AMD Ryzen AI Max PRO 390 vs Intel Core Ultra 7 265 Comparison

The Intel Core Ultra 7 265 and AMD Ryzen AI Max PRO 390 are both high-end processors that land in the 93rd percentile of all CPUs, but they are built for completely different environments. The Intel part is a desktop chip on Socket 1851, while the AMD part is a mobile chip on Socket FP11. Benchmark data shows the Intel chip wins 14 of 15 head-to-head tests, often by massive margins, making it the clear choice for raw compute performance. The AMD chip’s single win in integer math and its superior memory bandwidth point to specific niche advantages, but for most workloads, the data favors Intel decisively.

The Verdict

If your priority is raw multi-threaded performance, the Intel Core Ultra 7 265 is the data-backed winner. It outperforms the AMD Ryzen AI Max PRO 390 by 70% in Cinebench R23 multi-core (42216 vs 24828) and by 8.6% in Cinebench R15 multi-core (4255 vs 3918). This is a desktop part with 20 cores and 20 threads, compared to the AMD’s 12 cores and 24 threads, and the benchmark results reflect that core-count advantage in heavily threaded workloads like rendering and video encoding.

Single-core performance is even more lopsided. The Intel chip leads by 98% in Cinebench R15 single-core (600 vs 303) and by a staggering 201.6% in Cinebench R23 single-core (5960 vs 1976). This is not a close contest; the Intel architecture holds a massive IPC and clock-speed advantage in the data. For any application that relies on single-thread responsiveness, the Intel part is the objective choice.

However, the AMD chip is not without merit. It is the only winner in PassMark integer math, scoring 148508 versus Intel’s 134773, a 9.2% advantage. It also offers quad-channel LPDDR5X memory with 256.0 GB/s bandwidth, exactly double the Intel’s 102.4 GB/s dual-channel DDR5. For workloads that are memory-bandwidth sensitive, the AMD part has a structural edge, even though it loses most compute benchmarks. Choose the AMD chip only if your workflow is dominated by integer math or memory throughput. For everything else, the Intel chip is the data-driven pick.

FAQ

Q: Which processor has better multi-core performance?

A: The Intel Core Ultra 7 265 wins all multi-core benchmarks. It leads by 70% in Cinebench R23 multi-core (42216 vs 24828) and by 15.8% in PassMark multi-thread (49682 vs 42912).

Q: Is the AMD Ryzen AI Max PRO 390 competitive in single-core tests?

A: No. The Intel chip wins every single-core test by significant margins, including a 98% lead in Cinebench R15 (600 vs 303) and an 18.2% lead in PassMark single-thread (4689 vs 3967).

Q: Does the AMD chip win any benchmark at all?

A: Yes, it wins PassMark integer math with a score of 148508, which is 9.2% higher than Intel’s 134773. This is the only head-to-head benchmark it wins out of 15 total tests.

Q: How do the memory systems differ?

A: The AMD chip uses quad-channel LPDDR5X memory with 256.0 GB/s bandwidth and supports ECC memory. The Intel chip uses dual-channel DDR5 with 102.4 GB/s bandwidth and does not support ECC.

Q: Which processor has more cores and threads?

A: The Intel Core Ultra 7 265 has more cores (20 vs 12), but the AMD Ryzen AI Max PRO 390 has more threads (24 vs 20) due to simultaneous multithreading.

Q: What are the thermal design power (TDP) ratings?

A: The Intel chip has a TDP of 65 watts, while the AMD chip has a TDP of 55 watts, making the AMD part slightly more power-efficient on paper.

Architecture Differences

The two chips come from fundamentally different design philosophies. The Intel Core Ultra 7 265 uses the Arrow Lake architecture, built on a 3 nm process node at TSMC, with 17,800 million transistors on a 243 mm² die. It has 20 cores and 20 threads, meaning no hyperthreading, and features a cache hierarchy of 192 KB L1 per core, 3 MB L2 per core, and 30 MB of shared L3 cache. The integrated graphics are Arc Xe-LPG with 32 execution units, and the chip supports PCIe Gen 5 with 20 CPU lanes.

The AMD Ryzen AI Max PRO 390 uses the Zen 5 architecture, built on a 4 nm process node at TSMC. It has 12 cores and 24 threads, leveraging simultaneous multithreading to double the thread count. Its cache layout is different: 80 KB L1 per core, 1 MB L2 per core, and a much larger 64 MB of shared L3 cache. The integrated graphics are Radeon 8050S, and the chip supports PCIe Gen 4 with 16 CPU lanes. The AMD chip also supports ECC memory, which the Intel chip does not.

The process node difference is notable: Intel uses a 3 nm process versus AMD’s 4 nm, which helps explain Intel’s higher boost clock of 5.30 GHz compared to AMD’s 5.00 GHz. The L3 cache difference is also significant, with AMD offering more than double the shared cache, which can benefit certain data-heavy workloads. The memory architecture diverges sharply, with AMD using quad-channel LPDDR5X and Intel using dual-channel DDR5, resulting in a 2.5x bandwidth advantage for AMD (256.0 GB/s vs 102.4 GB/s).

Specification Differences

The two processors differ on nearly every key specification. The Intel Core Ultra 7 265 has 20 cores and 20 threads, while the AMD Ryzen AI Max PRO 390 has 12 cores and 24 threads. Intel’s base clock is 2.40 GHz with a boost clock of 5.30 GHz; AMD’s base clock is 3.20 GHz with a boost clock of 5.00 GHz. The Intel chip has a higher TDP at 65 watts versus AMD’s 55 watts.

The sockets are incompatible: Intel uses Socket 1851, while AMD uses Socket FP11. The memory support differs completely, with Intel supporting dual-channel DDR5 and AMD supporting quad-channel LPDDR5X. The memory bandwidth figures are 102.4 GB/s for Intel and 256.0 GB/s for AMD. ECC memory is supported on the AMD chip but not on the Intel chip.

PCIe support differs as well: Intel has Gen 5 with 20 lanes, while AMD has Gen 4 with 16 lanes. The integrated graphics are also different, with Intel using Arc Xe-LPG Graphics 32EU and AMD using Radeon 8050S. The process nodes differ (3 nm for Intel, 4 nm for AMD), and the cache configurations are not the same, as detailed in the architecture section. The Intel chip has a launch MSRP of $394, while the AMD chip has no listed launch MSRP.

Head-to-Head Benchmarks

The benchmark data tells a clear story of Intel dominance, but the margins vary wildly by workload. The largest win for Intel is in Cinebench R23 single-core, where it scores 5960 versus AMD’s 1976, a 201.6% advantage. This is an extraordinary gap that suggests the Intel architecture is far more efficient per clock in lightly threaded tasks. The Cinebench R15 single-core test shows a similar pattern, with Intel leading 600 to 303, a 98% margin.

In multi-core workloads, Intel also dominates but by smaller margins. Cinebench R23 multi-core shows Intel at 42216 versus AMD’s 24828, a 70% lead. This is a massive difference, but it is less than the single-core gap, indicating that AMD’s additional threads help close the distance somewhat. In Cinebench R15 multi-core, Intel leads 4255 to 3918, an 8.6% margin, which is much closer.

PassMark tests reveal a mixed bag. Intel wins floating point math by 82.5% (172776 vs 94666), data encryption by 55.4% (40456 vs 26027), and find prime numbers by 29.4% (418 vs 323). Intel also wins multi-thread by 15.8% (49682 vs 42912), random string sorting by 15.5% (63833 vs 55248), and single-thread by 18.2% (4689 vs 3967). The only AMD victory is in integer math, where it scores 148508 versus Intel’s 134773, a 9.2% advantage. The close calls are in data compression (Intel wins by 3.3%) and extended instructions (Intel wins by 1.4%), where the scores are nearly identical.

Where Each One Wins

The Intel Core Ultra 7 265 wins in almost every measurable category. It is the clear choice for any workload that benefits from high single-core performance, such as gaming, legacy software, or applications that are not well-threaded. The 201.6% lead in Cinebench R23 single-core is decisive. It also wins heavily in multi-threaded rendering, with a 70% lead in Cinebench R23 multi-core, making it the superior choice for video editing, 3D rendering, and content creation. In PassMark, Intel wins all but one test, including a dominant 82.5% lead in floating point math, which is relevant for scientific computing and financial modeling. The chip’s PCIe Gen 5 support with 20 lanes also gives it an edge for high-speed storage and expansion cards.

The AMD Ryzen AI Max PRO 390 has exactly one benchmark win: PassMark integer math, where it scores 9.2% higher than Intel. This suggests it may be better for tasks that are heavily integer-based, such as cryptography, compression algorithms, or certain database operations. Its quad-channel LPDDR5X memory with 256.0 GB/s bandwidth is a structural advantage that could benefit workloads that are memory-bound, even though the benchmark data does not show a corresponding win in most tests. The chip also supports ECC memory, which is useful for error-sensitive compute environments. Its lower TDP of 55 watts makes it a more power-efficient option for mobile or compact systems, and it is the only choice here for a Socket FP11 mobile platform. However, based on the benchmark data, the AMD chip is a niche pick for integer-heavy or memory-throughput-sensitive workloads, while Intel wins the broad performance crown.