AMD EPYC 9654 vs Intel Core i9-13900H Comparison

FAQ

Q: How do the AMD EPYC 9654 and Intel Core i9-13900H compare in overall average benchmark scores?

A: The EPYC 9654 records an average benchmark score of 29,409, while the Core i9-13900H sits at 28,886. Both processors place in the 81st percentile among all CPUs in the database, indicating they are statistically close in aggregate performance despite very different designs.

Q: Which processor wins more head-to-head benchmark comparisons?

A: The AMD EPYC 9654 wins all six recorded head-to-head tests, covering Cinebench R15, R20, and R23 in both single-core and multi-core modes. The Intel Core i9-13900H has zero wins in the direct comparison set.

Q: What is the largest performance gap in the head-to-head results?

A: The biggest delta appears in Cinebench R23 single-core, where the EPYC 9654 scores 14,354 versus the Core i9-13900H's 1,964.5, a 630.7% advantage. This is notable because the Intel chip has a much higher boost clock, yet the AMD processor still dominates in this test.

Q: How does the EPYC 9654's nearest rival comparison differ from the Core i9-13900H's?

A: The EPYC 9654's closest rival is the AMD Ryzen 7 3800X with an average score of 29,447, a delta of -0.1%, while the Core i9-13900H's nearest rival is the Intel Core i5-12600H at 28,882, a delta of 0%. Both chips sit within a very tight band of similar-scoring processors.

Q: Do these processors share the same memory support?

A: No. The EPYC 9654 supports DDR5 memory with a twelve-channel bus and 460.8 GB/s bandwidth, while the Core i9-13900H supports both DDR4 and DDR5 with a dual-channel bus. The EPYC also supports ECC memory, which the Intel chip does not.

Q: What are the core and thread counts for each processor?

A: The AMD EPYC 9654 has 96 cores and 192 threads, while the Intel Core i9-13900H has 14 cores and 20 threads. This massive difference in core count drives much of the multi-core benchmark disparity.

Architecture Differences

The AMD EPYC 9654 and Intel Core i9-13900H represent fundamentally different design philosophies. The EPYC 9654 is a server/workstation part built on TSMC's 5 nm process node, using the Zen 4 architecture under the Genoa codename. It contains 78,840 million transistors across a die configuration of 12x 72 mm². The Core i9-13900H, by contrast, is a mobile processor built on Intel's 10 nm node, using the Raptor Lake architecture with a single 257 mm² die.

The cache hierarchies diverge sharply. The EPYC 9654 offers 64 KB of L1 cache per core, 1 MB of L2 per core, and a massive 384 MB of shared L3 cache. The Core i9-13900H provides 80 KB of L1 per core, 2 MB of L2 per core, and only 24 MB of shared L3. The EPYC's L3 cache is 16 times larger, which likely explains some of its extraordinary performance in workloads that benefit from large working sets.

Memory architecture also separates these two. The EPYC 9654 uses a twelve-channel memory bus supporting DDR5 with a theoretical bandwidth of 460.8 GB/s, plus ECC memory support. The Core i9-13900H uses a dual-channel bus supporting both DDR4 and DDR5, with no ECC capability. The EPYC also offers 128 PCIe Gen 5 lanes (CPU only), while the Intel chip provides 8 Gen 5 lanes.

The Intel part includes integrated graphics in the form of Iris Xe Graphics 96EU, whereas the EPYC 9654 has no integrated graphics listed. The EPYC targets the server/workstation segment with a socket of AMD Socket SP5, while the Core i9-13900H is a mobile chip on Intel BGA 1744. Both processors are marked as Active in production status, and neither has an unlocked multiplier.

Head-to-Head Benchmarks

The recorded head-to-head data covers only Cinebench tests, and the results are decisively one-sided. In Cinebench R15 multi-core, the EPYC 9654 scores 10,248 against the Core i9-13900H's 2,666.5, a 284.3% advantage. The single-core R15 test shows the EPYC at 1,446 versus 279, a 418.3% lead. These deltas are substantial even accounting for the different market segments.

Cinebench R20 amplifies the gap. Multi-core sees the EPYC 9654 at 42,703 versus 9,676, a 341.3% delta. Single-core R20 has the EPYC at 6,028 against 1,365, a 341.6% difference. The pattern holds consistently: the AMD chip wins by roughly 3.4 to 4.2 times in these tests.

Cinebench R23 delivers the most extreme results. Multi-core shows the EPYC 9654 at 101,675 versus 17,471, a 482% advantage. Single-core R23 records the EPYC at 14,354 against 1,964.5, a 630.7% delta. This single-core result is particularly striking because the Core i9-13900H has a boost clock of 5.40 GHz compared to the EPYC's 3.70 GHz. The database shows that raw clock speed does not translate into Cinebench single-core dominance for the Intel part.

The wins tally stands at 6 for the AMD EPYC 9654 and 0 for the Intel Core i9-13900H. No benchmark in the head-to-head set favors the mobile chip. The data suggests that the EPYC's architecture, cache size, and memory bandwidth combine to overcome the Intel chip's clock advantage in every recorded test.

The Verdict

The benchmark data is unambiguous: the AMD EPYC 9654 outperforms the Intel Core i9-13900H in every recorded head-to-head test. For workloads measured by Cinebench, the EPYC 9654 is the clear choice, delivering anywhere from 284.3% to 630.7% higher scores. The server-class processor's 96 cores, 384 MB of L3 cache, and twelve-channel DDR5 memory provide a structural advantage that the mobile chip cannot offset.

The Intel Core i9-13900H, however, is not without reason for existence. Its 45 W TDP, integrated graphics, and dual-channel memory support suit mobile computing scenarios where power and space are constrained. The EPYC 9654's 360 W TDP and server socket make it impractical for laptops. The database shows two processors aimed at entirely different deployment contexts.

Who should pick which? Data centers, research institutions, and workstation users running compute-heavy Cinebench workloads should choose the EPYC 9654. Mobile professionals who need a capable processor in a laptop form factor, with integrated graphics and lower power consumption, would select the Core i9-13900H. The average benchmark scores are close (29,409 versus 28,886), but the head-to-head results reveal the EPYC's dominance in the specific tests recorded.

Specification Differences

| Specification | AMD EPYC 9654 | Intel Core i9-13900H |

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

| Cores | 96 | 14 |

| Threads | 192 | 20 |

| Base Clock | 2.40 GHz | 2.60 GHz |

| Boost Clock | 3.70 GHz | 5.40 GHz |

| TDP | 360 W | 45 W |

| Socket | AMD Socket SP5 | Intel BGA 1744 |

| Architecture | Zen 4 | Raptor Lake |

| Codename | Genoa | Raptor Lake-H |

| Process Node | 5 nm | 10 nm |

| Foundry | TSMC | Intel |

| Transistors | 78,840 million | Not listed |

| Die Size | 12x 72 mm² | 257 mm² |

| L1 Cache | 64 KB (per core) | 80 KB (per core) |

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

| L3 Cache | 384 MB (shared) | 24 MB (shared) |

| Memory Support | DDR5 | DDR4, DDR5 |

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

| Memory Bandwidth | 460.8 GB/s | Not listed |

| ECC Memory | Yes | No |

| PCIe | Gen 5, 128 Lanes (CPU only) | Gen 5, 8 Lanes (CPU only) |

| Integrated Graphics | None | Iris Xe Graphics 96EU |

| Market Segment | Server/Workstation | Mobile |

| Release Date | 2022-11-09 | 2023-01-03 |

| Launch MSRP | $11805 | $617 |

Where Each One Wins

The AMD EPYC 9654 wins every recorded head-to-head benchmark, but the nature of those wins points to specific use cases. Multi-core Cinebench tests show the EPYC leading by 284.3% to 482%, reflecting its 96-core, 192-thread design. This makes it suited for heavily parallel workloads such as rendering, scientific simulation, and server-side batch processing. The 384 MB L3 cache and 460.8 GB/s memory bandwidth further support memory-intensive applications.

The EPYC's single-core wins are equally decisive, ranging from 418.3% to 630.7% in Cinebench R15, R20, and R23. This is counterintuitive given the Intel chip's higher boost clock, but the data shows the EPYC's architecture delivers superior single-thread results in these tests. The implication is that the EPYC 9654 is not merely a multi-core brute; it also handles latency-sensitive single-threaded tasks effectively in the measured scenarios.

The Intel Core i9-13900H wins in scenarios not covered by the head-to-head set. Its 45 W TDP makes it viable for thin-and-light laptops, whereas the EPYC's 360 W TDP demands a server chassis with robust cooling. The integrated Iris Xe Graphics 96EU provides display output and basic GPU acceleration without a discrete card, while the EPYC has no integrated graphics. The dual-channel memory support and smaller die size (257 mm² versus 12x 72 mm²) reflect a design optimized for space and power efficiency.

The database also shows the Core i9-13900H has recorded scores in additional tests beyond Cinebench, including 3DMark and Passmark suites. In Passmark single-thread, it scores 3,754; in Passmark integer math, 97,159; and in Passmark floating-point math, 69,611. These are not directly compared to the EPYC, but they indicate the Intel chip's competence in general-purpose mobile workloads. The EPYC 9654 has no recorded scores in those specific tests, so the comparison remains incomplete for those metrics.

The verdict from the recorded data is straightforward: for Cinebench-based performance, choose the EPYC 9654. For mobile deployment with lower power and integrated graphics, the Core i9-13900H remains the only feasible option between these two. The 81st percentile ranking for both chips in the overall CPU population shows that each holds its own among a broad field, but their roles in a system could hardly be more different.