AMD Ryzen AI 9 365 vs Intel Xeon 6369P Comparison

The Intel Xeon 6369P and AMD Ryzen AI 9 365 occupy opposite ends of the computing spectrum—a desktop-class server/workstation part versus a low-power mobile processor—yet benchmark results show a surprisingly competitive split across workloads. The Xeon 6369P wins 9 of the 15 head-to-head tests, but the Ryzen AI 9 365 counters with 6 wins, including several in real-world data tasks. The most dramatic single-core gap comes in Cinebench R23 single-core, where the Intel part scores 3,638 versus 1,992 for AMD, a 82.6% advantage. That is a massive margin for any comparison. However, the AMD chip turns the tables in Cinebench R15 multicore, scoring 2,842 against 2,598, an 8.6% lead, despite having fewer wins overall. The data suggests neither chip dominates outright; instead, each is tuned for a different workload profile.

Head-to-Head Benchmarks

The Intel Xeon 6369P’s biggest win is in Cinebench R23 multicore, where it scores 25,774 against AMD's 18,698—a 37.8% lead. This is the largest delta in the entire benchmark set, excluding the single-core anomaly. The Xeon also shows a 20.8% advantage in Cinebench R15 single-core (366 vs. 303) and a 20.5% lead in PassMark find prime numbers (141 vs. 117). In floating-point math, the Intel part scores 74,151 versus 62,802, an 18.1% margin, and it leads PassMark physics by 17.8% (2,008 vs. 1,704). The Xeon also wins PassMark multithread (30,315 vs. 29,467, a 2.9% edge) and PassMark single-thread (4,305 vs. 3,841, a 12.1% edge). The single-thread wins are consistent across both PassMark and Cinebench, indicating a strong per-core advantage.

The AMD Ryzen AI 9 365 wins by smaller margins but in distinct areas. Its best win is PassMark extended instructions, scoring 25,113 versus 22,807, a 9.2% lead. It also wins PassMark random string sorting (39,447 vs. 37,237, a 5.6% edge), data compression (354,510 vs. 346,632, a 2.2% lead), and data encryption (18,297 vs. 17,922, a 2% edge). The integer math result is nearly a tie, with AMD at 101,831 and Intel at 101,013, a 0.8% difference—effectively a statistical dead heat. The AMD chip also wins Cinebench R15 multicore by 8.6%, but that is its only multi-threaded Cinebench win; the Intel part dominates the newer R23 multicore test. Notably, the AMD chip’s wins are all in PassMark or the older Cinebench test, while Intel’s wins include both the newer Cinebench and several PassMark workloads.

The deltaPct values reveal the asymmetry: Intel’s wins range from 2.9% (multithread) to 82.6% (R23 single-core), while AMD’s wins are all under 10%, with the largest at 9.2% (extended instructions). This means Intel wins by larger margins, but AMD wins more often in data-processing tasks. The overall average benchmark score is close: 40,327 for Intel versus 40,048 for AMD, a 0.7% difference. Both chips sit at the 87th percentile in the global CPU ranking, with nearest rivals like the Intel Core i9-13905H (avg 40,313) and AMD Ryzen 9 270 (avg 40,246) sitting within 0.7% of the Intel part.

Architecture Differences

The fundamental divergence begins with the process node: Intel uses a 10nm process at its own foundry, while AMD uses a 4nm process from TSMC. The Intel Xeon 6369P is built on Raptor Lake architecture (specifically Raptor Lake-R), part of the Xeon 6 generation, while the AMD chip uses Zen 5 architecture (codenamed Strix Point) in the Ryzen AI 300 generation. The Intel part has 8 cores and 16 threads; the AMD part has 10 cores and 20 threads, giving AMD a 25% core advantage. Despite that, Intel’s base clock is 3.30 GHz versus AMD’s 2.00 GHz, and Intel’s boost clock is 5.70 GHz versus 5.00 GHz—so Intel compensates for fewer cores with much higher frequencies.

Cache layouts differ significantly. Both have 80 KB of L1 per core, but Intel’s L2 is 2 MB per core versus AMD’s 1 MB per core. Intel’s L3 is 24 MB shared, while AMD’s L3 is 16 MB. The die size is close (257 mm² for Intel, 233 mm² for AMD), but the transistor counts are not listed. Memory support also diverges: Intel supports both DDR4 and DDR5, while AMD supports DDR5 and LPDDR5X. Intel has dual-channel memory bus, and AMD also has dual-channel, but AMD’s memory bandwidth is listed at 89.6 GB/s, while Intel’s is not specified. Intel supports ECC memory; AMD does not. Intel’s PCIe is Gen 5 with 16 lanes (CPU only), while AMD uses Gen 4 with 16 lanes. Intel has no integrated graphics, but AMD includes Radeon 880M graphics. The sockets are incompatible: Intel Socket 1700 versus AMD Socket FP8.

FAQ

Q: Which processor has a higher single-core score?

A: The Intel Xeon 6369P leads in every single-core test: Cinebench R15 single-core scores 366 vs. 303 (20.8% lead), Cinebench R23 single-core scores 3,638 vs. 1,992 (82.6% lead), and PassMark single-thread scores 4,305 vs. 3,841 (12.1% lead).

Q: Does the AMD Ryzen AI 9 365 win any multi-threaded tests?

A: Yes, it wins Cinebench R15 multicore (2,842 vs. 2,598, an 8.6% lead). However, in the newer Cinebench R23 multicore test, the Intel Xeon wins decisively with 25,774 vs. 18,698, a 37.8% margin.

Q: How do the average benchmark scores compare?

A: The Intel Xeon 6369P has an average benchmark score of 40,327, while the AMD Ryzen AI 9 365 scores 40,048. The difference is 0.7%, placing both at the 87th percentile against all CPUs.

Q: What is the core and thread count difference?

A: The AMD Ryzen AI 9 365 has 10 cores and 20 threads, while the Intel Xeon 6369P has 8 cores and 16 threads. AMD has 2 more cores and 4 more threads.

Q: Which processor supports ECC memory?

A: Only the Intel Xeon 6369P supports ECC memory. The AMD Ryzen AI 9 365 does not list ECC support.

Q: Does either processor include integrated graphics?

A: Only the AMD Ryzen AI 9 365 includes integrated graphics (Radeon 880M). The Intel Xeon 6369P lists integrated graphics as N/A.

Specification Differences

| Specification | Intel Xeon 6369P | AMD Ryzen AI 9 365 |

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

| Manufacturer | Intel | AMD |

| Cores | 8 | 10 |

| Threads | 16 | 20 |

| Base Clock | 3.30 GHz | 2.00 GHz |

| Boost Clock | 5.70 GHz | 5.00 GHz |

| TDP | 95 W | 28 W |

| Socket | Intel Socket 1700 | AMD Socket FP8 |

| Architecture | Raptor Lake | Zen 5 |

| Codename | Raptor Lake-R | Strix Point |

| Generation | Xeon 6 (Raptor Lake Refresh) | Ryzen AI 300 (Zen 5 / Zen 5c) |

| Process Node | 10 nm | 4 nm |

| Foundry | Intel | TSMC |

| Die Size | 257 mm² | 233 mm² |

| L2 Cache | 2 MB (per core) | 1 MB (per core) |

| L3 Cache | 24 MB (shared) | 16 MB |

| Memory Support | DDR4, DDR5 | DDR5, LPDDR5X |

| Memory Bus | Dual-channel | Dual-channel |

| Memory Bandwidth | Not listed | 89.6 GB/s |

| ECC Memory | Yes | No |

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

| Integrated Graphics | N/A | Radeon 880M |

| Market Segment | Server/Workstation | Mobile |

| Release Date | 2025-02-23 | 2024-06-30 |

| Launch MSRP | $606 | Not listed |

| Part Number | SRPLQ | 100-000001530 |

Where Each One Wins

The Intel Xeon 6369P is the clear winner for workloads that demand raw per-core performance and sustained multi-threaded compute under higher power envelopes. Its 82.6% lead in Cinebench R23 single-core and 37.8% lead in Cinebench R23 multicore make it the choice for rendering, simulation, or any task that scales with the newer Cinebench engine. It also wins floating-point math (18.1% ahead), physics (17.8% ahead), and prime number finding (20.5% ahead), indicating strength in scientific and engineering calculations. The Xeon’s higher TDP (95 W vs. 28 W) and ECC support further position it for workstation reliability. The launch MSRP of $606 reflects its server/workstation segment, though no pricing comparison is made here.

The AMD Ryzen AI 9 365 wins in data-centric workloads that favor its higher core count and 4nm efficiency. It leads in extended instructions (9.2%), random string sorting (5.6%), data compression (2.2%), and data encryption (2%). These are exactly the tasks found in database operations, archive handling, and crypto workloads. The AMD chip also has integrated Radeon 880M graphics, making it a self-contained mobile solution, and its 28 W TDP suggests it is designed for battery-conscious devices. The 10-core, 20-thread configuration gives it a parallel advantage in lightly-threaded batch processing, as shown by its Cinebench R15 multicore win. For users who prioritize portability and integrated graphics, the AMD part is the obvious pick, despite its lower clocks and smaller cache.

The data also shows a nuanced middle ground: in integer math, the two chips are within 0.8% (101,831 vs. 101,013), meaning neither has a meaningful advantage for general integer calculations. The PassMark multithread score is also close, with Intel ahead by just 2.9%. This suggests that for mixed workloads, the choice depends more on platform features (ECC, PCIe generation, memory type) than raw compute. The Intel part’s 87th percentile and the AMD part’s 87th percentile confirm they are peers in the broader market, but the benchmark deltas show they excel in different domains—Intel for heavy compute, AMD for data throughput and mobile efficiency.