AMD Ryzen 9 9900X vs AMD Ryzen AI 5 PRO 435 Comparison

Head-to-Head Benchmarks

The benchmark data shows a decisive sweep. Across all 11 shared test categories, the AMD Ryzen 9 9900X holds the top score, with the AMD Ryzen AI 5 PRO 435 trailing in every instance. The margins are substantial, especially in multi-threaded workloads.

In passmark_multithread, the 9900X scores 54643 against the Ryzen AI 5 PRO 435's 19091, a 186.2% difference. That is nearly three times the throughput. The single-thread gap is far smaller, 4672 versus 3757, a 24.4% lead for the 9900X, but it still favors the desktop chip.

The largest single margin appears in passmark_find_prime_numbers, where the 9900X delivers 436 versus 57, a 664.9% advantage. This test is heavily dependent on integer processing and core count, so the result reflects both the 12-core configuration and the higher clocks of the 9900X.

Other notable wins include passmark_extended_instructions (55243 vs 16724, up 230.3%), passmark_physics (3381 vs 995, up 239.8%), and passmark_integer_math (181056 vs 60879, up 197.4%). The 9900X also leads passmark_data_encryption by 196.6% (33421 vs 11267), passmark_data_compression by 193.6% (683579 vs 232803), and passmark_floating_point_math by 192.1% (120083 vs 41114). Random string sorting shows a 188.8% gap (72013 vs 24936).

The average benchmark score for the 9900X is 57498, placing it in the 92nd percentile of all CPUs in the database. The Ryzen AI 5 PRO 435 averages 37762, which sits in the 86th percentile. The 9900X is closer in average score to workstation and server parts: the AMD EPYC 9015 (57555, -0.1%), the AMD EPYC 7313 (57399, +0.2%), the Intel Core i9-14900 (58115, -1.1%), and the Intel Xeon Platinum 8260M (58323, -1.4%). The Ryzen AI 5 PRO 435 sits alongside the AMD Ryzen AI Embedded P132 (37804, -0.1%), the Intel Core 5 211E (37829, -0.2%), the Intel Core i5-13600K (37685, +0.2%), and the AMD Ryzen AI 9 HX 370 (37904, -0.4%).

Architecture Differences

Both processors use the Zen 5 architecture on TSMC's 4 nm process, but they target different platforms and power envelopes. The Ryzen 9 9900X, codenamed Granite Ridge, is a desktop part on AMD Socket AM5 with 12 cores and 24 threads. The Ryzen AI 5 PRO 435, codenamed Gorgon Point, is a mobile part on AMD Socket FP8 with 6 cores and 12 threads.

The 9900X runs at a base clock of 4.40 GHz and boosts to 5.60 GHz, with a TDP of 120 W. The Ryzen AI 5 PRO 435 starts at 2.00 GHz and boosts to 4.50 GHz, with a TDP of 28 W. That clock and power gap explains much of the performance difference, particularly in single-thread tests where the 9900X leads by 24.4%.

Cache allocation differs sharply. Both have 80 KB of L1 and 1 MB of L2 per core, but the 9900X carries 64 MB of L3 cache while the Ryzen AI 5 PRO 435 carries only 4 MB. That 16x difference in L3 capacity matters for workloads that repeatedly scan large datasets.

Memory support is another split. Both support DDR5 and dual-channel memory with 89.6 GB/s of bandwidth, and both accept ECC memory. The Ryzen AI 5 PRO 435 additionally supports LPDDR5X, which is typical for mobile parts. PCIe connectivity differs as well: the 9900X offers Gen 5 with 24 CPU lanes, while the Ryzen AI 5 PRO 435 offers Gen 4 with 14 CPU lanes.

The integrated graphics are different. The 9900X uses Radeon Graphics, while the Ryzen AI 5 PRO 435 uses the Radeon 840M. The 9900X has an unlocked multiplier; the mobile chip does not. The 9900X carries a 16,630 million transistor count on a 2x 70.6 mm² die, while the database does not list transistor or die size data for the Ryzen AI 5 PRO 435.

Release timing also differs. The 9900X was released on 2024-08-14, while the Ryzen AI 5 PRO 435 has a release date of 2026-01-04.

Where Each One Wins

The Ryzen 9 9900X wins every benchmark category in the shared set. That makes a use-case split straightforward: the desktop chip is the choice for compute-heavy tasks that can use its 12 cores, 24 threads, and 64 MB of L3 cache. The passmark_multithread score of 54643 and the cinebench_r23_multicore score of 32172 confirm strong parallel performance. The 3dmark_max_threads score of 13929 and the 3dmark_16_threads score of 12552 show that the chip holds up under sustained multi-thread load.

The Ryzen AI 5 PRO 435, despite losing every head-to-head, is not without merit. Its 28 W TDP and mobile socket (FP8) place it in a different class. It supports LPDDR5X memory and uses Gen 4 PCIe with 14 lanes, both suited to thin-and-light laptops. Its single-thread score of 3757 is not far behind the 9900X's 4672, which means everyday responsiveness should be acceptable. The passmark_single_thread result of 3757 and the passmark_singlethread result of 3757 are identical, confirming consistency in the database.

For tasks that rely on extended instruction sets, the 9900X is far ahead. The passmark_extended_instructions score of 55243 versus 16724 is a 230.3% gap. For encryption and compression, the 9900X also dominates: 33421 vs 11267 in data encryption and 683579 vs 232803 in data compression. Physics simulation shows a 239.8% lead (3381 vs 995), which points to strong floating-point and multi-core scaling.

The Ryzen AI 5 PRO 435 does produce competitive numbers for its power class. Its average benchmark score of 37762 is comparable to the Intel Core i5-13600K (37685, +0.2%), a desktop part with a much higher power draw. That suggests the mobile chip achieves respectable performance per watt, although the database does not include power efficiency metrics beyond the stated TDP.

The Verdict

The data points to the Ryzen 9 9900X as the superior processor for raw performance. It wins all 11 head-to-head benchmarks, holds the 92nd percentile ranking, and averages 57498 across the database. Its nearest rivals are server and high-end desktop parts like the AMD EPYC 9015 and Intel Core i9-14900, which puts it in a performance tier well above the Ryzen AI 5 PRO 435.

The Ryzen AI 5 PRO 435 is a different product for a different socket. It is a 28 W mobile chip with 6 cores and 12 threads, and it sits in the 86th percentile. Its average score of 37762 is close to the Intel Core i5-13600K and the AMD Ryzen AI 9 HX 370, both of which are more powerful desktop or high-end mobile parts. That placement suggests the Ryzen AI 5 PRO 435 delivers solid performance for its power envelope.

For a desktop builder who prioritizes multi-core work, the 9900X is the clear pick. For a laptop buyer who needs a 28 W chip with LPDDR5X support and ECC, the Ryzen AI 5 PRO 435 is the only one of the two that fits that socket. The 9900X cannot be installed in an FP8 laptop, and the Ryzen AI 5 PRO 435 cannot be installed in an AM5 desktop. The choice is less about which is faster and more about which platform matches the intended use.

FAQ

Q: Which CPU has more cores and threads?

A: The AMD Ryzen 9 9900X has 12 cores and 24 threads. The AMD Ryzen AI 5 PRO 435 has 6 cores and 12 threads.

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

A: In passmark_single_thread, the 9900X scores 4672 and the Ryzen AI 5 PRO 435 scores 3757. The 9900X leads by 24.4%.

Q: Which processor has more L3 cache?

A: The Ryzen 9 9900X has 64 MB of L3 cache. The Ryzen AI 5 PRO 435 has 4 MB of L3 cache.

Q: Do both CPUs support ECC memory?

A: Yes, both the Ryzen 9 9900X and the Ryzen AI 5 PRO 435 support ECC memory.

Q: What sockets do these processors use?

A: The Ryzen 9 9900X uses AMD Socket AM5. The Ryzen AI 5 PRO 435 uses AMD Socket FP8.

Q: Which CPU wins the head-to-head benchmarks?

A: The Ryzen 9 9900X wins all 11 shared benchmark tests. The Ryzen AI 5 PRO 435 wins none.

Specification Differences

| Specification | AMD Ryzen 9 9900X | AMD Ryzen AI 5 PRO 435 |

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

| Cores | 12 | 6 |

| Threads | 24 | 12 |

| Base clock | 4.40 GHz | 2.00 GHz |

| Boost clock | 5.60 GHz | 4.50 GHz |

| TDP | 120 W | 28 W |

| Socket | AMD Socket AM5 | AMD Socket FP8 |

| Codename | Granite Ridge | Gorgon Point |

| L3 cache | 64 MB | 4 MB |

| Memory support | DDR5 | DDR5, LPDDR5X |

| PCIe | Gen 5, 24 Lanes (CPU only) | Gen 4, 14 Lanes (CPU only) |

| Integrated graphics | Radeon Graphics | Radeon 840M |

| Market segment | Desktop | Mobile |

| Release date | 2024-08-14 | 2026-01-04 |

| Launch MSRP | $499 | Not listed |

| Multiplier unlocked | Yes | No |

| Transistors | 16,630 million | Not listed |

| Die size | 2x 70.6 mm² | Not listed |

| Part number | 100-000000662 | 100-000001788 |