AMD Radeon 780M vs AMD Radeon 860M Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 860M records an average benchmark score of 26401, which is higher than the AMD Radeon 780M's average of 17588. The 860M also sits at the 72nd percentile against all GPUs, while the 780M sits at the 61st percentile.

Q: How do the two GPUs compare in Geekbench OpenCL?

A: The Radeon 860M scores 22759 in Geekbench OpenCL, while the Radeon 780M scores 18602. That is an 18.3% advantage for the 860M in this test.

Q: Which GPU wins in Geekbench Vulkan?

A: The Radeon 780M scores 33683 in Geekbench Vulkan, beating the Radeon 860M's 30043 by 12.1%.

Q: What are the architectural generations of each GPU?

A: The Radeon 780M uses RDNA 3.0 architecture on the Phoenix chip, while the Radeon 860M uses RDNA 3.5 architecture on the Krackan Point chip. Both are built on TSMC's 4 nm process.

Q: Do both GPUs have the same DirectX support?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the TDP for each GPU?

A: Both the Radeon 780M and the Radeon 860M have a TDP of 15 W and use system-shared memory.

Architecture Differences

The Radeon 780M is built on the Phoenix chip with RDNA 3.0 architecture, while the Radeon 860M uses the Krackan Point chip with RDNA 3.5 architecture. Both are manufactured on TSMC's 4 nm process, but the 780M's die size is 178 mm² with 25,390 million transistors, resulting in a transistor density of 142.6M per mm². The 860M's die size and transistor count are not recorded in the database.

The compute configuration differs significantly. The 780M has 768 shading units, 48 texture mapping units, 32 raster output units, and 12 ray tracing cores. The 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 ray tracing cores. This means the 780M carries a 50% higher shading unit count and double the ROP count.

Clock behavior also differs. The 780M has a base clock of 800 MHz and a boost clock of 2900 MHz, while the 860M has a lower 600 MHz base clock but a higher 3000 MHz boost clock. The 780M's pixel rate is 92.80 GPixel/s and its texture rate is 139.2 GTexel/s, compared to the 860M's 48.00 GPixel/s and 96.00 GTexel/s. The 780M delivers 8.909 TFLOPS for both FP32 and FP16 (1:1), while the 860M delivers 3.072 TFLOPS for both.

Both GPUs use system-shared memory with system-dependent bandwidth and connect via PCIe 4.0 x8. Neither has power connectors, and both are integrated graphics processors (IGP). The 780M's display outputs are motherboard-dependent, while the 860M's are portable-device-dependent.

The release dates differ: the 780M launched on January 30, 2024, and the 860M launched on February 28, 2025. The 780M lists its predecessor as Navi II IGP and successor as Navi III IGP, while the 860M also lists its predecessor as Navi II IGP but has no recorded successor.

The Verdict

The recorded data shows a clear split in workload preferences. The Radeon 860M delivers the higher average benchmark score (26401 versus 17588) and ranks at the 72nd percentile, which is 11 percentile points above the 780M. Its nearest rivals include the NVIDIA GeForce MX550 (26421, 0.1% higher), the NVIDIA GeForce RTX 5060 (26331, 0.3% lower), and the AMD Radeon RX 5700 XT 50th Anniversary (26553, 0.6% lower).

The Radeon 780M, by contrast, sits at the 61st percentile with an average score of 17588. Its nearest rivals are the AMD Radeon Pro 560 (17551, 0.2% lower), the NVIDIA GeForce RTX 4060 (17639, 0.3% higher), and the AMD Radeon HD 7790 (17666, 0.4% higher).

For users prioritizing compute-heavy OpenCL workloads, the 860M is the stronger choice based on its 18.3% lead in Geekbench OpenCL. For Vulkan-based tasks, the 780M holds a 12.1% advantage. The 780M also has a substantially larger compute pipeline: 50% more shading units, 50% more TMUs, double the ROPs, and 50% more ray tracing cores.

Given the 860M's higher overall average score and better percentile placement, the data indicates it is the more capable general-purpose part. However, the 780M's Vulkan win and superior rasterization rates (92.80 GPixel/s versus 48.00 GPixel/s) suggest it retains advantages in specific rendering scenarios.

Specification Differences

| Specification | AMD Radeon 780M | AMD Radeon 860M |

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

| Chip | Phoenix | Krackan Point |

| Architecture | RDNA 3.0 | RDNA 3.5 |

| Process Node | 4 nm | 4 nm |

| Transistors | 25,390 million | unknown |

| Die Size | 178 mm² | unknown |

| Transistor Density | 142.6M / mm² | null |

| Base Clock | 800 MHz | 600 MHz |

| Boost Clock | 2900 MHz | 3000 MHz |

| Shading Units | 768 | 512 |

| TMUs | 48 | 32 |

| ROPs | 32 | 16 |

| Ray Tracing Cores | 12 | 8 |

| Pixel Rate | 92.80 GPixel/s | 48.00 GPixel/s |

| Texture Rate | 139.2 GTexel/s | 96.00 GTexel/s |

| FP32 | 8.909 TFLOPS | 3.072 TFLOPS |

| FP16 | 8.909 TFLOPS (1:1) | 3.072 TFLOPS (1:1) |

| Release Date | 2024-01-30 | 2025-02-28 |

| Successor | Navi III IGP | null |

| Display Outputs | Motherboard Dependent | Portable Device Dependent |

Head-to-Head Benchmarks

The database records two direct head-to-head benchmark comparisons between these GPUs.

In Geekbench OpenCL, the Radeon 860M scores 22759 against the Radeon 780M's 18602. The 860M wins this test by 18.3%. This is the 860M's strongest recorded win, and it aligns with the GPU's higher average benchmark score and better percentile ranking. The 860M's nearest rival in this category, the NVIDIA GeForce MX550, scores 26421 on average, just 0.1% above the 860M, which suggests the 860M is competitive with mainstream discrete mobile GPUs.

In Geekbench Vulkan, the Radeon 780M reverses the result. It scores 33683, which is 12.1% ahead of the Radeon 860M's 30043. This is notable because the 780M's Vulkan score alone is higher than its OpenCL score by roughly 81%, while the 860M's Vulkan score is lower than its OpenCL score by about 24%. The 780M's Vulkan performance appears to be an outlier strength relative to its other recorded metrics.

The head-to-head tally is even at one win each. However, the magnitude of the wins is asymmetric: the 860M's OpenCL win is 18.3%, while the 780M's Vulkan win is 12.1%. The 860M also holds a substantial lead in the average benchmark score (26401 versus 17588), which is a 50.1% difference in favor of the 860M.

The 780M's pixel rate of 92.80 GPixel/s is 93.3% higher than the 860M's 48.00 GPixel/s, and its texture rate of 139.2 GTexel/s is 45% higher than the 860M's 96.00 GTexel/s. The FP32 throughput difference is even larger: 8.909 TFLOPS versus 3.072 TFLOPS, a 190% advantage for the 780M. Despite these raw throughput advantages, the 780M's average benchmark score is lower, which indicates that the 860M's architectural improvements in RDNA 3.5 deliver better real-world efficiency per unit of compute.

The 780M's nearest rival list includes the NVIDIA GeForce RTX 4060 at 17639 (0.3% above the 780M), while the 860M's nearest rival list includes the NVIDIA GeForce RTX 5060 at 26331 (0.3% below the 860M). The generational gap between these two integrated GPUs is reflected in the fact that the 860M competes with a newer discrete GPU class, while the 780M sits near older discrete parts.