GPU Comparison

FAQ

Q: How does the Intel Arc Pro B60 compare to the NVIDIA GeForce GTX 860M in average benchmark score?

A: The Intel Arc Pro B60 has an average benchmark score of 3182, while the GTX 860M scores 2967. The Arc Pro B60 sits at the 20th percentile of all GPUs, and the GTX 860M sits at the 19th percentile, making both relatively low performers in the overall database.

Q: What is the biggest performance gap between the two cards in the head-to-head tests?

A: The largest delta is in PassMark DirectX 12, where the Arc Pro B60 scores 76 versus the GTX 860M's 13, a 484.6% advantage. The smallest gap is in PassMark DirectX 9, with the Arc Pro B60 leading 179 to 55, a 225.5% difference.

Q: Which card has more memory and bandwidth?

A: The Intel Arc Pro B60 has 24 GB of GDDR6 memory on a 192-bit bus with 456.0 GB/s bandwidth. The GTX 860M has 2 GB of GDDR5 on a 128-bit bus with 80.00 GB/s bandwidth. That is a 12x capacity difference and a 5.7x bandwidth advantage for the Intel card.

Q: Are both cards the same physical size?

A: No. The Arc Pro B60 is a dual-slot card measuring 167 mm (6.6 inches) long, 69 mm (2.7 inches) high, and 40 mm (1.6 inches) wide. The GTX 860M has no listed dimensions and is an IGP (integrated graphics processor) with no power connectors, designed for portable devices.

Q: What are the production statuses of these two GPUs?

A: The Intel Arc Pro B60 is listed as Active and was released on 2025-09-04. The NVIDIA GTX 860M is End-of-life, released on 2014-03-09, with its predecessor being GeForce 700M and successor being GeForce 900M.

Q: Which card supports newer graphics APIs?

A: The Arc Pro B60 supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The GTX 860M supports DirectX 12 (11_0), Vulkan 1.2.175, and OpenGL 4.6. The Intel card also has 20 dedicated ray tracing cores, which the NVIDIA card lacks entirely.

Architecture Differences

The Intel Arc Pro B60 is built on the BMG-G21 chip using the Xe2-HPG architecture, part of the Battlemage (Pro Series) generation. It is manufactured on a 5 nm process at TSMC, packing 19,600 million transistors into a 272 mm² die, giving a transistor density of 72.1M / mm². In contrast, the NVIDIA GeForce GTX 860M uses the GK104 chip with the Kepler architecture, from the GeForce 800M generation, on a 28 nm process at TSMC. That older node houses 3,540 million transistors on a 294 mm² die, with a density of just 12.0M / mm².

The compute configuration differs dramatically. The Arc Pro B60 has 2560 shading units, 160 TMUs, and 80 ROPs, plus 20 dedicated ray tracing cores. The GTX 860M has 1152 shading units, 96 TMUs, and 16 ROPs, with no ray tracing hardware at all. This structural difference explains the massive performance deltas in every benchmark category.

Clock speeds also tell the story of process advantage. The Intel card runs at a 2000 MHz base and 2400 MHz boost, while the NVIDIA part operates at 797 MHz base and 915 MHz boost. Memory clocks further separate them: the Arc Pro B60 runs at 2375 MHz (19 Gbps effective) versus the GTX 860M's 1250 MHz (5 Gbps effective).

The API support reflects their respective eras. The Arc Pro B60 supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the GTX 860M is limited to DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6, but the feature set divergence in modern DX12 and Vulkan titles is substantial.

Power and physical design are equally divergent. The Arc Pro B60 has a 200 W TDP, requires a 550 W power supply, uses a single 8-pin connector, and is a dual-slot card. The GTX 860M has a 75 W TDP, no power connectors, and is an IGP with no dimensions listed, as it is designed for mobile integration.

Head-to-Head Benchmarks

The Intel Arc Pro B60 wins all seven head-to-head benchmark comparisons, with no wins for the GTX 860M. The margins are consistently massive, reflecting both architectural and generational gaps.

In PassMark DirectX 10, the Arc Pro B60 scores 61 versus 15, a 306.7% advantage. The DirectX 11 test shows 122 against 23, a 430.4% delta. DirectX 12 is even more lopsided: 76 versus 13, a 484.6% difference, the largest single gap in the entire comparison.

Legacy DirectX 9 performance favors the Intel card by 225.5%, with scores of 179 and 55. This is the smallest relative margin, but still a decisive win. The 2D test shows 763 versus 226, a 237.6% advantage, indicating that even basic desktop composition tasks are far faster on the newer architecture.

The most important metric for gaming, PassMark G3D, shows the Arc Pro B60 at 14580 versus 3081 for the GTX 860M, a 373.2% lead. Compute workloads are similarly skewed: the GPU compute test shows 7029 versus 1251, a 461.9% gap.

Looking at the nearest rivals for context, the Arc Pro B60's average score of 3182 places it 0.6% above the NVIDIA Quadro P1000 (3163) and 3.5% above the RTX 5080 SUPER (3075). It trails the GT 640 by 0.9% and the GeForce 920M by 3.2%. The GTX 860M's average of 2967 puts it 0.5% above the GTX 750 Ti (2953) and 1.9% above the RTX 4060 Ti 8 GB (2913), while sitting 0.5% below the GeForce 820A (2983) and 1.5% below the Quadro P600 (2923).

Specification Differences

The two cards differ in nearly every measurable specification. The Intel Arc Pro B60 uses a 5 nm process with 19,600 million transistors on a 272 mm² die, while the GTX 860M uses 28 nm with 3,540 million transistors on a 294 mm² die. Transistor density is 72.1M / mm² versus 12.0M / mm².

Memory is a major differentiator: the Arc Pro B60 has 24 GB of GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth, while the GTX 860M has 2 GB of GDDR5 on a 128-bit bus with 80.00 GB/s bandwidth. The Intel card's base clock is 2000 MHz with a 2400 MHz boost; the NVIDIA card runs at 797 MHz base and 915 MHz boost.

Compute resources differ: 2560 shading units, 160 TMUs, and 80 ROPs for the Intel card versus 1152 shading units, 96 TMUs, and 16 ROPs for the NVIDIA. Pixel rate is 192.0 GPixel/s versus 21.96 GPixel/s, texture rate is 384.0 GTexel/s versus 87.84 GTexel/s, and FP32 throughput is 12.29 TFLOPS versus 2.108 TFLOPS. The Arc Pro B60 also lists FP16 at 24.58 TFLOPS (2:1), while the GTX 860M has no FP16 specification.

Power requirements are starkly different: 200 W TDP with a 550 W suggested PSU and one 8-pin connector versus 75 W TDP with no connectors. The Arc Pro B60 uses PCIe 5.0 x8 and has four mini-DisplayPort 2.1 outputs; the GTX 860M uses PCIe 3.0 x16 and has display outputs described as "Portable Device Dependent." The Intel card is 167 mm long, 69 mm high, and 40 mm wide; the NVIDIA card has no listed dimensions.

The Verdict

The data is unambiguous. The Intel Arc Pro B60 wins every single head-to-head benchmark by margins ranging from 225.5% to 484.6%, and it has seven wins to zero for the GTX 860M. The average benchmark scores (3182 versus 2967) reflect a 7.2% overall advantage, but the individual test deltas are far more telling.

The GTX 860M is an end-of-life mobile chip from 2014, built on a 28 nm process with Kepler architecture. It was never designed for modern workloads, and its specifications confirm this: 2 GB of GDDR5, no ray tracing, no FP16 support, and a 128-bit memory bus. Its nearest rival in the database, the GTX 750 Ti, is only 0.5% faster on average, showing that this is a low-tier GPU even among its peers.

The Arc Pro B60, despite being a professional-grade card, also sits at the 20th percentile among all GPUs, with its nearest rival being the Quadro P1000 at a 0.6% delta. This means it is not a high-end part either, but it is a modern, active product with current API support and a 2025 release date.

Anyone considering the GTX 860M for anything beyond legacy compatibility should look at the data and choose the Arc Pro B60 instead. The performance gap is so large that the GTX 860M cannot handle modern DirectX 12 or Vulkan workloads in any practical sense, while the Arc Pro B60 at least offers viable compute and rendering performance for its class.

Where Each One Wins

The Intel Arc Pro B60 wins in every category measured, so the "where each one wins" split is entirely one-sided.

For DirectX 9 legacy titles, the Arc Pro B60 leads by 225.5%, which is the smallest margin but still a dominant win. This suggests that even in older games, the newer architecture's higher clocks and memory bandwidth provide a substantial edge.

In DirectX 10 and DirectX 11, the margins grow to 306.7% and 430.4% respectively, confirming that the Arc Pro B60 is far better suited for any game from the past 15 years. DirectX 12 shows the largest gap at 484.6%, meaning modern titles that rely on DX12 features will run more than five times better on the Intel card.

The 2D test shows a 237.6% advantage, which matters for productivity and desktop use. The G3D test, the most representative of general gaming performance, shows a 373.2% lead. Compute workloads are 461.9% faster on the Arc Pro B60, making it the clear choice for any GPU-accelerated tasks like rendering or scientific computing.

There is no benchmark category where the GTX 860M wins. Its only "advantage" is its 75 W TDP, which is lower than the Arc Pro B60's 200 W, and its IGP form factor, which allows it to fit in portable devices. But even those advantages come with severe trade-offs: no display outputs of its own, no power connector, and no upgrade path.

For a user with a laptop that has a GTX 860M, the data suggests replacing that system entirely. For a desktop builder, the Arc Pro B60 is the only sensible choice between these two, given its overwhelming performance lead in every single test.