AMD Ryzen AI Max+ 392 vs Intel Core Ultra 5 235 Comparison

Head-to-Head Benchmarks

The recorded data shows a clear split between the two processors across the Passmark test suite. The AMD Ryzen AI Max+ 392 takes 6 of the 11 head-to-head benchmarks, while the Intel Core Ultra 5 235 wins 5. The magnitude of the wins, however, is not symmetrical. AMD's largest victory comes in integer math, where it scores 152,414 against Intel's 87,948, a 73.3% advantage. This is the single most lopsided result in the comparison and indicates a substantial difference in raw integer throughput.

Data compression also favors AMD heavily. The Ryzen AI Max+ 392 scores 554,760 versus 390,711 for the Core Ultra 5 235, a 42% lead. Extended instructions follow the same pattern, with AMD at 45,666 and Intel at 32,752, a 39.4% gap. Random string sorting goes to AMD by 21.5%, with scores of 59,487 and 48,980 respectively. The multithread benchmark shows AMD ahead at 45,231 against 37,816, a 19.6% margin. Physics simulation also goes to AMD, 2,887 versus 2,570, a 12.3% difference.

Intel counters in several individual workloads. Floating point math is Intel's strongest category, scoring 117,951 versus AMD's 99,548, a 15.6% advantage. Prime number finding goes to Intel by 13.7%, with scores of 371 and 320. Single-thread performance also belongs to Intel, 4,516 versus 3,927, a 13% lead. Data encryption is a narrower Intel win, 29,293 versus 27,784, a 5.2% margin.

The average benchmark score in the database places the AMD part at 90,541, which puts it in the 96th percentile of all CPUs. The Intel part averages 46,062 and sits in the 89th percentile. The nearest rivals for AMD are the Intel Xeon 654 at 90,717 (0.2% higher), the AMD Ryzen 9 9955HX at 91,199 (0.7% higher), the Intel Xeon w7-2575X at 88,172 (2.7% lower), and the Intel Xeon 6736P at 87,864 (3% lower). For Intel, the closest competitors are the AMD Ryzen AI 9 HX 375 at 46,030 (0.1% lower), the Intel Core i9-13900HX at 46,098 (0.1% higher), the AMD EPYC 4364P at 45,970 (0.2% lower), and the AMD EPYC 7303 at 45,960 (0.2% lower).

The scoring pattern suggests that AMD's advantage is concentrated in workloads that scale with thread count and memory bandwidth, while Intel holds the edge in latency-sensitive and single-threaded tasks.

Architecture Differences

The two processors come from fundamentally different design philosophies. The AMD Ryzen AI Max+ 392 uses the Zen 5 architecture on a 4 nm TSMC process, with the Strix Halo codename. It has 12 cores and 24 threads, relying on simultaneous multithreading to double its thread count. The Intel Core Ultra 5 235 uses the Arrow Lake architecture on a 3 nm TSMC process, with the Arrow Lake-S codename. It has 14 cores and 14 threads, with no multithreading enabled, meaning each core handles exactly one thread.

Cache configurations differ substantially. The AMD part provides 80 KB of L1 per core, 1 MB of L2 per core, and 64 MB of shared L3 cache. The Intel part provides 192 KB of L1 per core, 3 MB of L2 per core, and 24 MB of shared L3 cache. The larger per-core L1 and L2 caches on Intel likely contribute to its single-thread wins, while AMD's much larger 64 MB L3 pool supports its multithreaded workload performance.

The memory subsystem also diverges. AMD uses LPDDR5X memory with a quad-channel bus and 256.0 GB/s of bandwidth. Intel uses DDR5 with a dual-channel bus and 102.4 GB/s of bandwidth. AMD's memory bandwidth is exactly 2.5 times Intel's, which helps explain the large lead in memory-intensive tasks like data compression and random string sorting. AMD also supports ECC memory, while Intel does not.

The integrated graphics differ as well. AMD pairs the CPU with a Radeon 8060S, while Intel includes Arc Xe-LPG Graphics with 24 execution units. The database provides no direct graphics benchmarks, so the comparison must remain qualitative. The process nodes differ: AMD is on 4 nm and Intel is on 3 nm, both fabricated by TSMC. Intel's die is 243 mm² with 17,800 million transistors, while AMD's die is listed as 2x 70.6 mm². The socket types are incompatible: AMD uses Socket FP11 and Intel uses Socket 1851. PCIe support also differs, with AMD offering Gen 4 with 16 lanes (CPU only) and Intel offering Gen 5 with 20 lanes (CPU only).

The release dates are close but not identical. Intel launched on 2026-01-05 and AMD launched on 2025-01-06, meaning the Intel part appears in the database with a later release date. The AMD part is a mobile processor, while the Intel part is a desktop processor.

The Verdict

The data indicates that the AMD Ryzen AI Max+ 392 is the stronger overall processor in the database's aggregate scoring. Its average benchmark score of 90,541 is roughly double the Intel Core Ultra 5 235's 46,062, and its 96th percentile ranking versus Intel's 89th percentile confirms the separation. The multithread benchmark shows AMD at 45,231 versus Intel at 37,816, a 19.6% advantage, and the integer math result of 73.3% ahead is a dominant margin.

The Intel Core Ultra 5 235, however, is not without merit. It wins single-thread performance by 13%, floating point math by 15.6%, prime number finding by 13.7%, and data encryption by 5.2%. For workloads that depend on single-core responsiveness or floating point throughput, the Intel part delivers higher scores. The Intel part is also a desktop chip with a 65 W TDP, while AMD is a mobile chip with a 55 W TDP.

The recorded data supports the following: the AMD processor is the choice for multithreaded, memory-bandwidth-heavy, and integer-intensive workloads. The Intel processor is the choice for single-threaded, floating point, and encryption workloads. The percentile rankings make the overall hierarchy clear: AMD sits in the 96th percentile, Intel in the 89th.

Specification Differences

| Field | AMD Ryzen AI Max+ 392 | Intel Core Ultra 5 235 |

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

| Cores | 12 | 14 |

| Threads | 24 | 14 |

| Base clock | 3.20 GHz | 3.40 GHz |

| Boost clock | 5.00 GHz | 5.00 GHz |

| TDP | 55 W | 65 W |

| Socket | AMD Socket FP11 | Intel Socket 1851 |

| Architecture | Zen 5 | Arrow Lake |

| Codename | Strix Halo | Arrow Lake-S |

| Process node | 4 nm | 3 nm |

| Transistors | Not listed | 17,800 million |

| Die size | 2x 70.6 mm² | 243 mm² |

| L1 cache | 80 KB (per core) | 192 KB (per core) |

| L2 cache | 1 MB (per core) | 3 MB (per core) |

| L3 cache | 64 MB (shared) | 24 MB (shared) |

| Memory support | LPDDR5X | DDR5 |

| Memory bus | Quad-channel | Dual-channel |

| Memory bandwidth | 256.0 GB/s | 102.4 GB/s |

| ECC memory | Yes | No |

| PCIe | Gen 4, 16 lanes (CPU only) | Gen 5, 20 lanes (CPU only) |

| Integrated graphics | Radeon 8060S | Arc Xe-LPG Graphics 24EU |

| Market segment | Mobile | Desktop |

| Release date | 2025-01-06 | 2026-01-05 |

| Launch MSRP | Not listed | $257 |

| Multiplier unlocked | No | No |

| Part number | 100-000001979 | SRQAS |

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 5 235 has 14 cores, while the AMD Ryzen AI Max+ 392 has 12 cores. However, AMD has 24 threads versus Intel's 14, because AMD enables simultaneous multithreading and Intel does not.

Q: Which processor has the higher single-thread benchmark score?

A: The Intel Core Ultra 5 235 scores 4,516 in the Passmark single-thread test, which is 13% higher than the AMD Ryzen AI Max+ 392's 3,927.

Q: How large is the difference in memory bandwidth?

A: The AMD Ryzen AI Max+ 392 provides 256.0 GB/s of memory bandwidth over a quad-channel LPDDR5X bus. The Intel Core Ultra 5 235 provides 102.4 GB/s over a dual-channel DDR5 bus. AMD's bandwidth is 2.5 times Intel's.

Q: Which processor wins the multithread benchmark?

A: The AMD Ryzen AI Max+ 392 scores 45,231 in the Passmark multithread test, which is 19.6% higher than the Intel Core Ultra 5 235's 37,816.

Q: What are the process nodes for each processor?

A: The AMD Ryzen AI Max+ 392 is fabricated on a 4 nm TSMC process. The Intel Core Ultra 5 235 is fabricated on a 3 nm TSMC process.

Q: Which processor supports ECC memory?

A: The AMD Ryzen AI Max+ 392 supports ECC memory. The Intel Core Ultra 5 235 does not.

Q: What is the L3 cache capacity for each processor?

A: The AMD Ryzen AI Max+ 392 has 64 MB of shared L3 cache. The Intel Core Ultra 5 235 has 24 MB of shared L3 cache.

Where Each One Wins

The AMD Ryzen AI Max+ 392 wins in data compression, extended instructions, integer math, multithread, physics, and random string sorting. These are workloads that benefit from high thread counts, large shared caches, and high memory bandwidth. The 73.3% lead in integer math and the 42% lead in data compression are the standout results. The 64 MB L3 cache and 256.0 GB/s memory bandwidth give this chip a clear advantage in data-heavy parallel tasks. Its 96th percentile ranking among all CPUs reflects this broad strength.

The Intel Core Ultra 5 235 wins in data encryption, find prime numbers, floating point math, and single-thread tests. These are workloads that favor higher per-core clock response and larger per-core caches. The 192 KB L1 and 3 MB L2 per core, combined with a 3.40 GHz base clock, support its 13% single-thread advantage. The floating point win of 15.6% is notable, as is the encryption win of 5.2%. Its 89th percentile ranking places it below the AMD part in overall standing, but its category wins are real and consistent.

The use-case split follows the benchmark pattern. For multithreaded content creation, data processing, physics simulation, and integer-heavy compilation workloads, the AMD Ryzen AI Max+ 392 delivers higher scores. For single-threaded applications, floating point calculations, prime number searches, and encryption tasks, the Intel Core Ultra 5 235 delivers higher scores. The database records AMD at 90,541 average and Intel at 46,062, which positions the AMD part in a higher performance class despite Intel's targeted wins.