AMD Radeon 860M vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains two shared benchmark results for the AMD Radeon 860M and the NVIDIA GeForce RTX 5090 Mobile. The outcome is decisive: the NVIDIA part wins both tests by substantial margins.

In Geekbench OpenCL, the AMD Radeon 860M scores 22,759 points, while the NVIDIA GeForce RTX 5090 Mobile scores 201,834 points. That is a delta of -88.7%, meaning the NVIDIA GPU delivers roughly 8.9 times the raw compute throughput in this workload. The Geekbench Vulkan result follows a similar pattern: the AMD part scores 30,043 points versus 198,405 points for the NVIDIA part, a delta of -84.9%.

The scale of these differences matters for interpretation. The AMD Radeon 860M sits in the 72nd percentile among all GPUs in the database, while the NVIDIA GeForce RTX 5090 Mobile sits in the 84th percentile. That 12-point percentile gap understates the performance chasm, because the percentile ranking compresses the vast absolute difference in scores into a narrower band. The average benchmark score for the AMD part is 26,401, while the NVIDIA part averages 45,152.

The AMD Radeon 860M's nearest rivals in the database include the NVIDIA GeForce MX550 at 26,421 average score (-0.1% delta), the NVIDIA GeForce RTX 5060 at 26,331 (+0.3%), the AMD Radeon RX 5700 XT 50th Anniversary at 26,553 (-0.6%), and the NVIDIA RTX A4000 at 26,683 (-1.1%). These deltas are all within roughly one percent, indicating the 860M is positioned in a tightly clustered performance tier. The NVIDIA GeForce RTX 5090 Mobile, by contrast, has nearest rivals that include the AMD Radeon Pro 5500 XT at 45,384 (-0.5%), the NVIDIA GeForce RTX 4070 Ti at 44,795 (+0.8%), the Intel Arc A730M at 45,592 (-1%), and the NVIDIA RTX 5880 Ada Generation at 45,972 (-1.8%). The absolute distance between these two clusters is enormous: the NVIDIA mobile flagship's average score is roughly 71% higher than the AMD IGP's average.

The head-to-head data records 0 wins for the AMD Radeon 860M and 2 wins for the NVIDIA GeForce RTX 5090 Mobile. No benchmark in the shared set favors the AMD part. The Vulkan delta of -84.9% is slightly smaller than the OpenCL delta of -88.7%, which suggests the AMD RDNA 3.5 architecture narrows the gap somewhat under Vulkan, but the NVIDIA part still more than sextuples the AMD score in that API.

FAQ

Q: Which GPU wins the shared Geekbench OpenCL test?

A: The NVIDIA GeForce RTX 5090 Mobile wins with a score of 201,834 versus 22,759 for the AMD Radeon 860M, a delta of -88.7% from the AMD part's perspective.

Q: How do the two GPUs compare in the Geekbench Vulkan test?

A: The NVIDIA GeForce RTX 5090 Mobile scores 198,405, while the AMD Radeon 860M scores 30,043. The delta is -84.9%, again favoring NVIDIA.

Q: What percentile rank does each GPU hold in the database?

A: The AMD Radeon 860M is in the 72nd percentile among all GPUs, and the NVIDIA GeForce RTX 5090 Mobile is in the 84th percentile.

Q: What are the average benchmark scores for each GPU?

A: The AMD Radeon 860M has an average benchmark score of 26,401. The NVIDIA GeForce RTX 5090 Mobile has an average benchmark score of 45,152.

Q: Which GPUs are the closest rivals to the AMD Radeon 860M?

A: The nearest rivals are the NVIDIA GeForce MX550 (26,421 average score, -0.1% delta), the NVIDIA GeForce RTX 5060 (26,331, +0.3%), the AMD Radeon RX 5700 XT 50th Anniversary (26,553, -0.6%), and the NVIDIA RTX A4000 (26,683, -1.1%).

Q: Which GPUs are the closest rivals to the NVIDIA GeForce RTX 5090 Mobile?

A: The nearest rivals are the AMD Radeon Pro 5500 XT (45,384 average score, -0.5% delta), the NVIDIA GeForce RTX 4070 Ti (44,795, +0.8%), the Intel Arc A730M (45,592, -1%), and the NVIDIA RTX 5880 Ada Generation (45,972, -1.8%).

The Verdict

The benchmark data is unambiguous. The NVIDIA GeForce RTX 5090 Mobile is the dominant part in every shared test, with OpenCL and Vulkan scores that are roughly nine times and six and a half times higher, respectively, than the AMD Radeon 860M. The NVIDIA part holds an 84th percentile rank and an average score of 45,152, placing it in a performance tier alongside desktop-class GPUs such as the NVIDIA GeForce RTX 4070 Ti and the NVIDIA RTX 5880 Ada Generation.

The AMD Radeon 860M, with a 72nd percentile rank and an average score of 26,401, competes in a much lower tier. Its nearest rivals are the NVIDIA GeForce MX550, the NVIDIA GeForce RTX 5060, and the AMD Radeon RX 5700 XT 50th Anniversary, all within roughly one percent of its average score. The data shows no scenario in which the AMD part outperforms the NVIDIA part in the shared benchmark set.

For users whose workload is represented by these benchmarks, the choice is dictated by the scores: the NVIDIA GeForce RTX 5090 Mobile delivers far higher compute throughput in both OpenCL and Vulkan. The AMD Radeon 860M is a low-power integrated GPU, and its benchmark positioning reflects that role. The verdict from the database is clear: the NVIDIA GeForce RTX 5090 Mobile wins all head-to-head comparisons recorded here.

Specification Differences

The two GPUs differ across nearly every recorded specification. The AMD Radeon 860M is built on a 4 nm process node at TSMC, while the NVIDIA GeForce RTX 5090 Mobile uses a 5 nm node at the same foundry. The NVIDIA chip, GB203, contains 45,600 million transistors on a 378 mm² die, with a transistor density of 120.6M per mm². The AMD chip, Krackan Point, has an unknown transistor count and die size in the database.

Clock speeds diverge sharply. The AMD Radeon 860M has a base clock of 600 MHz and a boost clock of 3000 MHz. The NVIDIA GeForce RTX 5090 Mobile has a base clock of 990 MHz and a boost clock of 1515 MHz. The AMD part boosts much higher, but the NVIDIA part starts from a higher base and relies on a much larger shader array.

Memory configurations are fundamentally different. The AMD Radeon 860M uses system shared memory, with a system-dependent bandwidth and no dedicated VRAM size or bus width. The NVIDIA GeForce RTX 5090 Mobile has 24 GB of GDDR7 memory on a 256-bit bus, delivering 896.0 GB/s of bandwidth with a memory clock of 1750 MHz (28 Gbps effective).

The bus interface also differs: the AMD part uses PCIe 4.0 x8, while the NVIDIA part uses PCIe 5.0 x16. Both are recorded as IGP slot width with no power connectors and portable-device-dependent display outputs. The AMD part has a 15 W TDP, while the NVIDIA part has a 95 W TDP.

Architecture Differences

The architectural gap is substantial. The AMD Radeon 860M uses the RDNA 3.5 architecture, part of the Navi III IGP generation with the Krackan Point chip. The NVIDIA GeForce RTX 5090 Mobile uses the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation with the GB203 chip.

Compute resources differ by an order of magnitude. The AMD part has 512 shading units, 32 texture mapping units, 16 ROPs, and 8 ray tracing cores. The NVIDIA part has 10,496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The NVIDIA part also has no null tensor core field, whereas the AMD part lists tensor cores as null, meaning the data does not record tensor hardware for the AMD IGP.

Pixel and texture rates reflect the resource disparity. The AMD Radeon 860M delivers 48.00 GPixel/s and 96.00 GTexel/s. The NVIDIA GeForce RTX 5090 Mobile delivers 169.7 GPixel/s and 496.9 GTexel/s. Floating-point throughput is similarly lopsided: the AMD part reaches 3.072 TFLOPS in both FP32 and FP16 (1:1), while the NVIDIA part reaches 31.80 TFLOPS in both.

Both GPUs support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The AMD part's predecessor is the Navi II IGP, and the NVIDIA part's predecessor is the GeForce 40 Mobile. The AMD part was released on 2025-02-28, while the NVIDIA part was released on 2025-03-26.

Where Each One Wins

The head-to-head data records zero wins for the AMD Radeon 860M across the two shared benchmarks. There is no workload in the database where the AMD part edges ahead of the NVIDIA GeForce RTX 5090 Mobile. The NVIDIA part wins both the OpenCL and Vulkan tests, with deltas of -88.7% and -84.9% respectively.

The AMD Radeon 860M's strengths lie in its own tier. Its 72nd percentile rank and average score of 26,401 place it among GPUs like the NVIDIA GeForce MX550 and the AMD Radeon RX 5700 XT 50th Anniversary. Within that tier, the data shows it is competitive, with deltas under one percent against all four nearest rivals. Its 15 W TDP, system-shared memory, and IGP form factor indicate it is designed for low-power portable devices, and its 3000 MHz boost clock is the highest clock figure recorded for either GPU.

The NVIDIA GeForce RTX 5090 Mobile wins outright in raw performance. Its 84th percentile rank, 45,152 average score, and decisive victories in both shared benchmarks place it in a different class. Its nearest rival tier includes the NVIDIA GeForce RTX 4070 Ti and the NVIDIA RTX 5880 Ada Generation, both desktop-class parts. The 24 GB GDDR7 memory with 896.0 GB/s bandwidth, 10,496 shading units, and 31.80 TFLOPS FP32 throughput provide the hardware basis for its benchmark dominance.

The use-case split follows the data. For workloads that require maximum compute throughput in OpenCL or Vulkan, the NVIDIA GeForce RTX 5090 Mobile is the only choice between these two. The AMD Radeon 860M occupies the low-power integrated segment, where its benchmark scores align with other IGP-class and entry-level discrete GPUs in the database. The recorded data offers no scenario where the AMD part wins a head-to-head comparison against the NVIDIA mobile flagship.