AMD EPYC 4345P vs Intel Core i9-13980HX Comparison

The Intel Core i9-13980HX and AMD EPYC 4345P represent two fundamentally different interpretations of high-performance computing. The Intel part is a mobile powerhouse with 24 cores and 32 threads, designed to deliver maximum throughput in a laptop chassis. The AMD EPYC, despite its server-class branding, is an 8-core, 16-thread Zen 5 processor on the desktop AM5 socket. The benchmark data reveals a clear split: the Intel chip dominates in raw multi-threaded workloads, while the AMD chip counters with superior single-core and lightly-threaded efficiency. The database records 11 benchmark wins for Intel and 6 for AMD, but the nature of those wins tells the more interesting story.

Where Each One Wins

The Intel Core i9-13980HX wins primarily through sheer core-count advantage. Its 24 cores and 32 threads allow it to run away with heavily parallel tasks. In Cinebench R15 multicore, the Intel chip scores 4717 against the AMD's 3227, a 46.2% lead. The margin persists in Cinebench R20 multicore, where Intel posts 16187 versus 13448, a 20.4% advantage. PassMark tests further cement this pattern: floating point math shows Intel at 118645 versus 74255, a 59.8% gap, and integer math sees Intel at 166455 versus 123774, a 34.5% lead. Data compression also favors Intel, 588306 against 421490, a 39.6% difference. The Intel chip even wins in extended instructions (33868 vs 31663, a 7% edge) and prime number finding (191 vs 167, a 14.4% lead).

The AMD EPYC 4345P wins in single-threaded and lightly-threaded scenarios. The most dramatic example is Cinebench R23 single-core, where AMD scores 4520 versus Intel's 2110, a 53.3% advantage. Cinebench R15 single-core also goes to AMD, 455 against 304.5, a 33.1% margin. PassMark single-thread scores show AMD at 4408 versus Intel's 4252, a 3.5% lead. Interestingly, Cinebench R23 multicore goes to AMD as well, 32020 versus 30273, a 5.5% edge, suggesting that Zen 5's per-core efficiency can overcome a 16-thread deficit in some workloads. Physics scores are essentially tied, with AMD at 2583 and Intel at 2575, a negligible 0.3% difference that favors AMD.

The Verdict

The data points to a clear use-case split. For users running heavily multithreaded applications, such as video rendering, 3D simulation, or data processing, the Intel Core i9-13980HX is the stronger choice. Its 59.8% lead in floating point math and 46.2% lead in Cinebench R15 multicore indicate that workloads which scale with core count will see substantial benefits. The Intel part also leads in data encryption by 51.6% (35332 vs 23313) and random string sorting by 43% (66125 vs 46238), making it suitable for security and database tasks.

For users prioritizing single-thread responsiveness, the AMD EPYC 4345P is the better pick. Its 53.3% advantage in Cinebench R23 single-core is massive, and even the smaller 3.5% lead in PassMark single-thread suggests better general application responsiveness. The AMD chip also wins Cinebench R23 multicore outright, which is notable given its 8-core configuration. This suggests Zen 5's architecture delivers more performance per core, and for software that is not perfectly parallelized, the AMD part could feel faster in daily use. The AMD chip's launch MSRP is $329, while the Intel part carries a launch MSRP of $668, but the database shows performance differences that are workload-dependent rather than universally one-sided.

Head-to-Head Benchmarks

The largest single win for Intel is in PassMark floating point math, where the 118645 score beats AMD's 74255 by 59.8%. This is the kind of margin that indicates a fundamental throughput advantage, likely from the extra cores and threads. Data encryption shows Intel at 35332 versus 23313, a 51.6% lead, which is critical for secure workloads. Random string sorting favors Intel by 43%, and data compression by 39.6%. Multi-thread benchmarks consistently favor Intel: PassMark multithread shows 46409 versus 36123, a 28.5% lead, and Cinebench R15 multicore shows the 46.2% gap.

The AMD side has its own decisive victories. Cinebench R23 single-core is the standout, with AMD at 4520 against Intel's 2110, a 53.3% margin. This is a massive single-thread advantage, suggesting that Zen 5's core design is significantly more efficient per clock. Cinebench R15 single-core shows AMD at 455 versus 304.5, a 33.1% lead. The Cinebench R23 multicore result is also telling: AMD wins 32020 versus 30273, a 5.5% margin, despite having only 16 threads against Intel's 32. This indicates that the AMD chip's per-thread performance is so strong that it can overcome the thread deficit in some workloads. PassMark single-thread results show AMD at 4408 versus 4252, a 3.5% lead.

FAQ

Q: Which processor has more cores and threads?

A: The Intel Core i9-13980HX has 24 cores and 32 threads, while the AMD EPYC 4345P has 8 cores and 16 threads.

Q: Which chip wins in Cinebench R23 multicore?

A: The AMD EPYC 4345P wins with a score of 32020 against Intel's 30273, a 5.5% advantage, despite having fewer cores.

Q: How large is the single-core performance gap?

A: In Cinebench R23 single-core, the AMD EPYC 4345P scores 4520 versus Intel's 2110, a 53.3% lead. In PassMark single-thread, the gap is smaller, 4408 versus 4252, a 3.5% advantage for AMD.

Q: What is the biggest benchmark win for Intel?

A: The largest Intel win is in PassMark floating point math, where it scores 118645 against AMD's 74255, a 59.8% margin.

Q: Do both processors support ECC memory?

A: Yes, both the Intel Core i9-13980HX and the AMD EPYC 4345P support ECC memory.

Q: Which processor has a higher boost clock?

A: The Intel Core i9-13980HX has a boost clock of 5.60 GHz, while the AMD EPYC 4345P boosts to 5.50 GHz.

Architecture Differences

The two processors come from different architectural generations and design philosophies. The Intel Core i9-13980HX uses the Raptor Lake architecture, built on a 10 nm process node at Intel's foundry. Its die size is 257 mm². The AMD EPYC 4345P uses the Zen 5 architecture, codenamed Grado, built on a 4 nm process node at TSMC. The AMD chip has 8,315 million transistors on a 70.6 mm² die, a much denser design. The Intel chip has a larger L2 cache at 2 MB per core, while AMD has 1 MB per core. For L3 cache, Intel has 36 MB shared, while AMD has 32 MB shared. Both have 80 KB of L1 cache per core.

The memory support differs significantly. Intel supports both DDR4 and DDR5, while AMD supports only DDR5. Both are dual-channel, but AMD has a recorded memory bandwidth of 89.6 GB/s. The PCIe configurations also differ: Intel offers Gen 5 with 20 lanes (CPU only), while AMD offers Gen 5 with 24 lanes (CPU only). The Intel chip has integrated UHD Graphics 770, while AMD has Radeon Graphics. The Intel chip is on the Intel BGA 1964 socket and targets the mobile segment, while AMD uses the AMD Socket AM5 and targets server/workstation. The Intel chip has an unlocked multiplier, while the AMD chip does not. The Intel part was released in 2023, while the AMD part was released in 2025.

Specification Differences

The most obvious specification difference is core count: Intel has 24 cores and 32 threads, AMD has 8 cores and 16 threads. The base clocks differ, with Intel at 2.20 GHz and AMD at 3.80 GHz. Boost clocks are closer, with Intel at 5.60 GHz and AMD at 5.50 GHz. The TDP ratings are 55 W for Intel and 65 W for AMD. The process nodes differ significantly: Intel is on 10 nm, AMD on 4 nm. The foundries are different, Intel using its own fabs and AMD using TSMC. The die sizes are vastly different, with Intel at 257 mm² and AMD at 70.6 mm². The L2 cache differs, Intel at 2 MB per core, AMD at 1 MB per core. L3 cache is 36 MB for Intel and 32 MB for AMD. Memory support differs, with Intel supporting DDR4 and DDR5, while AMD supports only DDR5. The PCIe lanes differ, Intel at 20 lanes, AMD at 24 lanes. The sockets are different, as are the market segments, release dates, and part numbers. The Intel chip has an unlocked multiplier, while AMD's is locked.