AMD Ryzen AI 9 HX 375 vs Intel Core Ultra 5 225F Comparison

The database places the AMD Ryzen AI 9 HX 375 and the Intel Core Ultra 5 225F in different market segments: the AMD part is a mobile 12-core processor with 24 threads, while the Intel part is a desktop 10-core processor with 10 threads. Their aggregate results separate them clearly: the AMD processor records an average benchmark score of 46030 and sits at the 89th percentile of all CPUs, while the Intel processor records 37313 and sits at the 85th percentile. The head-to-head test log gives AMD 9 wins and Intel 6 wins.

The Verdict

The recorded data points to the AMD Ryzen AI 9 HX 375 for workloads that scale across many threads, integer math, compression, sorting, and extended instructions. It wins the Cinebench R23 multicore test by 32.5%, the PassMark integer math test by 83.3%, the PassMark data compression test by 30.3%, and the PassMark random string sorting test by 19.4%. It also carries a Radeon 890M integrated GPU, making it the only one of the two with recorded integrated graphics.

The Intel Core Ultra 5 225F is the data-backed choice for floating-point math, physics, prime-number finding, encryption, and PassMark single-thread work. It leads by 65.3% in PassMark find prime numbers, 25.1% in PassMark physics, 18.8% in PassMark floating point math, 12.1% in PassMark single-thread, and 8.2% in PassMark data encryption. Because the Intel part has no integrated graphics and uses a desktop socket, the recorded data ties it to desktop systems that provide graphics elsewhere.

The AMD part’s average benchmark score of 46030 places it at the 89th percentile. Its nearest rivals are the Intel Core Ultra 5 235 at 46062, the AMD EPYC 4364P at 45970, the Intel Core i9-13900HX at 46098, and the AMD EPYC 7303 at 45960; the deltas are -0.1%, 0.1%, -0.1%, and 0.2% respectively. The Intel part’s average score of 37313 places it at the 85th percentile, with nearest rivals the Intel Core i9-13900HK at 37425, the AMD Ryzen 7 7735H at 37161, the Intel Core i7-13700 at 37135, and the AMD Ryzen 7 160 at 37117; the deltas are -0.3%, 0.4%, 0.5%, and 0.5% respectively.

Architecture Differences

The two processors use different architectures. AMD uses Zen 5 with the Strix Point codename and belongs to the Ryzen AI 300 (Zen 5 / Zen 5c) generation. Intel uses Arrow Lake with the Arrow Lake-S codename and belongs to the Core Ultra Series 2, Ultra 5 (Arrow Lake) generation. Both are manufactured by TSMC, but on different nodes: AMD uses 4 nm, Intel uses 3 nm. The Intel die is 243 mm² and contains 17,800 million transistors; the AMD die is 233 mm² and the transistor count is not recorded.

Core organization differs. AMD has 12 cores and 24 threads, while Intel has 10 cores and 10 threads. AMD’s base clock is 2.00 GHz with a boost of 5.10 GHz; Intel’s base clock is 3.30 GHz with a boost of 4.90 GHz. The AMD part is rated at 28 W TDP and uses AMD Socket FP8, while the Intel part is rated at 65 W TDP and uses Intel Socket 1851.

Cache structures also differ. AMD provides 80 KB of L1 and 1 MB of L2 per core, with 16 MB of L3. Intel provides 192 KB of L1 and 3 MB of L2 per core, with 20 MB of shared L3. Memory support differs as well: AMD accepts DDR5 and LPDDR5X, Intel accepts DDR5. Both have dual-channel memory buses, but the recorded memory bandwidth is 89.6 GB/s for AMD and 102.4 GB/s for Intel. PCIe connectivity differs: AMD uses Gen 4 with 16 CPU lanes, Intel uses Gen 5 with 20 CPU lanes. Integrated graphics are present only on AMD, as Radeon 890M; Intel lists N/A. The AMD part is a mobile processor, while the Intel part is a desktop processor. Their release dates are 2024-06-30 and 2025-01-06 respectively.

FAQ

Q: Which processor has more cores and threads?

A: The AMD Ryzen AI 9 HX 375 has 12 cores and 24 threads. The Intel Core Ultra 5 225F has 10 cores and 10 threads.

Q: Which processor includes integrated graphics?

A: The AMD part includes Radeon 890M integrated graphics. The Intel part lists N/A for integrated graphics, so the recorded data assigns no iGPU to it.

Q: Which processor is faster in Cinebench R23 multicore?

A: The AMD part scores 21812 against 16467, a 32.5% advantage in the head-to-head result.

Q: Where does the Intel processor hold its biggest lead?

A: In PassMark find prime numbers, Intel scores 352 versus 122, a 65.3% margin. It also leads in PassMark physics, floating point math, data encryption, and PassMark single-thread.

Q: What memory bandwidth is recorded for each?

A: AMD records 89.6 GB/s with DDR5 and LPDDR5X support. Intel records 102.4 GB/s with DDR5 support. Both have dual-channel memory buses.

Q: What are the process nodes and sockets?

A: AMD uses a 4 nm TSMC process with AMD Socket FP8. Intel uses a 3 nm TSMC process with Intel Socket 1851.

Specification Differences

| Field | AMD Ryzen AI 9 HX 375 | Intel Core Ultra 5 225F |

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

| Manufacturer | AMD | Intel |

| Series | N/A | Core Ultra Series 2 |

| Cores | 12 | 10 |

| Threads | 24 | 10 |

| Base clock | 2.00 GHz | 3.30 GHz |

| Boost clock | 5.10 GHz | 4.90 GHz |

| TDP | 28 W | 65 W |

| Socket | AMD Socket FP8 | Intel Socket 1851 |

| Architecture | Zen 5 | Arrow Lake |

| Codename | Strix Point | Arrow Lake-S |

| Generation | Ryzen AI 300 (Zen 5 / Zen 5c) | Ultra 5 (Arrow Lake) |

| Process node | 4 nm | 3 nm |

| Transistors | N/A | 17,800 million |

| Die size | 233 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 | 16 MB | 20 MB (shared) |

| Memory support | DDR5, LPDDR5X | DDR5 |

| Memory bandwidth | 89.6 GB/s | 102.4 GB/s |

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

| Integrated graphics | Radeon 890M | N/A |

| Market segment | Mobile | Desktop |

| Release date | 2024-06-30 | 2025-01-06 |

| Launch MSRP | N/A | $231 |

| Part number | 100-000001682 | SRQD2SRVF9 |

Head-to-Head Benchmarks

The database records 9 wins for AMD and 6 wins for Intel. The largest AMD margin is 83.3% in PassMark integer math, where AMD scores 121754 versus 66417. The second largest AMD margin is 32.5% in Cinebench R23 multicore, 21812 versus 16467. AMD also takes PassMark data compression by 30.3%, Cinebench R15 multicore by 25.3%, PassMark random string sorting by 19.4%, PassMark multithread by 6.2%, Cinebench R23 singlecore by 5%, Cinebench R15 singlecore by 4.9%, and PassMark extended instructions by 4.4%.

Intel’s largest margin is 65.3% in PassMark find prime numbers, 352 versus 122. It also wins PassMark physics by 25.1%, with 2430 versus 1819, and PassMark floating point math by 18.8%, with 92554 versus 75153. Intel leads PassMark single-thread by 12.1%, with 4397 versus 3867, and PassMark data encryption by 8.2%, with 22648 versus 20802. The PassMark single-thread and PassMark singlethread entries both record identical values in the database.

Where Each One Wins

AMD wins the tests that load many threads and integer operations. The 24-thread part takes Cinebench R23 multicore by 32.5%, Cinebench R15 multicore by 25.3%, PassMark multithread by 6.2%, PassMark integer math by 83.3%, PassMark data compression by 30.3%, PassMark random string sorting by 19.4%, and PassMark extended instructions by 4.4%. It also wins both Cinebench single-core tests, by 4.9% in R15 singlecore and by 5% in R23 singlecore. These results place the AMD part ahead in compression, sorting, integer-heavy, and multithreaded workloads.

Intel wins the tests that stress floating-point throughput, physics, prime-number loops, encryption, and PassMark single-thread execution. It leads in PassMark floating point math by 18.8%, PassMark physics by 25.1%, PassMark find prime numbers by 65.3%, PassMark data encryption by 8.2%, and PassMark single-thread by 12.1%. The Intel part’s higher base clock, 3.30 GHz versus 2.00 GHz, and larger shared L3, 20 MB versus 16 MB, appear alongside those wins. The data therefore splits cleanly: AMD for threaded, integer, and compression-oriented work, Intel for floating-point, physics, and PassMark single-thread work.