AMD EPYC 4465P vs Intel Core i9-13900KS Comparison

# AMD EPYC 4465P vs Intel Core i9-13900KS

The benchmark database records 17 head-to-head comparisons between these two processors, and the Intel Core i9-13900KS wins 15 of them, while the AMD EPYC 4465P takes only 2. The average benchmark scores tell a similar story: the EPYC 4465P sits at 66,925 with a 93rd percentile ranking, while the i9-13900KS averages 64,051, also in the 93rd percentile. However, the EPYC's wins come in specific workloads where its architecture provides a distinct advantage, making this a contest of specialization rather than a simple sweep.

Where Each One Wins

The AMD EPYC 4465P claims victory in exactly two recorded tests: PassMark find prime numbers and PassMark physics. The prime number test shows a 31.5% advantage over the Intel part, a substantial margin that points to the Zen 5 architecture's efficiency in integer-heavy, branch-predictable workloads. The physics test shows a smaller but still meaningful 6% lead, suggesting the EPYC handles physics simulation calculations more effectively despite having fewer cores.

Every other benchmark favors the Intel Core i9-13900KS. The single-threaded results are close, with Intel leading by 2.9% in PassMark single thread, but the multi-threaded and specialized workloads show much larger gaps. The i9-13900KS dominates in data compression (29.2% ahead), data encryption (32.6% ahead), floating point math (31.6% ahead), and random string sorting (25.1% ahead). These are workload categories where the Intel part's higher core count and faster clock speeds translate into clear throughput advantages.

The use-case split is therefore straightforward: the EPYC 4465P suits integer-heavy scientific or mathematical workloads where prime number calculation and physics simulation are central, while the i9-13900KS handles general productivity, encryption, compression, and floating-point tasks with decisive margins.

Architecture Differences

The two processors come from fundamentally different design philosophies. The AMD EPYC 4465P uses the Zen 5 architecture on a 4 nm TSMC process, with 12 cores and 24 threads. It features a 3.40 GHz base clock and a 5.40 GHz boost clock, with a 65 W TDP. The Intel Core i9-13900KS uses Raptor Lake architecture on Intel's 10 nm process, packing 24 cores and 32 threads. Its base clock is 3.20 GHz, but the boost clock reaches 6.00 GHz, and the TDP is 150 W.

Cache configurations differ notably. Both have 80 KB of L1 cache per core, but the EPYC's L2 is 1 MB per core while the i9-13900KS has 2 MB per core. The L3 cache favors AMD: the EPYC has 64 MB shared, while the Intel part has 36 MB shared. The die size also reflects the different approaches: the EPYC uses a 2x 70.6 mm² design with 16,630 million transistors, while the i9-13900KS uses a single 257 mm² die.

Memory support is another differentiator. The EPYC supports only DDR5 with dual-channel memory and 89.6 GB/s bandwidth, while the i9-13900KS supports both DDR4 and DDR5, also dual-channel with the same 89.6 GB/s bandwidth. Both support ECC memory. The PCIe configurations differ as well: the EPYC provides Gen 5 with 24 CPU-only lanes, while the i9-13900KS offers Gen 5 with 20 lanes. The EPYC integrates Radeon Graphics, while the Intel part uses UHD Graphics 770. Socket compatibility also diverges: the EPYC uses AMD Socket AM5, and the i9-13900KS uses Intel Socket 1700.

Head-to-Head Benchmarks

The Cinebench results show consistent Intel advantages across all versions. In Cinebench R15 multi-core, the i9-13900KS scores 5,177 against the EPYC's 4,326, a 16.4% lead. Single-core R15 follows the same pattern: 730 versus 610, also 16.4% ahead. Cinebench R20 multi-core shows 21,574 versus 18,025 (16.5% lead), and single-core shows 3,045 versus 2,544 (16.5% lead). Cinebench R23 multi-core gives 51,368 versus 42,918 (16.4% lead), and single-core gives 7,252 versus 6,059 (16.5% lead). The consistency of these margins, all within a tight 16.4% to 16.5% range, indicates a stable architectural advantage rather than a workload-specific quirk.

PassMark tests reveal larger disparities in certain areas. Data compression shows the i9-13900KS at 814,838 against the EPYC's 577,210, a 29.2% gap. Data encryption is even wider: 47,772 versus 32,184, a 32.6% difference. Floating point math favors Intel at 154,805 versus 105,833, a 31.6% margin. Random string sorting shows 90,257 versus 67,597, a 25.1% lead. Integer math gives the i9-13900KS a 17.3% edge (211,027 versus 174,551), and multi-thread performance shows a 17.8% lead (60,644 versus 49,871). Extended instructions are closer but still favor Intel: 48,217 versus 42,867, an 11.1% difference.

The two AMD wins stand out precisely because they break this pattern. The prime number test shows the EPYC at 338 versus the i9-13900KS at 257, a 31.5% advantage for AMD. The physics test gives the EPYC 3,647 against Intel's 3,441, a 6% lead. These results indicate that the Zen 5 architecture's integer execution pipeline handles specific algorithmic patterns more efficiently than Raptor Lake, even when the Intel part has more cores and higher clock speeds.

The Verdict

The data directs a clear verdict. The Intel Core i9-13900KS is the stronger general-purpose processor, winning 15 of 17 comparisons with margins ranging from 2.9% to 32.6%. Its advantages in compression, encryption, floating-point math, and multi-threaded rendering make it the default choice for content creation, data processing, and productivity workloads. The 24-core configuration and 6.00 GHz boost clock provide raw throughput that the EPYC cannot match in most scenarios.

The AMD EPYC 4465P earns its place in a narrower set of workloads. Its prime number processing advantage of 31.5% and physics simulation lead of 6% indicate that the Zen 5 architecture handles specific integer-heavy algorithms with exceptional efficiency. For environments where those exact workloads dominate, the EPYC's lower TDP of 65 W compared to Intel's 150 W also suggests a more power-efficient option, though the database does not record power measurements.

Server and workstation buyers should note that the EPYC 4465P targets the server/workstation segment, while the i9-13900KS is a desktop part. The EPYC's 24 PCIe Gen 5 lanes versus Intel's 20 lanes provides slightly more expansion headroom for server peripherals. However, the i9-13900KS offers DDR4 compatibility in addition to DDR5, which may matter for existing system upgrades. The verdict from the benchmarks: choose the i9-13900KS for broad performance, choose the EPYC 4465P for specialized integer and physics workloads.

FAQ

Q: Which processor has more cores?

A: The Intel Core i9-13900KS has 24 cores and 32 threads, while the AMD EPYC 4465P has 12 cores and 24 threads.

Q: What is the clock speed difference?

A: The EPYC 4465P has a base clock of 3.40 GHz and a boost clock of 5.40 GHz. The i9-13900KS has a base clock of 3.20 GHz and a boost clock of 6.00 GHz.

Q: Which CPU is faster in Cinebench R23 multi-core?

A: The Intel Core i9-13900KS scores 51,368 in Cinebench R23 multi-core, which is 16.4% higher than the EPYC 4465P's score of 42,918.

Q: Does the AMD EPYC 4465P win any benchmarks?

A: Yes, it wins two tests: PassMark find prime numbers with a 31.5% lead over the i9-13900KS, and PassMark physics with a 6% lead.

Q: What memory types do these processors support?

A: The EPYC 4465P supports only DDR5, while the i9-13900KS supports both DDR4 and DDR5. Both use dual-channel memory with 89.6 GB/s bandwidth.

Q: What is the TDP difference?

A: The AMD EPYC 4465P has a TDP of 65 W, while the Intel Core i9-13900KS has a TDP of 150 W.

Specification Differences

| Specification | AMD EPYC 4465P | Intel Core i9-13900KS |

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

| Cores | 12 | 24 |

| Threads | 24 | 32 |

| Base Clock | 3.40 GHz | 3.20 GHz |

| Boost Clock | 5.40 GHz | 6.00 GHz |

| TDP | 65 W | 150 W |

| Socket | AMD Socket AM5 | Intel Socket 1700 |

| Architecture | Zen 5 | Raptor Lake |

| Process Node | 4 nm (TSMC) | 10 nm (Intel) |

| Die Size | 2x 70.6 mm² | 257 mm² |

| Transistors | 16,630 million | Not recorded |

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

| L3 Cache | 64 MB shared | 36 MB shared |

| Memory Support | DDR5 | DDR4, DDR5 |

| PCIe Lanes | Gen 5, 24 lanes | Gen 5, 20 lanes |

| Integrated Graphics | Radeon Graphics | UHD Graphics 770 |

| Market Segment | Server/Workstation | Desktop |

| Multiplier Unlocked | No | Yes |

| Launch MSRP | $399 | $699 |