AMD Radeon 860M vs AMD Radeon 880M Comparison

Head-to-Head Benchmarks

The recorded data contains two direct comparisons between the AMD Radeon 860M and the AMD Radeon 880M, both from the Geekbench suite. The 880M wins both tests by a substantial margin.

In Geekbench OpenCL, the 860M scores 22,759 while the 880M scores 31,285. This represents a 27.3% advantage for the 880M. The OpenCL test measures general-purpose compute throughput, which aligns with the architectural differences between the two parts: the 880M carries 768 shading units versus 512 on the 860M, and its FP32 output of 4.454 TFLOPS is roughly 45% higher than the 860M's 3.072 TFLOPS. The benchmark delta is smaller than the raw FP32 gap, suggesting some scaling losses in real workloads, but the direction is consistent.

The Vulkan test shows a similar pattern. The 860M posts 30,043, while the 880M reaches 40,006. The 24.9% lead for the 880M is slightly narrower than the OpenCL gap. Vulkan workloads tend to exercise the graphics pipeline more heavily, and both parts share the same RDNA 3.5 architecture, same 16 ROPs, and same 4 nm TSMC process. The 880M's advantage in this test comes primarily from its 48 texture mapping units and 12 ray tracing cores versus 32 TMUs and 8 RT cores on the 860M.

The 860M's average benchmark score across all recorded tests is 26,401. The 880M's average is 8,436, but this figure is heavily skewed by the inclusion of multiple Passmark tests in the 880M's benchmark list, while the 860M only has Geekbench entries. The head-to-head results are the more reliable comparison for these two parts.

The 860M's nearest rivals in the database include the NVIDIA GeForce MX550 at 26,421 (a 0.1% delta), the NVIDIA GeForce RTX 5060 at 26,331 (a 0.3% delta), the AMD Radeon RX 5700 XT 50th Anniversary at 26,553 (a 0.6% delta), and the NVIDIA RTX A4000 at 26,683 (a 1.1% delta). These deltas are all within 1.1% of the 860M's average score, indicating that the 860M sits in a tightly clustered performance band.

The 880M's nearest rivals are quite different. The NVIDIA GeForce GTX 675MX scores 8,427 (a 0.1% delta), the NVIDIA GeForce MX330 scores 8,458 (a 0.3% delta), the AMD Radeon HD 8870M scores 8,462 (a 0.3% delta), and the AMD Radeon R9 M375X scores 8,325 (a 1.3% delta). The 880M's average score is dragged down by its Passmark DirectX 9 score of 97, DirectX 10 score of 31, DirectX 11 score of 73, and DirectX 12 score of 32, which are legacy API tests that do not reflect modern workload performance.

The 880M also has a 3DMark Steel Nomad DX12 score of 535, a Passmark G2D score of 969, a Passmark G3D score of 7,615, and a Passmark GPU compute score of 3,719. These additional data points provide context for the 880M's broader benchmark coverage but are not directly comparable to the 860M's limited test set.

Where Each One Wins

The 880M wins both head-to-head benchmarks, so the data does not show a single test where the 860M comes out ahead. The 880M leads by 27.3% in OpenCL and 24.9% in Vulkan. No recorded benchmark favors the 860M.

The 860M does have a higher boost clock at 3,000 MHz versus 2,900 MHz on the 880M, and a higher base clock at 600 MHz versus 400 MHz. These clock advantages are not sufficient to overcome the 880M's larger execution resource pool. The 880M has 50% more shading units, 50% more texture mapping units, and 50% more ray tracing cores, which outweigh the 860M's clock speed advantage.

In terms of raw throughput rates, the 880M delivers 139.2 GTexel/s of texture fill rate versus 96.00 GTexel/s on the 860M, a 45% advantage. The pixel rates are nearly identical: 46.40 GPixel/s on the 880M versus 48.00 GPixel/s on the 860M. The 860M actually holds a slight lead in pixel fill rate due to its higher clock, but this is a minor difference of 1.60 GPixel/s.

The 880M's FP32 compute of 4.454 TFLOPS and FP16 compute of 4.454 TFLOPS (1:1 ratio) are both higher than the 860M's 3.072 TFLOPS in each precision. The 1:1 FP16 to FP32 ratio on both parts indicates no dedicated half-precision acceleration path, so compute workloads scale directly with the shading unit count.

For use cases that emphasize compute throughput, such as OpenCL-based general purpose workloads, the 880M is clearly the stronger option. For graphics workloads that stress texture filtering, the 880M's 48 TMUs provide a significant edge. The 860M's only measurable advantage is its higher clock speeds, which give it a small lead in pixel fill rate but do not translate into a benchmark win in the recorded data.

Architecture Differences

Both the AMD Radeon 860M and the AMD Radeon 880M are built on the RDNA 3.5 architecture and belong to the Navi III IGP generation for Strix Point Mobile. Both use a 4 nm process node from TSMC. The 860M uses the Krackan Point chip, while the 880M uses the Strix Point chip. The transistor counts are not disclosed for the 860M, but the 880M is listed with 34,000 million transistors on a 233 mm² die, giving a transistor density of 145.9 million transistors per square millimeter.

The shading unit count is the primary differentiator. The 860M has 512 shading units, 32 TMUs, 16 ROPs, and 8 ray tracing cores. The 880M has 768 shading units, 48 TMUs, 16 ROPs, and 12 ray tracing cores. The ROP count is identical at 16, which is why the pixel rates are so close. The TMU and shading unit counts scale together, with the 880M having exactly 50% more of each.

Clock behavior differs between the two parts. The 860M has a base clock of 600 MHz and a boost clock of 3,000 MHz. The 880M has a base clock of 400 MHz and a boost clock of 2,900 MHz. Despite the lower clocks, the 880M achieves higher benchmark scores because its additional execution units more than compensate.

Both parts share a 15 W TDP, an IGP slot width, no power connectors, and a PCIe 4.0 x8 bus interface. Memory is system shared for both, with no dedicated VRAM, and memory bandwidth is listed as system dependent. The display outputs are portable device dependent for both. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The 860M was released on February 28, 2025, while the 880M was released on July 14, 2024. Both are currently active in production. Both list Navi II IGP as their predecessor, and neither has a successor listed. Neither part has a launch MSRP recorded in the database.

The 880M's die size of 233 mm² and transistor count of 34,000 million indicate a larger, more complex chip than the 860M, although the 860M's die details are not recorded. The 880M's transistor density of 145.9M per square millimeter reflects the 4 nm process density.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The AMD Radeon 880M scores 31,285 versus 22,759 for the AMD Radeon 860M, a 27.3% advantage for the 880M.

Q: How do the clock speeds compare?

A: The 860M has a base clock of 600 MHz and a boost clock of 3,000 MHz. The 880M has a base clock of 400 MHz and a boost clock of 2,900 MHz. The 860M runs at higher clocks in both states.

Q: What are the shading unit counts?

A: The 860M has 512 shading units, while the 880M has 768 shading units. The 880M also has 48 TMUs versus 32, and 12 ray tracing cores versus 8.

Q: Do both GPUs use the same process node?

A: Yes, both are fabricated on a 4 nm process from TSMC. Both use the RDNA 3.5 architecture and belong to the Navi III IGP generation for Strix Point Mobile.

Q: What is the FP32 compute performance?

A: The 860M delivers 3.072 TFLOPS, while the 880M delivers 4.454 TFLOPS. Both have a 1:1 FP16 to FP32 ratio.

Q: What is the pixel fill rate for each?

A: The 860M has a pixel rate of 48.00 GPixel/s, while the 880M has a pixel rate of 46.40 GPixel/s. The 860M is slightly faster in this metric despite losing both head-to-head benchmarks.

The Verdict

The benchmark data clearly favors the AMD Radeon 880M in the two recorded head-to-head tests. It leads by 27.3% in Geekbench OpenCL and 24.9% in Geekbench Vulkan. The 880M's larger execution resource pool, with 768 shading units, 48 TMUs, and 12 ray tracing cores, provides a decisive advantage over the 860M's 512 shading units, 32 TMUs, and 8 ray tracing cores.

The 860M's higher clock speeds, 600 MHz base and 3,000 MHz boost, do not close the gap. The 880M achieves its performance with lower clocks of 400 MHz base and 2,900 MHz boost, relying on additional parallel hardware rather than frequency. The 860M does hold a slight edge in pixel fill rate at 48.00 GPixel/s versus 46.40 GPixel/s, but this does not translate into a win in any recorded benchmark.

For systems where compute and graphics throughput matter most, the 880M is the stronger choice based on the recorded data. The 880M's 4.454 TFLOPS of FP32 performance and 139.2 GTexel/s texture rate are substantially higher than the 860M's 3.072 TFLOPS and 96.00 GTexel/s. The 880M also offers 50% more ray tracing cores, which may benefit applications that use hardware accelerated ray tracing.

The 860M remains a capable integrated GPU with a 72nd percentile ranking among all GPUs in the database, and its nearest rivals are clustered within 1.1% of its average score. The 880M's percentile ranking of 43 is lower, but this is influenced by its broader benchmark coverage, including legacy Passmark tests that pull down its average. The head-to-head results are the definitive comparison, and they show the 880M as the faster part.

The release dates also matter for selection context. The 880M launched on July 14, 2024, while the 860M launched on February 28, 2025. Both are active production parts with no successor listed. Neither has a recorded launch MSRP, and both are IGP-class parts with a 15 W TDP and system shared memory. The choice between them, based strictly on the data, depends on whether the additional compute and texture resources of the 880M justify its selection over the 860M's higher clocks and slightly better pixel fill rate. The benchmark results indicate that the 880M's resource advantage delivers measurable performance gains in both OpenCL and Vulkan workloads.