AMD Ryzen AI Embedded P185 vs Intel Core i9-13900 Comparison

The AMD Ryzen AI Embedded P185 and the Intel Core i9-13900 land in nearly the same neighborhood on the database's aggregate scale, yet the head-to-head measurements tell a starkly one-sided story. The i9-13900, a 13th Gen Raptor Lake desktop part, wins every shared benchmark in the recorded data, often by wide margins. The P185 counters with a fundamentally different design brief: it is a 28-watt mobile embedded processor built on a 4 nm TSMC process, pairing Zen 5 and Zen 5c cores with a comparatively strong integrated GPU and modern LPDDR5X memory support. Understanding which one wins, and where, requires separating raw throughput from the efficiency and feature set that define each chip's intended role.

Where Each One Wins

On pure performance, the data shows a clean sweep for the i9-13900. It wins all eleven shared PassMark tests, and the gaps are rarely close. In multi-thread throughput it scores 45,680 against 31,817 for the P185, roughly 30 percent ahead. Single-thread results are the narrowest contest: 4,309 versus 3,977, a gap of just under 8 percent. Everything in between is decisive. Floating point math favors the Intel chip by about 41 percent, data encryption by about 44 percent, and data compression by about 35 percent. If the question is simply "which processor finishes a heavy compute job first," the i9-13900 answers it in every recorded test.

The P185's wins are structural rather than scoreboard-based. It operates at a 28-watt TDP versus 65 watts for the i9-13900, and it does so as a mobile embedded part rather than a desktop socket processor. That power envelope is the P185's entire argument: it delivers 93rd-percentile aggregate performance among all CPUs in the database, sitting just above the i9-13900's 92nd percentile, while drawing less than half the rated power. Its Radeon 890M integrated graphics are also a generational step beyond the UHD Graphics 770 in the Intel part, which matters for systems without a discrete GPU. And its memory subsystem is more modern on paper, supporting DDR5 and LPDDR5X with a recorded bandwidth of 89.6 GB/s, while the i9-13900 supports DDR4 and DDR5 with no bandwidth figure recorded in the database.

So the split is straightforward. Sustained desktop-class compute, rendering, encryption-heavy workloads, and physics simulation belong to the i9-13900. Thermally constrained embedded deployments, compact fanless or lightly cooled systems, and platforms that need capable integrated graphics and low-power LPDDR5X are where the P185's design pays off despite trailing in every benchmark.

Architecture Differences

These two processors come from opposite ends of the design spectrum. The P185 is AMD's Gorgon Point design, built on TSMC's 4 nm node, with 12 cores and 24 threads drawn from a mix of Zen 5 and Zen 5c cores. The "c" variant cores are area- and power-optimized siblings of the full Zen 5 design, and the combination lets AMD fit a heterogeneous 12-core layout into a 233 mm² die intended for mobile embedded platforms. Its base clock is 2.00 GHz with a boost of 5.10 GHz, and its cache hierarchy consists of 80 KB of L1 per core, 1 MB of L2 per core, and 16 MB of L3.

The i9-13900 is Intel's Raptor Lake-S architecture on the company's own 10 nm process, with a 257 mm² die. It deploys 24 cores and 32 threads, doubling the P185's core count and adding eight extra threads, which directly explains its dominance in every multi-threaded test. Its clocks run from a 2.00 GHz base up to 5.60 GHz boost, edging the P185 at the top end. Cache is another significant differentiator: the same 80 KB of L1 per core, but 2 MB of L2 per core, double the AMD figure, and 36 MB of shared L3, more than twice the P185's 16 MB. That cache advantage shows up in the integer and sorting benchmarks, where the Intel chip leads by roughly 33 and 37 percent respectively.

Platform connectivity also diverges. The i9-13900 offers PCIe Gen 5 with 16 CPU lanes on Intel Socket 1700, while the P185 provides PCIe Gen 4 with 16 CPU lanes on AMD Socket FP8. Both support ECC memory and both dual-channel memory buses. Neither part has an unlocked multiplier. The i9-13900 entered production as a desktop processor released in early January 2023 with a launch MSRP of $549, whereas the P185 is a mobile embedded part with a recorded release date in early 2026 and no launch MSRP listed in the database.

FAQ

Q: Which CPU is faster overall?

A: The Intel Core i9-13900 wins every shared benchmark in the database. Its average benchmark score of 60,676 sits close to the P185's 62,839 on the aggregate index, but in direct measurement the Intel chip leads by margins ranging from about 8 percent in single-thread to about 44 percent in data encryption.

Q: How close is single-thread performance?

A: Quite close. The i9-13900 scores 4,309 in PassMark single-thread against 3,977 for the P185, a gap of under 8 percent. Single-thread is the P185's most competitive test in the recorded data.

Q: Which one is more power efficient?

A: The P185 is rated at a 28-watt TDP versus 65 watts for the i9-13900, and it still reaches the 93rd percentile of aggregate CPU performance in the database, one point ahead of the i9-13900's 92nd percentile. On a performance-per-watt basis the embedded AMD part is clearly the stronger design.

Q: How do their rivals compare?

A: The P185's aggregate score sits within half a percent of chips like the Intel Core Ultra 7 255HX and AMD Ryzen AI 9 PRO 465, while the i9-13900 is grouped near the Intel Xeon Gold 6338T, AMD Ryzen 9 7945HX, and Intel Core i9-14900F. Both parts occupy the same broad performance tier even though the head-to-head results favor Intel heavily.

Q: Which has better integrated graphics?

A: The P185's Radeon 890M is a substantially more capable integrated GPU than the i9-13900's UHD Graphics 770. The database records no benchmark runs for either iGPU, but the Radeon 890M is a modern AMD graphics design suited to real rendering work, while UHD Graphics 770 is a basic display adapter.

Q: Do both support ECC memory?

A: Yes. Both processors list ECC memory support, making each viable for stability-critical embedded and workstation deployments.

Specification Differences

The table below covers every field where the two processors diverge in the recorded data.

| Field | AMD Ryzen AI Embedded P185 | Intel Core i9-13900 |

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

| Cores | 12 | 24 |

| Threads | 24 | 32 |

| Boost clock | 5.10 GHz | 5.60 GHz |

| TDP | 28 W | 65 W |

| Socket | AMD Socket FP8 | Intel Socket 1700 |

| Architecture | Gorgon Point (Zen 5 / Zen 5c) | Raptor Lake-S |

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

| Die size | 233 mm² | 257 mm² |

| L2 cache | 1 MB per core | 2 MB per core |

| L3 cache | 16 MB | 36 MB (shared) |

| Memory support | DDR5, LPDDR5X | DDR4, DDR5 |

| Memory bandwidth | 89.6 GB/s | not recorded |

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

| Integrated graphics | Radeon 890M | UHD Graphics 770 |

| Market segment | Mobile | Desktop |

| Release date | 2026 | 2023 |

| Launch MSRP | not listed | $549 |

Both share an 80 KB per-core L1, dual-channel memory buses, ECC support, locked multipliers, and active production status.

Head-to-Head Benchmarks

The shared test suite consists of eleven PassMark workloads, and the i9-13900 takes all of them. The widest gap is data encryption: 35,242 for Intel against 19,612 for AMD, a 44 percent deficit for the P185. Floating point math is nearly as lopsided, 120,492 versus 70,587, about 41 percent in Intel's favor. Data compression lands at 577,285 versus 374,429, a 35 percent gap, and random string sorting reads 64,396 against 40,557, roughly 37 percent apart.

Mid-tier results follow the same pattern. Integer math goes to Intel 176,107 to 117,832, about 33 percent ahead. Prime number finding is 186 versus 129, a 31 percent gap. The flagship multi-thread score is 45,680 for the i9-13900 against 31,817 for the P185, close to 30 percent, a direct consequence of the Intel chip's 24 cores and 32 threads compared with 12 cores and 24 threads. Physics runs 2,484 to 1,772, about 29 percent apart. Extended instructions favor Intel 32,760 to 26,544, a 19 percent difference.

The narrowest result is single-thread: 4,309 versus 3,977, under 8 percent. That figure is the most revealing one in the dataset, because it shows the P185's per-core throughput is genuinely competitive. Its losses are scale losses, not architecture losses. Feed the same Zen 5 and Zen 5c core design a higher power budget and the deficit in multi-thread workloads narrows accordingly.

Context from each part's rival grouping reinforces the picture. The i9-13900's aggregate score of 60,676 places it within about one percent of the AMD Ryzen 9 7945HX and Intel Core i9-14900F, and marginally ahead of the Intel Xeon Gold 6338T. The P185's 62,839 puts it fractionally above the Intel Core Ultra 7 255HX and just below the Core i7-13790F and Core Ultra 7 265HX. In database terms these are peer-tier processors on the aggregate index. In direct measurement, the i9-13900 is the faster chip in every test, while the P185 delivers its numbers from less than half the power envelope, with faster memory bandwidth on record, stronger integrated graphics, and a newer 4 nm process behind it. Which one "wins" therefore depends entirely on whether the design target is maximum throughput or maximum efficiency within a constrained platform.