Intel Arc Pro B60 Dual vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between these two cards, but the comparison is complicated by the fact that the Intel Arc Pro B60 Dual has no individual benchmark scores in the database. The NVIDIA GeForce RTX 5090 Mobile, by contrast, has a full set of recorded measurements across ten tests. Its average benchmark score of 45152 places it in the 84th percentile of all GPUs, which is a strong showing for a mobile part. The Arc Pro B60 Dual sits at the 50th percentile with an average benchmark score of zero, meaning the database has not yet captured any performance measurements for it. This does not indicate the card is slow, only that the data is incomplete.

What can be analyzed directly is the RTX 5090 Mobile's position against its nearest rivals. It is effectively tied with the AMD Radeon Pro 5500 XT, which posts an average score of 45384, a delta of negative 0.5 percent. It edges out the NVIDIA GeForce RTX 4070 Ti, which scores 44795, giving the mobile card a 0.8 percent advantage. The Intel Arc A730M scores 45592, placing it 1 percent ahead of the RTX 5090 Mobile, while the NVIDIA RTX 5880 Ada Generation leads by 1.8 percent with a score of 45972. These are tight margins, all within roughly two percent of each other, which suggests the RTX 5090 Mobile delivers desktop-class performance in a mobile form factor.

Looking at the individual benchmark scores for the RTX 5090 Mobile, the strongest results come from the compute and graphics tests. In Geekbench OpenCL it scores 201834, and in Geekbench Vulkan it scores 198405. These are the two highest raw scores in its recorded set. The PassMark G3D score is 30034, and the PassMark GPU Compute score is 13401. The DirectX tests show a different pattern: DirectX 9 scores 324, DirectX 11 scores 269, DirectX 10 scores 183, and DirectX 12 scores 138. The 2D graphics score is 1057. These numbers indicate that the card's raw compute throughput is far ahead of its legacy DirectX performance, which is typical for a modern architecture optimized for current APIs.

FAQ

Q: Does the Intel Arc Pro B60 Dual have any benchmark scores in the database?

A: No. The database records zero benchmarks for the Arc Pro B60 Dual, and its average benchmark score is 0. The NVIDIA GeForce RTX 5090 Mobile has ten recorded benchmark scores with an average of 45152.

Q: How does the RTX 5090 Mobile compare to its closest rival, the AMD Radeon Pro 5500 XT?

A: The RTX 5090 Mobile scores 45152 on average, while the Radeon Pro 5500 XT scores 45384. That is a delta of negative 0.5 percent, making the two effectively equal in average performance.

Q: What is the highest single benchmark score recorded for the RTX 5090 Mobile?

A: The highest score is 201834 in Geekbench OpenCL. The Geekbench Vulkan score is nearly as high at 198405.

Q: Which DirectX version shows the lowest score for the RTX 5090 Mobile?

A: DirectX 12 shows the lowest score at 138. DirectX 9 scores 324, DirectX 11 scores 269, and DirectX 10 scores 183.

Q: What is the RTX 5090 Mobile's percentile ranking among all GPUs?

A: It ranks in the 84th percentile of all GPUs. The Arc Pro B60 Dual ranks in the 50th percentile.

Q: Does the RTX 5090 Mobile outperform the NVIDIA RTX 5880 Ada Generation?

A: No. The RTX 5880 Ada Generation scores 45972, which is 1.8 percent higher than the RTX 5090 Mobile's 45152.

Architecture Differences

The two cards use fundamentally different architectures built for different purposes. The Intel Arc Pro B60 Dual uses the BMG-G21 chip with the Xe2-HPG architecture, part of the Battlemage Pro Series. It is manufactured on TSMC's 5 nm process with 19,600 million transistors on a 272 mm² die, giving a transistor density of 72.1 million per square millimeter. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip with the Blackwell 2.0 architecture, part of the GeForce 50 Mobile series. It is also on a 5 nm process from TSMC, but packs 45,600 million transistors on a 378 mm² die, for a density of 120.6 million per square millimeter.

The compute resources differ sharply. The Intel card has 2560 shading units, 160 texture mapping units, and 80 raster output units. It includes 20 ray tracing cores but no dedicated tensor cores. The NVIDIA card has 10496 shading units, 328 TMUs, and 112 ROPs. It includes 82 ray tracing cores and 328 tensor cores. The FP32 throughput tells the story: Intel delivers 12.29 TFLOPS, while NVIDIA delivers 31.80 TFLOPS. For FP16, Intel reaches 24.58 TFLOPS using a 2:1 ratio, while NVIDIA sustains 31.80 TFLOPS at a 1:1 ratio, meaning it does not rely on rate doubling for half-precision work.

Memory configurations also diverge. The Intel card uses 24 GB of GDDR6 on a 192-bit bus, yielding 456.0 GB/s of bandwidth. The NVIDIA card uses 24 GB of GDDR7 on a 256-bit bus, nearly doubling bandwidth to 896.0 GB/s. Clock speeds reflect their different roles: Intel runs at a 2000 MHz base and 2400 MHz boost, while NVIDIA runs at a 990 MHz base and 1515 MHz boost. The higher transistor count and wider memory bus on the NVIDIA part compensate for its lower clocks.

Power and physical design are opposites. The Intel card is a dual-slot, 300 mm long, 110 mm tall, and 40 mm wide add-in board with a 400 W TDP, a single 16-pin power connector, and a suggested 800 W power supply. The NVIDIA card is an integrated graphics package with a 95 W TDP, no power connectors, and no listed dimensions. The Intel card connects via PCIe 5.0 x8 and outputs four mini-DisplayPort 2.1 connections. The NVIDIA card uses PCIe 5.0 x16 and its display outputs are listed as portable device dependent.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card's predecessor is the GeForce 40 Mobile series, while the Intel card has no listed predecessor. The Intel card launched on 2025-09-04 with a launch MSRP of 1,199 USD. The NVIDIA card launched earlier on 2025-03-26 with no MSRP listed.

The Verdict

The data supports a clear split. For raw compute and modern API workloads, the NVIDIA GeForce RTX 5090 Mobile is the stronger part. Its 31.80 TFLOPS FP32 throughput is more than double the Intel card's 12.29 TFLOPS. Its memory bandwidth of 896.0 GB/s is nearly double the Intel card's 456.0 GB/s. Its 10496 shading units and 328 tensor cores give it a massive advantage in shader-heavy and AI-accelerated tasks. The recorded benchmark results confirm this: the RTX 5090 Mobile sits in the 84th percentile and matches or beats desktop cards like the RTX 4070 Ti and Radeon Pro 5500 XT.

The Intel Arc Pro B60 Dual is a different kind of product. It is a professional workstation card with a 400 W TDP, dual-slot cooling, and four mini-DisplayPort outputs. Its 24 GB of GDDR6 memory matches the NVIDIA card's capacity, and its 20 ray tracing cores provide hardware RT support. Its 50th percentile ranking and lack of recorded benchmarks mean the database cannot yet confirm its real-world performance. What the data does show is that it is built for a different environment: a full-size PCIe card with a 16-pin connector and an 800 W PSU recommendation, rather than an integrated mobile package.

For a laptop or compact system, the RTX 5090 Mobile is the only viable choice, as the Intel card is a dual-slot desktop board. For a workstation needing professional display outputs and a fixed power budget, the Intel card offers a known configuration with 24 GB of memory and a 1,199 USD launch MSRP. The RTX 5090 Mobile has no MSRP listed, so direct cost comparison is impossible. Based strictly on measured performance and architectural resources, the NVIDIA card dominates in every compute metric recorded. The Intel card's advantage lies in its form factor and professional feature set, not in raw speed.

Specification Differences

The two cards differ in nearly every measurable specification except memory capacity and API support. Both have 24 GB of memory, but the Intel card uses GDDR6 while the NVIDIA card uses GDDR7. The bus widths differ, 192-bit for Intel versus 256-bit for NVIDIA, and bandwidth is 456.0 GB/s versus 896.0 GB/s. The Intel card has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The NVIDIA card has 10496 shading units, 328 TMUs, 112 ROPs, and 82 RT cores. The NVIDIA card also has 328 tensor cores, which the Intel card lacks entirely.

Clocks are reversed in character. The Intel card runs at 2000 MHz base and 2400 MHz boost, while the NVIDIA card runs at 990 MHz base and 1515 MHz boost. The Intel card's memory runs at 2375 MHz (19 Gbps effective), while the NVIDIA card's memory runs at 1750 MHz (28 Gbps effective). FP32 output is 12.29 TFLOPS for Intel and 31.80 TFLOPS for NVIDIA. FP16 output is 24.58 TFLOPS (2:1) for Intel and 31.80 TFLOPS (1:1) for NVIDIA.

The Intel card is a dual-slot, 300 mm by 110 mm by 40 mm board with a 400 W TDP, one 16-pin connector, and an 800 W suggested PSU. The NVIDIA card is an IGP with a 95 W TDP, no connectors, and no dimensions. The Intel card uses PCIe 5.0 x8 and has four mini-DisplayPort 2.1 outputs. The NVIDIA card uses PCIe 5.0 x16 and its outputs are portable device dependent. The Intel card has a release date of 2025-09-04 and a launch MSRP of 1,199 USD. The NVIDIA card has a release date of 2025-03-26 and no MSRP.

The chips are also very different physically. Intel's BMG-G21 has 19,600 million transistors on a 272 mm² die. NVIDIA's GB203 has 45,600 million transistors on a 378 mm² die. Transistor density is 72.1 million per square millimeter for Intel and 120.6 million per square millimeter for NVIDIA. Both use TSMC's 5 nm process. The NVIDIA card has a listed predecessor, the GeForce 40 Mobile series, while the Intel card does not.

Where Each One Wins

The NVIDIA GeForce RTX 5090 Mobile wins in every measured performance category. Its FP32 throughput of 31.80 TFLOPS is 159 percent higher than the Intel card's 12.29 TFLOPS. Its FP16 throughput of 31.80 TFLOPS at 1:1 ratio is 29 percent higher than Intel's 24.58 TFLOPS at 2:1 ratio. Its texture rate of 496.9 GTexel/s beats Intel's 384.0 GTexel/s by 29 percent. Its pixel rate of 169.7 GPixel/s is lower than Intel's 192.0 GPixel/s, a 12 percent deficit, which is the one metric where Intel holds an advantage. Its memory bandwidth of 896.0 GB/s is 96 percent higher than Intel's 456.0 GB/s.

The Intel card wins in form factor and professional connectivity. It is a standalone dual-slot card with four mini-DisplayPort 2.1 outputs, making it suitable for multi-monitor workstation setups. The NVIDIA card's display outputs depend on the portable device it is installed in. The Intel card also has a higher pixel rate, 192.0 GPixel/s versus 169.7 GPixel/s, which can benefit certain rasterization-heavy workloads despite its lower overall compute.

The RTX 5090 Mobile wins in power efficiency on paper, with a 95 W TDP versus 400 W, but this reflects its integrated mobile nature rather than a direct efficiency comparison. The Intel card requires an 800 W power supply, while the NVIDIA card requires none beyond what the host laptop provides. For compute-heavy tasks like OpenCL or Vulkan workloads, the database shows the NVIDIA card scoring 201834 and 198405 respectively, confirming its strength. For legacy DirectX 9 workloads, it scores 324, which is its best legacy result. The Intel card has no recorded scores, so its wins cannot be quantified, only inferred from its architecture and professional positioning.