Intel UHD Graphics 610 vs NVIDIA GeForce GTX 860M Comparison

The NVIDIA GeForce GTX 860M and the Intel UHD Graphics 610 represent two completely different philosophies in mobile graphics: one is a dedicated discrete GPU designed for gaming laptops, while the other is an integrated solution baked into a low-power processor. The benchmark data shows an overwhelming performance gap, with the GTX 860M winning both head-to-head tests by margins that are difficult to overstate. This analysis breaks down exactly where these two parts differ, how they stack up in real workloads, and which type of user should consider each.

Head-to-Head Benchmarks

The two head-to-head benchmark results paint a stark picture of the performance chasm between these GPUs. In the Geekbench OpenCL test, the NVIDIA GeForce GTX 860M scores 10,461 points, while the Intel UHD Graphics 610 manages only 2,692 points. That translates to a delta of 288.6% in favor of the NVIDIA part — meaning the GTX 860M delivers nearly four times the raw compute throughput in this OpenCL workload. The Vulkan results tell a similar story, with the GTX 860M scoring 9,648 against Intel’s 2,811, a 243.2% advantage.

Looking at the broader benchmark suite, the GTX 860M’s average benchmark score of 2,967 places it in the 19th percentile of all GPUs, while the UHD 610 sits just one percentile lower at 18th with an average score of 2,752. This narrow percentile gap is misleading; the Intel part’s average is pulled up by its relatively strong Geekbench scores, but it lacks the extensive PassMark coverage that the NVIDIA part enjoys. The GTX 860M has ten recorded benchmarks spanning DirectX 9 through 12, G2D, G3D, and compute workloads, while the UHD 610 only has two Geekbench entries. In the PassMark G3D test, the GTX 860M scores 3,081, and its PassMark GPU compute score is 1,251 — numbers the Intel part simply cannot match because it doesn't have comparable data.

The nearest rival data contextualizes the GTX 860M’s standing. It sits 0.5% ahead of the GeForce GTX 750 Ti (2,953 average), 0.5% behind the GeForce 820A (2,983), and 1.5% ahead of the Quadro P600 (2,923). Interestingly, the RTX 4060 Ti 8 GB appears in its rival list with a score of 2,913, putting the GTX 860M 1.9% ahead — a quirk of the aggregate scoring methodology. For the UHD 610, its closest rival is the GeForce 820M at 2,784, with the Intel part trailing by 1.1%. The UHD 610 also sits 1.5% behind the RTX 3060 Ti GDDR6X (2,795) and 1.7% behind the AMD Radeon 550 (2,801), while edging out the RTX 5070 SUPER by 2.3% (2,690). These comparisons underscore that while both parts occupy the low end of the performance spectrum, the NVIDIA discrete GPU consistently outperforms the Intel integrated solution across every comparable workload.

Architecture Differences

The architectural divide between these two GPUs is fundamental. The GTX 860M is built on NVIDIA’s Kepler architecture, using the GK104 chip fabricated on a 28 nm process at TSMC. That chip packs 3,540 million transistors into a 294 mm² die, yielding a transistor density of 12.0 million per mm². The UHD 610, by contrast, uses Intel’s Generation 9.5 architecture, specifically the Comet Lake GT1 chip, built on Intel’s 14 nm+++ process. Intel does not disclose transistor count or die size for this part, but the process node difference alone — 28 nm versus 14 nm+++ — suggests the Intel solution is significantly simpler and smaller.

The compute resources differ by an order of magnitude. The GTX 860M has 1,152 shading units, 96 texture mapping units, and 16 ROPs. The UHD 610 has just 96 shading units, 12 TMUs, and 2 ROPs. That’s a 12x difference in shading units and an 8x difference in TMUs, which directly explains the massive gap in texture and pixel throughput. The GTX 860M achieves 87.84 GTexel/s and 21.96 GPixel/s, while the UHD 610 manages only 12.60 GTexel/s and 2.100 GPixel/s. Floating-point performance follows the same pattern: the NVIDIA part delivers 2.108 TFLOPS of FP32 compute, versus 201.6 GFLOPS for Intel — a 10.5x advantage. The UHD 610 does offer FP16 at 403.2 GFLOPS (2:1 ratio), but the GTX 860M has no listed FP16 capability.

Clock speeds tell an interesting story. The GTX 860M runs at a 797 MHz base clock with a 915 MHz boost, while the UHD 610 has a much lower 350 MHz base but boosts to 1,050 MHz. Despite the Intel part’s higher boost clock, it cannot compensate for its drastically reduced core count. Memory architecture is another major differentiator: the GTX 860M uses 2 GB of dedicated GDDR5 memory on a 128-bit bus, delivering 80.00 GB/s of bandwidth at 5 Gbps effective. The UHD 610 relies entirely on system shared memory, with bus width and bandwidth described as “System Dependent” — meaning performance varies with the host system’s RAM configuration. The NVIDIA part also has its own memory clock of 1,250 MHz, whereas Intel’s memory clock is simply “System Shared.”

FAQ

Q: Which GPU is faster in Geekbench OpenCL and Vulkan tests?

A: The NVIDIA GeForce GTX 860M wins both. In OpenCL, it scores 10,461 versus 2,692 for the Intel UHD 610, a 288.6% advantage. In Vulkan, the GTX 860M scores 9,648 against 2,811, a 243.2% lead.

Q: How do their shading unit counts compare?

A: The GTX 860M has 1,152 shading units, while the UHD 610 has only 96. This 12x difference in core count is the primary driver of the performance gap between the two parts.

Q: What process nodes are these GPUs built on?

A: The GTX 860M uses a 28 nm process at TSMC, while the UHD 610 uses Intel’s 14 nm+++ process. The NVIDIA chip contains 3,540 million transistors on a 294 mm² die.

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12, but at different feature levels. The GTX 860M supports DirectX 12 (11_0), while the UHD 610 supports DirectX 12 (12_1). The Intel part also supports Vulkan 1.3, compared to Vulkan 1.2.175 for NVIDIA.

Q: What is the memory configuration for each GPU?

A: The GTX 860M has 2 GB of dedicated GDDR5 memory on a 128-bit bus with 80.00 GB/s bandwidth. The UHD 610 uses system shared memory, with its bandwidth being system dependent.

Q: What are their average benchmark scores and percentiles?

A: The GTX 860M has an average benchmark score of 2,967, placing it in the 19th percentile of all GPUs. The UHD 610 has an average score of 2,752, placing it in the 18th percentile.

Specification Differences

| Specification | NVIDIA GeForce GTX 860M | Intel UHD Graphics 610 |

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

| Architecture | Kepler | Generation 9.5 |

| Process Node | 28 nm | 14 nm+++ |

| Foundry | TSMC | Intel |

| Transistors | 3,540 million | Not disclosed |

| Die Size | 294 mm² | Not disclosed |

| Transistor Density | 12.0M / mm² | Not disclosed |

| Base Clock | 797 MHz | 350 MHz |

| Boost Clock | 915 MHz | 1,050 MHz |

| Memory Clock | 1,250 MHz (5 Gbps effective) | System Shared |

| Memory Size | 2 GB | System Shared |

| Memory Type | GDDR5 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

| Memory Bandwidth | 80.00 GB/s | System Dependent |

| Shading Units | 1,152 | 96 |

| TMUs | 96 | 12 |

| ROPs | 16 | 2 |

| Pixel Rate | 21.96 GPixel/s | 2.100 GPixel/s |

| Texture Rate | 87.84 GTexel/s | 12.60 GTexel/s |

| FP32 Performance | 2.108 TFLOPS | 201.6 GFLOPS |

| FP16 Performance | Not listed | 403.2 GFLOPS (2:1) |

| TDP | 75 W | 15 W |

| Bus Interface | PCIe 3.0 x16 | Ring Bus |

| Display Outputs | Portable Device Dependent | Motherboard Dependent |

| DirectX Support | 12 (11_0) | 12 (12_1) |

| Vulkan Support | 1.2.175 | 1.3 |

| Release Date | 2014-03-09 | 2020-04-29 |

The Verdict

The data makes the choice clear for anyone needing graphics performance: the NVIDIA GeForce GTX 860M is in a completely different league. Its 288.6% lead in OpenCL and 243.2% lead in Vulkan are not incremental improvements — they represent a fundamental class difference. The GTX 860M’s 2.108 TFLOPS of FP32 compute, 80.00 GB/s of dedicated memory bandwidth, and 1,152 shading units make it suitable for gaming and GPU-accelerated workloads on a laptop. The UHD 610, with 201.6 GFLOPS, shared system memory, and just 96 shading units, is only adequate for basic desktop tasks like video playback and light 2D rendering.

The UHD 610 does have advantages in power efficiency, with a 15 W TDP versus 75 W for the GTX 860M, and it supports a newer DirectX feature level (12_1 vs 11_0) plus Vulkan 1.3. It also has a higher boost clock at 1,050 MHz compared to 915 MHz. However, these advantages are dwarfed by the raw performance disparity. The GTX 860M sits at the 19th percentile of all GPUs, while the UHD 610 is at the 18th — a near-tie in relative standing — but the GTX 860M’s average score of 2,967 versus 2,752 reflects its consistently higher output across more benchmark categories.

For users choosing between these two, the decision hinges on workload. If the task involves gaming, 3D rendering, or GPU compute, the GTX 860M is the only viable option. Its nearest rivals — the GTX 750 Ti, GeForce 820A, and Quadro P600 — all sit within 1.5% of its average score, confirming it holds its own among entry-level discrete GPUs. The UHD 610, meanwhile, is best suited for systems where power consumption is paramount and graphics demands are minimal. Its nearest rival comparison — trailing the GeForce 820M by 1.1% and the Radeon 550 by 1.7% — places it at the very bottom of even integrated GPU performance. The verdict is unambiguous: the GTX 860M for performance, the UHD 610 only when power draw is the absolute priority and workloads are trivial.