Intel Arc Pro B60 Dual vs NVIDIA GeForce RTX 4090 D Comparison

The Verdict

The recorded data presents a stark contrast between two professional-oriented graphics cards from different market positions. The Intel Arc Pro B60 Dual, a Battlemage Pro Series product, occupies the 50th percentile among all GPUs in the database, while the NVIDIA GeForce RTX 4090 D sits at the 98th percentile. The Intel card shows no recorded benchmark entries, whereas the NVIDIA card has three benchmark scores with an average of 178,050. The RTX 4090 D trails its closest rival, the NVIDIA RTX PRO 5000 Blackwell, by 2.2 percent, and the A100 SXM4 80 GB by 3.1 percent. The Intel Arc Pro B60 Dual has no nearest rivals listed, which means the database contains no comparative data for it. The data indicates that the RTX 4090 D is the only option with verified performance metrics, and its scores place it firmly in the top tier of the database. The Intel card, despite its newer release date, has zero benchmark results, so any performance assessment must rely solely on its architectural specifications. Users requiring validated performance should select the NVIDIA card based on its measured results. The Intel card remains an unverified option in the database, with its capabilities undetermined by recorded measurements. The RTX 4090 D's percentile rank of 98 confirms it outperforms the vast majority of GPUs in the database, while the Intel card's 50th percentile suggests a mid-range positioning, although this percentile is not supported by any actual benchmark scores.

Architecture Differences

The two cards employ entirely different GPU architectures from separate manufacturers. The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage Pro Series generation, manufactured on a 5 nm process at TSMC. The NVIDIA GeForce RTX 4090 D utilizes the AD102 chip with the Ada Lovelace architecture, belonging to the GeForce 40-series, also fabricated on a 5 nm process at TSMC. Both cards share the same foundry and process node, but their transistor counts diverge significantly. The Intel chip contains 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1 million per square millimeter. The NVIDIA chip packs 76,300 million transistors into a 609 mm² die, achieving a density of 125.3 million per square millimeter. The NVIDIA chip has nearly four times the transistor count and more than double the die area.

The shading resources differ dramatically. The Intel card features 2,560 shading units, 160 texture mapping units, and 80 render output units. The NVIDIA card contains 14,592 shading units, 456 TMUs, and 176 ROPs. Ray tracing hardware also differs: Intel includes 20 RT cores, while NVIDIA integrates 114 RT cores. NVIDIA additionally provides 456 tensor cores, a feature absent from the Intel specification. Clock speeds show the NVIDIA card running higher, with a base clock of 2280 MHz and a boost of 2520 MHz, compared to Intel's 2000 MHz base and 2400 MHz boost. Memory configurations present another contrast. Both cards offer 24 GB of memory, but Intel uses GDDR6 at 19 Gbps effective on a 192-bit bus, delivering 456.0 GB/s bandwidth. NVIDIA uses GDDR6X at 21 Gbps effective on a 384-bit bus, achieving 1.01 TB/s bandwidth. The NVIDIA memory subsystem provides more than double the bandwidth.

The power and physical specifications also vary. The Intel card consumes 400 W with a dual-slot design, while the NVIDIA card draws 425 W in a triple-slot format. Both use a 1x 16-pin power connector and recommend an 800 W power supply. The Intel card measures 300 mm by 110 mm by 40 mm, while the NVIDIA card is 304 mm by 137 mm by 61 mm. Interface differences include Intel's PCIe 5.0 x8 versus NVIDIA's PCIe 4.0 x16. Display outputs differ as well: Intel provides four mini-DisplayPort 2.1 connectors, while NVIDIA offers one HDMI 2.1 and three DisplayPort 1.4a outputs. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The Intel card was released on September 4, 2025, with its production status listed as Active, while the NVIDIA card launched on December 27, 2023, and is now marked as End-of-life. The NVIDIA card's predecessor is the GeForce 30 series, and its successor is the GeForce 50 series.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark comparisons between these two cards, and the wins counter shows zero victories for either side. The Intel Arc Pro B60 Dual has no benchmark entries at all, with an average benchmark score of zero. The NVIDIA GeForce RTX 4090 D, however, has three recorded benchmark results. In the 3DMark Steel Nomad DX12 test, the RTX 4090 D scores 8,587. In Geekbench OpenCL, it achieves 278,621. In Geekbench Vulkan, it records 246,941. These three scores produce an average benchmark score of 178,050 for the NVIDIA card.

The RTX 4090 D's nearest rivals provide context for its performance. The NVIDIA RTX PRO 5000 Blackwell has an average score of 182,109, which is 2.2 percent higher than the RTX 4090 D. The NVIDIA A100 SXM4 80 GB averages 183,725, exceeding the RTX 4090 D by 3.1 percent. The NVIDIA RTX 5000 Ada Generation averages 184,664, a 3.6 percent advantage. The NVIDIA A100 SXM4 40 GB averages 187,147, which is 4.9 percent above the RTX 4090 D. These deltas indicate that the RTX 4090 D, while strong, sits slightly below four other NVIDIA professional cards in the database's average scoring. The benchmark data shows the RTX 4090 D delivering compute scores that place it within a narrow band of its rivals, never more than 5 percent behind any of them. The absence of Intel benchmark data means no direct comparison is possible. The Geekbench OpenCL score of 278,621 versus the Vulkan score of 246,941 suggests the RTX 4090 D performs better under OpenCL workloads in this specific test, with a difference of 31,680 points. The 3DMark score of 8,587 is a separate metric focused on graphics workload, not directly comparable to the Geekbench compute scores.

FAQ

Q: What is the average benchmark score for the Intel Arc Pro B60 Dual?

A: The Intel Arc Pro B60 Dual has an average benchmark score of 0, as no benchmark entries are recorded in the database for this card.

Q: What are the benchmark scores for the NVIDIA GeForce RTX 4090 D?

A: The RTX 4090 D scores 8,587 in 3DMark Steel Nomad DX12, 278,621 in Geekbench OpenCL, and 246,941 in Geekbench Vulkan, resulting in an average of 178,050.

Q: How does the RTX 4090 D compare to its nearest rival, the RTX PRO 5000 Blackwell?

A: The RTX PRO 5000 Blackwell has an average score of 182,109, which is 2.2 percent higher than the RTX 4090 D's average of 178,050.

Q: Which card has a higher transistor density?

A: The NVIDIA RTX 4090 D has a transistor density of 125.3 million per square millimeter, while the Intel Arc Pro B60 Dual has 72.1 million per square millimeter.

Q: What memory bandwidth does each card provide?

A: The Intel Arc Pro B60 Dual delivers 456.0 GB/s with GDDR6 memory on a 192-bit bus, while the NVIDIA RTX 4090 D delivers 1.01 TB/s with GDDR6X on a 384-bit bus.

Q: What is the production status of each card?

A: The Intel Arc Pro B60 Dual is listed as Active, while the NVIDIA GeForce RTX 4090 D is listed as End-of-life.

Where Each One Wins

The Intel Arc Pro B60 Dual wins in no recorded benchmark categories, as the database contains zero benchmark scores for this card. Its only advantages appear in its specification sheet. The Intel card uses a PCIe 5.0 x8 interface, which is a newer bus standard than the NVIDIA card's PCIe 4.0 x16. The Intel card also provides four mini-DisplayPort 2.1 outputs, while the NVIDIA card offers one HDMI 2.1 and three DisplayPort 1.4a outputs. The Intel card is physically smaller, measuring 300 mm in length, 110 mm in height, and 40 mm in width, compared to the NVIDIA card's 304 mm, 137 mm, and 61 mm. The Intel card is dual-slot, while the NVIDIA card is triple-slot. The Intel card has a lower TDP of 400 W versus 425 W for the NVIDIA card. The Intel card was released on September 4, 2025, making it a more recent product, and it remains in Active production status.

The NVIDIA GeForce RTX 4090 D wins in every measurable performance category. Its 73.54 TFLOPS FP32 compute far exceeds the Intel card's 12.29 TFLOPS. In FP16, the NVIDIA card achieves 73.54 TFLOPS at a 1:1 ratio, while the Intel card manages 24.58 TFLOPS at a 2:1 ratio. The NVIDIA card's pixel rate of 443.5 GPixel/s and texture rate of 1,149.1 GTexel/s dwarf the Intel card's 192.0 GPixel/s and 384.0 GTexel/s. The NVIDIA memory bandwidth of 1.01 TB/s more than doubles the Intel's 456.0 GB/s. The NVIDIA card has 14,592 shading units versus 2,560, 456 TMUs versus 160, 176 ROPs versus 80, and 114 RT cores versus 20. The NVIDIA card includes 456 tensor cores, which the Intel card lacks entirely. The NVIDIA card holds three benchmark scores in the database, all of which contribute to its 98th percentile ranking, while the Intel card's percentile of 50 is unsupported by any measured data. The RTX 4090 D also has a higher base clock of 2280 MHz and boost clock of 2520 MHz, compared to the Intel card's 2000 MHz and 2400 MHz. The NVIDIA card's memory runs at 21 Gbps effective versus the Intel's 19 Gbps effective.

Specification Differences

The two cards differ across multiple specification fields. The Intel Arc Pro B60 Dual uses the BMG-G21 chip with Xe2-HPG architecture from the Battlemage Pro Series, while the NVIDIA RTX 4090 D uses the AD102 chip with Ada Lovelace architecture from the GeForce 40-series. Transistor counts differ: 19,600 million for Intel versus 76,300 million for NVIDIA. Die sizes are 272 mm² for Intel and 609 mm² for NVIDIA. Transistor density is 72.1 million per square millimeter for Intel and 125.3 million for NVIDIA. Base clocks are 2000 MHz for Intel and 2280 MHz for NVIDIA. Boost clocks are 2400 MHz for Intel and 2520 MHz for NVIDIA. Memory speeds are 19 Gbps effective for Intel and 21 Gbps effective for NVIDIA. Memory types are GDDR6 for Intel and GDDR6X for NVIDIA. Bus widths are 192-bit for Intel and 384-bit for NVIDIA. Memory bandwidth is 456.0 GB/s for Intel and 1.01 TB/s for NVIDIA.

Shading units are 2,560 for Intel and 14,592 for NVIDIA. TMUs are 160 for Intel and 456 for NVIDIA. ROPs are 80 for Intel and 176 for NVIDIA. RT cores are 20 for Intel and 114 for NVIDIA. Tensor cores are absent for Intel and 456 for NVIDIA. Pixel rates are 192.0 GPixel/s for Intel and 443.5 GPixel/s for NVIDIA. Texture rates are 384.0 GTexel/s for Intel and 1,149.1 GTexel/s for NVIDIA. FP32 compute is 12.29 TFLOPS for Intel and 73.54 TFLOPS for NVIDIA. FP16 compute is 24.58 TFLOPS (2:1) for Intel and 73.54 TFLOPS (1:1) for NVIDIA. TDP is 400 W for Intel and 425 W for NVIDIA. Slot widths are dual-slot for Intel and triple-slot for NVIDIA. Bus interfaces are PCIe 5.0 x8 for Intel and PCIe 4.0 x16 for NVIDIA. Display outputs are four mini-DisplayPort 2.1 for Intel and one HDMI 2.1 with three DisplayPort 1.4a for NVIDIA. Dimensions are 300 mm by 110 mm by 40 mm for Intel and 304 mm by 137 mm by 61 mm for NVIDIA. Release dates are September 4, 2025 for Intel and December 27, 2023 for NVIDIA. Production status is Active for Intel and End-of-life for NVIDIA. The launch MSRP for Intel is 1,199 USD, and for NVIDIA it is 1,599 USD.