AMD EPYC 9745 vs Intel Xeon 6980P Comparison

FAQ

Q: Which processor has a higher average benchmark score?

A: The AMD EPYC 9745 records an average benchmark score of 425,973, placing it in the 100th percentile among all CPUs. The Intel Xeon 6980P averages 251,516, which places it in the 99th percentile.

Q: How does the EPYC 9745 compare to its closest rivals?

A: The EPYC 9745 leads its nearest rival, the AMD Ryzen Threadripper PRO 9995WX, by 3.4%. It is also 7.1% ahead of the AMD EPYC 9655P, 12.3% ahead of the AMD EPYC 9535, and 14.1% ahead of the AMD EPYC 9655.

Q: Where does the Xeon 6980P sit among its nearest competitors?

A: The Xeon 6980P is 3% ahead of the AMD EPYC 9634 and 5.6% ahead of the Intel Xeon 6747P. However, it trails the AMD EPYC 9684X by 5.8% and the AMD Ryzen Threadripper 9970X by 10.1%.

Q: Do both processors have the same core and thread counts?

A: Yes, both the AMD EPYC 9745 and the Intel Xeon 6980P have 128 cores and 256 threads.

Q: What are the memory specifications for each processor?

A: Both support DDR5 memory with a twelve-channel memory bus. The EPYC 9745 has a memory bandwidth of 576.0 GB/s, while the Xeon 6980P has a higher memory bandwidth of 614.4 GB/s.

Q: Which processor has more PCIe lanes?

A: The AMD EPYC 9745 provides Gen 5 with 128 lanes (CPU only), while the Intel Xeon 6980P provides Gen 5 with 96 lanes (CPU only).

Architecture Differences

The AMD EPYC 9745 is built on the Zen 5 architecture, codenamed Turin, and belongs to the EPYC 9005 series. It is manufactured on a 3 nm process at TSMC. The Intel Xeon 6980P uses the Granite Rapids architecture, part of the Xeon 6 generation (Granite Rapids-AP), and is manufactured on a 5 nm process at Intel. This process difference is significant: the AMD part uses a more advanced node, which contributes to its efficiency and performance characteristics. The Xeon 6980P has a die size of 3x 598 mm², while the EPYC 9745 does not have a recorded die size in the database.

Cache hierarchies differ substantially. The EPYC 9745 has 80 KB of L1 per core, 1 MB of L2 per core, and 256 MB of shared L3 cache. The Xeon 6980P has 112 KB of L1 per core, 2 MB of L2 per core, and 504 MB of shared L3 cache. The Intel part therefore has a larger cache at every level, including nearly double the L3 capacity. Despite this, benchmark results show the AMD processor consistently outperforming the Intel part across all recorded tests.

Clock speeds tell a mixed story. The EPYC 9745 has a base clock of 2.40 GHz and a boost clock of 3.70 GHz. The Xeon 6980P has a lower base clock of 2.00 GHz but a higher boost clock of 3.90 GHz. The AMD part can maintain a higher base frequency, while the Intel part can reach a higher peak frequency. The EPYC 9745 has a TDP of 400 watts, while the Xeon 6980P has a TDP of 500 watts. The AMD processor draws less power while delivering significantly higher performance in the recorded benchmarks.

Socket and platform support also differ. The EPYC 9745 uses AMD Socket SP5, while the Xeon 6980P uses Intel Socket 7529. Both are server/workstation parts with active production status. Neither has integrated graphics, and neither has an unlocked multiplier. The EPYC 9745 was released on October 9, 2024, while the Xeon 6980P was released earlier on September 23, 2024. The EPYC 9745 has a launch MSRP of $12141, while the Xeon 6980P has a launch MSRP of $12460.

Head-to-Head Benchmarks

The AMD EPYC 9745 wins every single head-to-head benchmark in the database. Out of 17 recorded comparisons, it takes all 17. The Intel Xeon 6980P does not win a single test. The margins are substantial across nearly every category.

In Cinebench tests, the EPYC 9745 dominates. In Cinebench R15 multicore, it scores 11,198 against the Xeon's 6,367, a 75.9% advantage. The single-core R15 test shows the same 75.9% delta, with scores of 1,580 versus 898. Cinebench R20 multicore results are 46,659 versus 26,533, again a 75.9% gap, and R20 single-core is 6,586 versus 3,745, also 75.9%. Cinebench R23 multicore shows 111,093 versus 63,175, a 75.8% difference, while R23 single-core is 15,683 versus 8,918, a 75.9% gap. These consistent deltas across all Cinebench versions indicate a fundamental per-clock and multi-core performance advantage for the Zen 5 part.

PassMark results reinforce the pattern. The largest single margin is in PassMark physics, where the EPYC 9745 scores 17,122 versus the Xeon's 3,350, a massive 411.1% advantage. This is the most extreme difference in the entire comparison. Integer math also shows a huge gap: 1,224,315 versus 637,476, a 92.1% delta. Random string sorting is close behind at 94.8%, with scores of 468,975 versus 240,792. Data encryption shows an 83.2% advantage (229,447 versus 125,246). Find prime numbers is 76.4% higher (979 versus 555). Multithread performance is 75.8% higher (130,698 versus 74,324). Data compression is 66.2% higher (3,929,890 versus 2,364,519). Single-thread performance is 66.9% higher (2,806 versus 1,681). Floating point math is 51.7% higher (761,219 versus 501,720). Extended instructions show the smallest but still decisive gap at 30.6% (280,477 versus 214,794).

Even the narrowest victory for the AMD part is a 30.6% lead. The EPYC 9745 does not just edge out the Xeon 6980P; it outperforms it by wide margins in every workload category represented in the database. The Xeon's larger cache and higher boost clock do not translate into any benchmark win.

The Verdict

The data is unambiguous. The AMD EPYC 9745 outperforms the Intel Xeon 6980P in every recorded benchmark, often by margins exceeding 75%. The EPYC 9745 also does so with a lower TDP of 400 watts versus 500 watts, a more advanced 3 nm process versus 5 nm, and a lower launch MSRP of $12141 versus $12460. The Intel part offers a higher boost clock of 3.90 GHz versus 3.70 GHz, larger caches (504 MB L3 versus 256 MB L3), and higher memory bandwidth (614.4 GB/s versus 576.0 GB/s), but none of these advantages produce a single winning benchmark result.

The EPYC 9745 also sits in the 100th percentile of all CPUs, while the Xeon 6980P sits in the 99th. The average benchmark score difference is 425,973 versus 251,516, a gap of roughly 69%. In the nearest rival comparison, the EPYC 9745 leads its closest competitor by 3.4%, while the Xeon 6980P trails two of its nearest rivals by 5.8% and 10.1%. The conclusion is straightforward: for any workload represented in the database, the AMD EPYC 9745 is the stronger processor.

Specification Differences

| Field | AMD EPYC 9745 | Intel Xeon 6980P |

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

| Architecture | Zen 5 | Granite Rapids |

| Codename | Turin | Granite Rapids |

| Generation | EPYC (Zen 5c (Turin)) | Xeon 6 (Granite Rapids-AP) |

| Process Node | 3 nm (TSMC) | 5 nm (Intel) |

| Base Clock | 2.40 GHz | 2.00 GHz |

| Boost Clock | 3.70 GHz | 3.90 GHz |

| TDP | 400 W | 500 W |

| Socket | AMD Socket SP5 | Intel Socket 7529 |

| L1 Cache | 80 KB (per core) | 112 KB (per core) |

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

| L3 Cache | 256 MB (shared) | 504 MB (shared) |

| Memory Bandwidth | 576.0 GB/s | 614.4 GB/s |

| PCIe | Gen 5, 128 lanes (CPU only) | Gen 5, 96 lanes (CPU only) |

| Die Size | Not recorded | 3x 598 mm² |

| Release Date | 2024-10-09 | 2024-09-23 |

Where Each One Wins

The AMD EPYC 9745 wins in every category where benchmark data exists. Its strongest relative advantages are in physics (411.1% ahead), random string sorting (94.8% ahead), and integer math (92.1% ahead). These results suggest workloads that rely on heavy integer computation, sorting algorithms, and physics simulation will see particularly large gains from the EPYC 9745. Data encryption also favors the AMD part strongly at 83.2%, and multithreaded workloads in general are about 75.8% faster. Single-thread performance, while the smallest category of victory in relative terms at 66.9%, still represents a decisive lead.

The Intel Xeon 6980P does not have a single recorded benchmark win. Its advantages are limited to specification-level features: a higher boost clock (3.90 GHz versus 3.70 GHz), a larger L3 cache (504 MB versus 256 MB), higher memory bandwidth (614.4 GB/s versus 576.0 GB/s), and more L1 and L2 cache per core. It also has a higher TDP of 500 watts and a 5 nm process node, compared to the EPYC 9745's 400 watt TDP and 3 nm node. In terms of raw platform connectivity, the AMD part offers more PCIe lanes (128 versus 96). For buyers, the data indicates that the EPYC 9745 is the superior choice for compute-intensive server and workstation tasks, while the Xeon 6980P's specification advantages do not translate into measurable performance wins in the database.