q: Which card has more memory bandwidth?

A: The AMD Radeon PRO W7900 has 864.0 GB/s of bandwidth from a 384-bit bus and 48 GB of GDDR6 memory. The Intel Arc Pro B60 Dual has 456.0 GB/s from a 192-bit bus and 24 GB of GDDR6 memory.

Q: How do the FP32 compute figures compare?

A: The AMD card delivers 61.32 TFLOPS of FP32 performance. The Intel card delivers 12.29 TFLOPS, which is 49.03 TFLOPS lower.

Q: Are both cards built on the same manufacturing process?

A: Yes, both use a 5 nm process at TSMC. The AMD chip measures 529 mm² with 57,700 million transistors, while the Intel chip measures 272 mm² with 19,600 million transistors.

Q: What benchmark scores exist for the Intel Arc Pro B60 Dual?

A: The database has no recorded benchmark scores for the Intel card. Its average benchmark score is 0, and its percentile rank is 50. The AMD card has a Geekbench OpenCL score of 84,379 and a Geekbench Vulkan score of 137,070.

Q: Which card has more ray tracing cores?

A: The AMD Radeon PRO W7900 has 96 ray tracing cores, compared to 20 on the Intel Arc Pro B60 Dual.

Q: How does the AMD card compare to its nearest rivals?

A: The AMD card's average score of 110,725 is 3.2% above the Radeon Pro W6600X, 1% above the Radeon Pro Vega II, 2.8% below the RTX A5500 Mobile, and 3.2% below the Tesla V100 SXM2 16 GB.