AMD Radeon 860M vs NVIDIA GeForce RTX 5080 Comparison
AMD Radeon 860M
GeForce RTX 5080
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon 860M vs NVIDIA GeForce RTX 5080
FAQ
Q: How do the two GPUs compare in average benchmark score?
A: The AMD Radeon 860M has an average benchmark score of 26401, while the NVIDIA GeForce RTX 5080 records 56083. The RTX 5080 holds a higher average score, and its percentile rank among all GPUs is 87, compared to the 860M’s percentile of 72.
Q: Which GPU wins in the Geekbench OpenCL test, and by how much?
A: The NVIDIA GeForce RTX 5080 wins the Geekbench OpenCL test with a score of 235901 versus the AMD Radeon 860M’s 22759. The delta percentage is -90.4, meaning the 860M trails by 90.4 percent in that workload.
Q: What is the result of the Geekbench Vulkan test between these two?
A: The RTX 5080 also wins the Geekbench Vulkan test, scoring 255450 against the 860M’s 30043. The delta percentage is -88.2, indicating the 860M is 88.2 percent behind in Vulkan performance.
Q: Which GPU has a higher boost clock?
A: The AMD Radeon 860M has a boost clock of 3000 MHz, while the NVIDIA GeForce RTX 5080 has a boost clock of 2617 MHz. The 860M’s boost clock is higher despite its lower overall performance.
Q: What memory configuration does each GPU use?
A: The AMD Radeon 860M uses system-shared memory with system-dependent bandwidth. The NVIDIA GeForce RTX 5080 uses 16 GB of GDDR7 memory on a 256-bit bus, with 960.0 GB/s of bandwidth.
Q: Which GPU has more shading units and ray tracing cores?
A: The NVIDIA GeForce RTX 5080 has 10752 shading units and 84 ray tracing cores. The AMD Radeon 860M has 512 shading units and 8 ray tracing cores.
Architecture Differences
The AMD Radeon 860M is built on the RDNA 3.5 architecture with the Krackan Point chip, belonging to the Navi III IGP (Strix Point Mobile) generation. It uses a 4 nm process node from TSMC. The NVIDIA GeForce RTX 5080 uses the Blackwell 2.0 architecture with the GB203 chip, part of the GeForce 50 generation, fabricated on a 5 nm process node, also by TSMC. The 860M is an integrated graphics processor, whereas the RTX 5080 is a discrete dual-slot add-in card.
The 860M has 512 shading units, 32 texture mapping units, and 16 raster output pipelines. The RTX 5080 has 10752 shading units, 336 texture mapping units, and 112 raster output pipelines. In ray tracing hardware, the 860M includes 8 RT cores, while the RTX 5080 includes 84 RT cores. The RTX 5080 additionally has 336 tensor cores; the 860M has no tensor cores listed. The 860M’s pixel rate is 48.00 GPixel/s and its texture rate is 96.00 GTexel/s, while the RTX 5080 reaches 293.1 GPixel/s and 879.3 GTexel/s.
The transistor count and die size differ substantially: the 860M reports unknown transistor count and die size, while the RTX 5080 has 45,600 million transistors on a 378 mm² die, with a transistor density of 120.6M per mm². The 860M uses a PCIe 4.0 x8 bus interface, while the RTX 5080 uses PCIe 5.0 x16. Power delivery also differs: the 860M is rated at 15 W TDP with no power connectors, while the RTX 5080 is rated at 360 W TDP with a single 16-pin power connector and a suggested PSU of 750 W.
Head-to-Head Benchmarks
The recorded head-to-head data covers two tests, both Geekbench workloads. In Geekbench OpenCL, the AMD Radeon 860M scores 22759, and the NVIDIA GeForce RTX 5080 scores 235901. The RTX 5080 wins with a delta of -90.4, meaning the 860M is 90.4 percent lower. In Geekbench Vulkan, the 860M scores 30043, while the RTX 5080 scores 255450. Again the RTX 5080 wins, with a delta of -88.2, meaning the 860M is 88.2 percent lower.
These two deltas are massive, but the context of the compute workloads matters. The OpenCL and Vulkan tests stress raw shader throughput and memory bandwidth. The RTX 5080’s 56.28 TFLOPS FP32 performance versus the 860M’s 3.072 TFLOPS FP32 explains the margin. The RTX 5080’s 960.0 GB/s memory bandwidth, compared to the 860M’s system-dependent bandwidth, also contributes. The 860M’s advantage lies only in clock speed: its boost clock of 3000 MHz exceeds the RTX 5080’s 2617 MHz, but the RTX 5080 compensates with far more execution units and dedicated memory.
The nearest rivals for each GPU provide additional perspective. The 860M’s nearest rival is the NVIDIA GeForce MX550, with an average score of 26421 and a delta of -0.1 percent, meaning the 860M is essentially tied with that GPU. The RTX 5060 scores 26331 with a delta of +0.3 percent, placing the 860M just ahead. The AMD Radeon RX 5700 XT 50th Anniversary scores 26553 with a delta of -0.6, and the NVIDIA RTX A4000 scores 26683 with a delta of -1.1. For the RTX 5080, the AMD Radeon 8060S scores 55757 with a delta of +0.6, the AMD Radeon RX 6750 GRE 12 GB scores 55698 with a delta of +0.7, the AMD Radeon Pro W5700X scores 54828 with a delta of +2.3, and the AMD Radeon RX 9070 GRE scores 57367 with a delta of -2.2. These rival deltas show that the RTX 5080 sits in a much higher performance tier, with its closest competitors within a few percent, while the 860M operates in a completely different range.
Specification Differences
The specification differences between the two are extensive. The AMD Radeon 860M uses RDNA 3.5, the NVIDIA GeForce RTX 5080 uses Blackwell 2.0. The process nodes differ: 4 nm for the 860M, 5 nm for the RTX 5080. The 860M has unknown transistor count and die size, while the RTX 5080 has 45,600 million transistors and a 378 mm² die. Base clocks differ: 600 MHz for the 860M versus 2295 MHz for the RTX 5080. Boost clocks are 3000 MHz versus 2617 MHz. Memory is system-shared for the 860M, while the RTX 5080 uses 16 GB GDDR7 on a 256-bit bus with 960.0 GB/s bandwidth.
Shading units: 512 versus 10752. TMUs: 32 versus 336. ROPs: 16 versus 112. RT cores: 8 versus 84. Tensor cores: none versus 336. Pixel rate: 48.00 GPixel/s versus 293.1 GPixel/s. Texture rate: 96.00 GTexel/s versus 879.3 GTexel/s. FP32: 3.072 TFLOPS versus 56.28 TFLOPS. FP16: 3.072 TFLOPS (1:1) versus 56.28 TFLOPS (1:1). TDP: 15 W versus 360 W. Slot width: IGP versus dual-slot. Power connectors: none versus 1x 16-pin. Suggested PSU: none versus 750 W. Bus interface: PCIe 4.0 x8 versus PCIe 5.0 x16. Display outputs: portable device dependent versus 1x HDMI 2.1b and 3x DisplayPort 2.1b. Dimensions: the 860M has no listed dimensions, while the RTX 5080 measures 304 mm by 137 mm by 40 mm. Release dates: 2025-02-28 for the 860M, 2025-01-29 for the RTX 5080. The 860M’s predecessor is Navi II IGP, the RTX 5080’s predecessor is GeForce 40. The RTX 5080 has a successor listed as GeForce 60, while the 860M has none.
The Verdict
The data shows a clear performance hierarchy. The NVIDIA GeForce RTX 5080 dominates both recorded head-to-head benchmarks, winning Geekbench OpenCL and Vulkan by margins of 90.4 percent and 88.2 percent, respectively. Its average benchmark score of 56083 is more than double the 860M’s 26401. The RTX 5080 also reaches the 87th percentile among all GPUs, compared to the 860M’s 72nd percentile. For workloads that rely on raw compute, memory bandwidth, or ray tracing, the RTX 5080 is the only choice based on these measurements.
The AMD Radeon 860M, however, is an integrated GPU with a 15 W TDP, designed for portable devices. Its 600 MHz base clock and 3000 MHz boost clock are higher boost than the RTX 5080, but its 512 shading units and system-shared memory cannot match a discrete card with 10752 shading units and 16 GB of dedicated GDDR7. The 860M’s nearest rivals include the NVIDIA GeForce MX550 and RTX 5060, all within about one percent of its average score. That places the 860M in the entry-level discrete GPU class, not the high-end tier occupied by the RTX 5080.
For a user who needs maximum compute throughput, the RTX 5080’s 56.28 TFLOPS FP32 and 960.0 GB/s bandwidth are decisive. For a user constrained to integrated graphics in a portable device, the 860M offers a functional baseline, but it competes with low-end discrete GPUs, not with the RTX 5080. The specification differences reinforce this: the RTX 5080 has 21 times the shading units, 10.5 times the RT cores, and 18.3 times the FP32 throughput. The verdict is unambiguous: the RTX 5080 is the superior GPU across every measured benchmark and specification field that matters for performance. The 860M is suitable only for scenarios where an IGP is the only option, and even then its performance relative to the RTX 5080 is minimal.