Intel Arc Pro B60 vs NVIDIA GeForce 920MX Comparison

The NVIDIA GeForce 920MX and Intel Arc Pro B60 represent two vastly different eras and market positions. The 920MX is a 2016 entry-level mobile GPU built on the 28nm Maxwell architecture, designed for basic laptop tasks. The Arc Pro B60 is a 2025 professional desktop GPU on Intel's 5nm Xe2-HPG architecture, engineered for workstation workloads. The benchmark data shows a stark contrast in raw performance, but also reveals an unusual overlap in their average scores due to differing test suites. This analysis will break down their specifications, benchmark results, and architectural differences to determine which GPU is appropriate for which use case.

FAQ

Q: How do the average benchmark scores compare between the two GPUs?

A: The NVIDIA GeForce 920MX has an average benchmark score of 3528, while the Intel Arc Pro B60 has an average score of 3182. This is a surprising result, showing the 920MX scoring about 10.9% higher on average, despite being significantly older and less powerful in raw specifications.

Q: What are the most significant performance differences in the raw compute benchmarks?

A: The Intel Arc Pro B60 demonstrates overwhelming dominance in compute-heavy tests. It scores 14580 in Passmark G3D and 7029 in Passmark GPU Compute. The 920MX's available benchmarks are limited to Geekbench OpenCL (4068) and Vulkan (2987), which do not directly correspond to the Passmark tests.

Q: Which GPU has a higher transistor density?

A: The Intel Arc Pro B60 has a dramatically higher transistor density. It packs 19,600 million transistors into a 272 mm² die, achieving a density of 72.1M / mm². In contrast, the GeForce 920MX has only 1,020 million transistors on a 77 mm² die, resulting in a density of just 13.2M / mm².

Q: How does the memory bandwidth differ between the two cards?

A: The Intel Arc Pro B60 offers 456.0 GB/s of bandwidth from its 24 GB GDDR6 memory on a 192-bit bus. The GeForce 920MX is limited to 14.40 GB/s from its 2 GB DDR3 memory on a 64-bit bus. This represents a massive 31.7x advantage for the Intel card.

Q: What is the percentile ranking for each GPU compared to all other GPUs?

A: The GeForce 920MX falls in the 21st percentile, while the Intel Arc Pro B60 is in the 20th percentile. Despite their massive generational and performance gap, both GPUs are ranked near the bottom of the overall GPU performance distribution.

Q: What are the closest rivals for each GPU based on average score?

A: The 920MX's nearest rival is the NVIDIA GeForce GT 545, which has an average score of 3594, placing it 1.8% higher. The Arc Pro B60's nearest rival is the NVIDIA Quadro P1000, with an average score of 3163, which is 0.6% lower than the Intel card.

The Verdict

The data presents a clear yet counterintuitive picture. For anyone using the GeForce 920MX, the decision is straightforward: the Intel Arc Pro B60 is categorically superior in every raw specification that matters for modern workloads. It offers 24 GB of GDDR6 memory versus 2 GB of DDR3, has 2560 shading units versus 256, and delivers 12.29 TFLOPS of FP32 performance versus 508.4 GFLOPS. The Arc Pro B60 is the only choice for any task involving modern 3D rendering, video editing, or GPU-accelerated compute.

However, the average benchmark scores tell a different story. The 920MX's average of 3528 is higher than the Arc Pro B60's 3182. This is likely due to the benchmark suites used. The 920MX was tested with Geekbench OpenCL and Vulkan, while the Arc Pro B60 was tested with 3DMark and Passmark DirectX tests. The Passmark DirectX 10, 11, and 12 scores for the Arc Pro B60 are notably low (61, 122, and 76 respectively), which significantly drags down its average. This suggests that the Intel card's drivers may be optimized for specific professional workloads rather than legacy DirectX performance.

The verdict depends entirely on the user's needs. If the task is rendering a professional 3D scene or processing a large dataset, the Arc Pro B60 wins without question. If the task involves the specific Geekbench tests, the 920MX shows a higher score. But based on the architectural data, the Arc Pro B60 is the only GPU suitable for serious work. The 920MX is an end-of-life product, while the Arc Pro B60 is an active product with modern API support.

Head-to-Head Benchmarks

There are no direct head-to-head benchmark results available in the data. The two GPUs were tested with entirely different benchmark suites, making a direct comparison impossible. The 920MX has scores for Geekbench OpenCL and Vulkan, while the Arc Pro B60 has scores for 3DMark Steel Nomad DX12 and several Passmark tests.

The 920MX scores 4068 on Geekbench OpenCL and 2987 on Geekbench Vulkan. The Arc Pro B60 scores 2646 on 3DMark Steel Nomad DX12, 14580 on Passmark G3D, and 7029 on Passmark GPU Compute. The Arc Pro B60's Passmark G3D score is exceptionally high, indicating strong performance in a general 3D graphics test. Its GPU Compute score of 7029 also shows solid compute capability.

In contrast, the 920MX's scores are moderate, but they are the only data points we have for it. The nearest rival data provides some context. The 920MX is 1.8% slower than the GeForce GT 545 and 2.7% faster than the Quadro 2000M. The Arc Pro B60 is 0.6% faster than the Quadro P1000 and 3.5% faster than the GeForce RTX 5080 SUPER, which is a surprising result given the RTX 5080 SUPER's expected market position.

The lack of shared benchmarks means we cannot state a definitive winner in a head-to-head test. We can only note that the Arc Pro B60 dominates in raw FP32 compute (12.29 TFLOPS vs 508.4 GFLOPS) and texture rate (384.0 GTexel/s vs 23.83 GTexel/s). These are the metrics that indicate real-world rendering capability.

Specification Differences

The specification gap between these two GPUs is enormous. The GeForce 920MX has a base clock of 965 MHz and a boost clock of 993 MHz, while the Arc Pro B60 has a base clock of 2000 MHz and a boost clock of 2400 MHz. The memory configuration is equally disparate: the 920MX has 2 GB of DDR3 with a 64-bit bus, while the Arc Pro B60 has 24 GB of GDDR6 with a 192-bit bus.

The shading units increase from 256 on the 920MX to 2560 on the Arc Pro B60. Texture mapping units go from 24 to 160, and ROPs go from 8 to 80. The pixel rate jumps from 7.944 GPixel/s to 192.0 GPixel/s. The TDP is also vastly different: 16 W for the 920MX versus 200 W for the Arc Pro B60.

The power connectors differ as well. The 920MX uses an MXM module slot with no power connectors, while the Arc Pro B60 is a dual-slot card requiring a 1x 8-pin power connector and a 550 W suggested PSU. The bus interface is PCIe 3.0 x8 for the 920MX and PCIe 5.0 x8 for the Arc Pro B60. The Arc Pro B60 also has specific dimensions of 167 mm in length, while the 920MX is listed as portable device dependent.

Architecture Differences

The architectural divide is a generational chasm. The GeForce 920MX is built on NVIDIA's Maxwell architecture using the GM108S chip, manufactured on a 28 nm process at TSMC. It has 1,020 million transistors on a 77 mm² die. The Intel Arc Pro B60 uses the BMG-G21 chip with the Xe2-HPG architecture, part of the Battlemage Pro Series. It is built on a 5 nm process, also at TSMC, with 19,600 million transistors on a 272 mm² die.

The 920MX supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The Arc Pro B60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The key difference is DirectX 12 Ultimate support on the Intel card, which enables features like ray tracing and mesh shaders. The Arc Pro B60 also has 20 dedicated ray tracing cores, which the 920MX lacks entirely.

The memory architecture is fundamentally different. The 920MX uses DDR3 memory, which is slow and has high latency. The Arc Pro B60 uses GDDR6, which is optimized for high bandwidth. The Arc Pro B60 also supports FP16 compute at 24.58 TFLOPS with a 2:1 ratio, while the 920MX has no listed FP16 capability. The Intel card also features 4x mini-DisplayPort 2.1 outputs, while the 920MX's outputs are portable device dependent.

Where Each One Wins

The Intel Arc Pro B60 wins in almost every measurable category. It is the only choice for any modern 3D workload. Its 12.29 TFLOPS FP32 performance is 24.2 times higher than the 920MX's 508.4 GFLOPS. Its 456.0 GB/s memory bandwidth is 31.7 times higher. Its 192.0 GPixel/s pixel rate is 24.2 times higher. For any task involving rendering, simulation, or GPU compute, the Arc Pro B60 is the definitive winner.

The Arc Pro B60 also wins on features. It has 20 ray tracing cores, DirectX 12 Ultimate support, and 24 GB of GDDR6 memory. This makes it suitable for professional 3D applications, AI inference, and high-resolution video work. Its dual-slot design and 200 W TDP indicate it is meant for a desktop workstation.

The GeForce 920MX's only "win" is in the average benchmark score category, where it scores 3528 versus 3182. This is a statistical artifact of different test suites, not a real performance advantage. The 920MX also wins on power consumption, with a 16 W TDP versus 200 W, making it suitable for low-power laptops. Its MXM module form factor is designed for thin and light notebooks.

For a user with a 920MX, the Arc Pro B60 represents a massive upgrade path. For a user choosing between the two today, the Arc Pro B60 is the only sensible option for any serious work. The 920MX is an end-of-life product that is only useful for basic display output and legacy applications. The Arc Pro B60 is an active product with modern features and a launch MSRP of 499 USD. The data unequivocally points to the Intel card as the superior hardware.