AMD Ryzen 9 9900X vs Intel Core Ultra 9 386H Comparison

The Verdict

The benchmark data delivers a clear and unambiguous result: the AMD Ryzen 9 9900X wins every single head-to-head comparison against the Intel Core Ultra 9 386H. Across 15 recorded tests, the AMD part takes 15 wins, with no victories for Intel. The Ryzen 9 9900X posts an average benchmark score of 57498, placing it in the 92nd percentile of all CPUs, while the Core Ultra 9 386H averages 43210, sitting in the 88th percentile. The gap in overall average score is roughly 33%, which aligns with the scale of the individual test deltas.

The Ryzen 9 9900X is the obvious choice for anyone building a desktop system where raw compute throughput is the priority. Its nearest rivals in the database include the Intel Core i9-14900, which sits 1.1% higher in average score, and the AMD EPYC 9015, which is essentially tied at 0.1% lower. The Core Ultra 9 386H, by contrast, sits alongside the AMD Ryzen AI Max PRO 385 at 0.3% lower and the Intel Core i9-12900 at 0.7% higher. The Intel mobile part is competitive within its own class, but it is not in the same performance tier as the AMD desktop flagship.

The Intel Core Ultra 9 386H is a mobile processor with a 25 W TDP, designed for laptops and compact systems. Its data shows a capable part, but one that sacrifices performance for mobility. The Ryzen 9 9900X, with a 120 W TDP, is a desktop part that uses its power budget to deliver far higher multi-threaded and single-threaded scores. The verdict based strictly on the recorded measurements: the AMD Ryzen 9 9900X is the superior processor for performance-sensitive desktop workloads, while the Intel Core Ultra 9 386H serves the mobile segment where the 25 W envelope matters more than peak compute.

Where Each One Wins

The Ryzen 9 9900X wins in every measured category, but the margin varies widely by workload. The largest deltas appear in integer math, data compression, and extended instructions. In PassMark integer math, the AMD part scores 181056 against 87284 for Intel, a 107.4% advantage. Data compression shows a 94% delta, with the Ryzen scoring 683579 versus 352365. Extended instructions deliver an 89.6% delta, 55243 versus 29138. These are workloads that scale with core count, threads, and cache, all areas where the Ryzen 9 9900X holds a structural advantage.

The smaller wins for AMD are in floating point math, physics, and single-threaded tests. PassMark floating point math shows 120083 versus 108527, a 10.6% delta. Physics scores 3381 versus 3028, an 11.7% delta. Single-thread performance in PassMark is 4672 versus 4218, a 10.8% delta. Cinebench R23 single-core shows a more modest 8.8% delta, 2253 versus 2071.5. These closer margins indicate that the Intel Core Ultra 9 386H is not far behind in lightly threaded or latency-sensitive tasks, but it still loses every contest.

The Intel part finds its relative strengths in the tests where the delta is smallest. Cinebench R23 single-core at 8.8% and PassMark single-thread at 10.8% represent its best showings. It also stays within 10.6% in floating point math. For a 25 W mobile chip, staying within roughly 9% to 11% of a 120 W desktop part in single-threaded work is notable. The architecture is efficient, but the power ceiling limits its multi-threaded output. The Ryzen 9 9900X wins everywhere, but the Intel part is closest in single-core and floating point, not in integer or compression workloads.

Architecture Differences

The two processors come from different design philosophies and target different physical envelopes. The AMD Ryzen 9 9900X uses the Zen 5 architecture on the Granite Ridge codename, built on a 4 nm process from TSMC. It is a desktop part in the 9000 series, using the AMD Socket AM5. The chip integrates 12 cores and 24 threads, with a base clock of 4.40 GHz and a boost clock of 5.60 GHz. The TDP is 120 W, and the multiplier is unlocked, allowing overclocking. The transistor count is 16,630 million across a dual-chiplet design with a die size of 2x 70.6 mm².

The Intel Core Ultra 9 386H uses the Panther Lake architecture, built on Intel's 3 nm process. It is a mobile part in the Core Ultra Series 3, using the Intel BGA 2540 socket. The chip has 16 cores and 16 threads, with a base clock of 2.10 GHz and a boost clock of 4.90 GHz. The TDP is 25 W, and the multiplier is locked. Intel does not list a transistor count or die size in the data. The market segment is mobile, and the production status is active, with a release date in early 2026.

Cache configurations differ substantially. The Ryzen 9 9900X provides 80 KB of L1 per core, 1 MB of L2 per core, and a 64 MB L3 cache. The Intel part provides 192 KB of L1 per core, 2.5 MB of L2 per core, and an 18 MB shared L3 cache. The AMD chip has far more total L3, 64 MB versus 18 MB, which helps in cache-sensitive workloads like data compression and integer math. The Intel chip has larger per-core L1 and L2, but the smaller shared L3 limits its ability to keep large working sets on-die.

Memory support also differs. Both use dual-channel memory, but the AMD part supports DDR5 and has a recorded memory bandwidth of 89.6 GB/s. The Intel part supports DDR5 and LPDDR5X, with a higher recorded memory bandwidth of 115.2 GB/s. The Intel chip also has ECC memory disabled, while the AMD chip supports ECC. PCIe lanes differ as well: the Ryzen 9 9900X offers 24 CPU-only Gen 5 lanes, while the Core Ultra 9 386H offers 12 CPU-only Gen 5 lanes. Integrated graphics are present on both: Radeon Graphics on the AMD side and Intel Xe3 Graphics on the Intel side.

The process node advantage goes to Intel at 3 nm versus TSMC's 4 nm, but the AMD part compensates with a much higher power budget and more L3 cache. The Intel part uses more cores (16 versus 12) but only 16 threads, meaning no simultaneous multithreading, while the AMD part provides 24 threads from 12 cores. That threading difference, combined with the higher boost clock on AMD, explains much of the multi-threaded performance gap.

FAQ

Q: Which processor has the higher multi-threaded performance?

A: The AMD Ryzen 9 9900X wins every multi-threaded benchmark in the comparison. In Cinebench R23 multi-core, it scores 32172 versus 20547 for the Intel Core Ultra 9 386H, a 56.6% delta. PassMark multi-thread shows 54643 versus 35399, a 54.4% delta.

Q: How do the two compare in single-threaded performance?

A: The AMD Ryzen 9 9900X leads in single-threaded tests as well, but by smaller margins. Cinebench R23 single-core shows 2253 versus 2071.5, an 8.8% delta. PassMark single-thread shows 4672 versus 4218, a 10.8% delta.

Q: What are the core and thread counts?

A: The AMD Ryzen 9 9900X has 12 cores and 24 threads. The Intel Core Ultra 9 386H has 16 cores and 16 threads, meaning the Intel part does not support simultaneous multithreading.

Q: What is the TDP difference?

A: The AMD Ryzen 9 9900X has a TDP of 120 W, while the Intel Core Ultra 9 386H has a TDP of 25 W. The Intel part is designed for mobile systems with a much lower power envelope.

Q: Which processor has more cache?

A: The AMD Ryzen 9 9900X has 64 MB of L3 cache, while the Intel Core Ultra 9 386H has 18 MB of shared L3. The AMD part also has 1 MB of L2 per core, while the Intel part has 2.5 MB of L2 per core.

Q: How does memory bandwidth compare?

A: The Intel Core Ultra 9 386H has a higher recorded memory bandwidth at 115.2 GB/s, compared to 89.6 GB/s for the AMD Ryzen 9 9900X. Both use dual-channel memory, but the Intel part also supports LPDDR5X in addition to DDR5.

Q: Which processor holds a higher percentile ranking?

A: The AMD Ryzen 9 9900X ranks in the 92nd percentile of all CPUs, while the Intel Core Ultra 9 386H ranks in the 88th percentile.

Head-to-Head Benchmarks

The head-to-head data covers 15 tests, and the AMD Ryzen 9 9900X wins all 15. The most decisive victories come in PassMark integer math and data compression. Integer math shows the largest delta at 107.4%, with the AMD part scoring 181056 against 87284 for Intel. This is a workload that heavily rewards the combination of 24 threads, a 5.60 GHz boost clock, and 64 MB of L3 cache. The Intel part, with 16 threads and a 4.90 GHz boost clock, cannot keep pace.

Data compression follows closely at a 94% delta. The AMD Ryzen 9 9900X scores 683579, while the Intel Core Ultra 9 386H scores 352365. Compression algorithms depend on cache capacity and memory latency, and the AMD part's 64 MB L3 versus 18 MB on Intel is a decisive factor. Extended instructions show an 89.6% delta, 55243 versus 29138, another cache and throughput-sensitive workload.

Cinebench R23 multi-core shows a 56.6% delta, with the AMD part scoring 32172 versus 20547. Cinebench R15 multi-core shows a 55.4% delta, 5008 versus 3223. PassMark multi-thread shows a 54.4% delta, 54643 versus 35399. Random string sorting delivers a 70.9% delta, 72013 versus 42135. These multi-threaded workloads all favor the AMD part's higher thread count and power budget.

The smaller margins appear in single-threaded and floating point tests. Cinebench R23 single-core shows an 8.8% delta, 2253 versus 2071.5. Cinebench R15 single-core shows a 16.3% delta, 353 versus 303.5. PassMark single-thread shows a 10.8% delta, 4672 versus 4218. PassMark floating point math shows a 10.6% delta, 120083 versus 108527. PassMark physics shows an 11.7% delta, 3381 versus 3028.

The middle tier of results includes data encryption at a 23.1% delta, 33421 versus 27150, and find prime numbers at a 27.9% delta, 436 versus 341. These tests show solid AMD wins but not the near-doubling seen in integer math or compression. The overall pattern is consistent: the AMD Ryzen 9 9900X dominates in throughput-oriented tasks, while the Intel Core Ultra 9 386H stays competitive in latency-bound single-threaded work but still loses every recorded comparison. The average benchmark scores confirm the hierarchy, with the AMD part at 57498 and the Intel part at 43210, a gap that places them in different performance classes despite the Intel part's smaller deficit in the 88th percentile.