AMD Ryzen AI 9 HX 370 vs Intel Core Ultra 9 288V Comparison

FAQ

Q: Which processor has more cores and threads?

A: The AMD Ryzen AI 9 HX 370 has 12 cores and 24 threads, while the Intel Core Ultra 9 288V has 8 cores and 8 threads.

Q: What is the difference in their average benchmark scores?

A: The AMD Ryzen AI 9 HX 370 records an average benchmark score of 37904, placing it in the 86th percentile. The Intel Core Ultra 9 288V records 23219, placing it in the 76th percentile.

Q: Which CPU wins the most head-to-head benchmark comparisons?

A: The AMD Ryzen AI 9 HX 370 wins 12 of the 15 recorded head-to-head tests. The Intel Core Ultra 9 288V wins 3.

Q: How do their single-thread performance scores compare?

A: The Intel Core Ultra 9 288V wins in PassMark single-thread with a score of 4274 versus 3973 for the AMD, a 7% margin. However, the AMD wins in Cinebench R23 single-core with 2018 versus 1950, a 3.5% margin.

Q: What are the process nodes for these two mobile chips?

A: The AMD Ryzen AI 9 HX 370 uses a 4 nm process from TSMC. The Intel Core Ultra 9 288V uses a 3 nm process from TSMC.

Q: Which processor has higher memory bandwidth?

A: The Intel Core Ultra 9 288V supports LPDDR5X memory with 136.5 GB/s bandwidth. The AMD Ryzen AI 9 HX 370 supports DDR5 and LPDDR5X with 89.6 GB/s bandwidth.

Architecture Differences

The AMD Ryzen AI 9 HX 370 uses the Zen 5 architecture under the Strix Point codename, belonging to the Ryzen AI 300 generation. This generation combines Zen 5 and Zen 5c cores. The Intel Core Ultra 9 288V uses the Lunar Lake architecture, belonging to the Core Ultra Series 2 generation. The Intel part pairs its 8 cores with 8 threads, meaning no hyperthreading, while the AMD part scales to 24 threads from its 12 cores.

The manufacturing process differs: TSMC produces the AMD chip at 4 nm and the Intel chip at 3 nm. The AMD die measures 233 mm², while the Intel die size is not recorded in the database. Cache layouts diverge significantly. The AMD processor allocates 80 KB of L1 cache per core, 1 MB of L2 per core, and a 16 MB L3 cache. The Intel processor allocates 192 KB of L1 per core, 2.5 MB of L2 per core, and a shared 12 MB L3 cache.

Memory support also separates the two. The AMD chip supports DDR5 and LPDDR5X across a dual-channel bus with 89.6 GB/s bandwidth. The Intel chip supports only LPDDR5X, also dual-channel, but with a higher 136.5 GB/s bandwidth. Neither supports ECC memory. PCIe connectivity differs as well: the AMD uses Gen 4 with 16 CPU lanes, while the Intel uses Gen 5 with 4 CPU lanes.

The integrated graphics units are distinct: AMD pairs the CPU with the Radeon 890M, while Intel uses the Arc 140V. Both processors are mobile segments, active in production, and have locked multipliers. The AMD uses AMD Socket FP8, and the Intel uses Intel BGA 2833.

Head-to-Head Benchmarks

The head-to-head results show a dominant multi-threaded performance gap in favor of the AMD Ryzen AI 9 HX 370. In Cinebench R23 multicore, the AMD scores 21761 against the Intel's 10178, a delta of 113.8%. The Cinebench R15 multicore test shows a similar pattern: 3409.5 versus 1583, a 115.4% advantage. PassMark integer math delivers the largest margin, with the AMD at 122933 and the Intel at 44019, a 179.3% lead. PassMark data compression also favors the AMD heavily: 445719 versus 186521, a 139% difference. PassMark extended instructions show the AMD at 31653 versus 15613, a 102.7% gap.

PassMark multithread scores reinforce the pattern. The AMD records 35148, the Intel records 19810, a 77.4% advantage. PassMark data encryption shows 22252 versus 14141, a 57.4% lead. PassMark floating point math has the AMD at 76892 and the Intel at 59536, a 29.2% margin. PassMark random string sorting shows 48723 versus 22622, a 115.4% difference. PassMark physics favors the AMD by a smaller margin: 1881 versus 1637, a 14.9% lead.

Single-thread results are much closer. Cinebench R23 single-core has the AMD at 2018 and the Intel at 1950, a 3.5% AMD win. Cinebench R15 single-core gives the AMD 306.5 and the Intel 301.5, a 1.7% margin. The Intel takes the PassMark single-thread test with 4274 versus 3973, a 7% advantage. The PassMark find prime numbers test also goes to the Intel: 195 versus 126, a 35.4% difference.

The overall win count stands at 12 for the AMD and 3 for the Intel. The Intel's wins are concentrated in single-thread integer workloads and the prime number search, while the AMD dominates across multi-threaded, compression, encryption, and extended instruction tests.

Specification Differences

The two processors differ across several specification fields. The AMD has 12 cores and 24 threads; the Intel has 8 cores and 8 threads. Base clocks are 2.00 GHz for the AMD and 3.30 GHz for the Intel. Both boost to 5.10 GHz. TDP ratings are close: 28 watts for the AMD, 30 watts for the Intel.

The AMD uses AMD Socket FP8, the Intel uses Intel BGA 2833. Process nodes differ at 4 nm versus 3 nm, both from TSMC. The AMD die size is 233 mm²; the Intel die size is not recorded. L1 cache is 80 KB per core for the AMD versus 192 KB per core for the Intel. L2 cache is 1 MB per core versus 2.5 MB per core. L3 cache is 16 MB versus 12 MB shared.

Memory support: the AMD accepts DDR5 and LPDDR5X, the Intel accepts only LPDDR5X. Memory bandwidth is 89.6 GB/s for the AMD and 136.5 GB/s for the Intel. PCIe generation and lane counts differ: Gen 4 with 16 lanes for the AMD, Gen 5 with 4 lanes for the Intel. Integrated graphics are the Radeon 890M versus the Arc 140V.

Release dates differ: the AMD launched on 2024-06-30, the Intel on 2024-09-23. Part numbers are also distinct, with the Intel carrying a longer identifier string.

Where Each One Wins

The AMD Ryzen AI 9 HX 370 wins in all multi-threaded rendering tests. Cinebench R23 and R15 multicore scores show a lead of over 113% in both cases. This positions the AMD for workloads that scale across cores, such as video encoding, 3D rendering, and compilation tasks. PassMark multithread, integer math, data compression, and encryption also favor the AMD by wide margins, indicating strong performance in data-heavy and parallel workloads.

The Intel Core Ultra 9 288V wins in PassMark single-thread and PassMark find prime numbers. The 7% single-thread advantage suggests faster responsiveness in lightly threaded applications and everyday tasks that rely on a single core. The prime number test, which often reflects integer and branch prediction efficiency, shows a 35.4% lead for the Intel, indicating an advantage in specific algorithmic workloads.

The AMD also holds the single-core advantage in Cinebench R23 and R15, but only by 3.5% and 1.7% respectively. This suggests that the Intel's single-thread win in PassMark is workload-specific rather than a general single-core superiority. In mixed productivity suites, the AMD's broader multi-thread dominance likely outweighs the Intel's narrow single-thread win.

The physical differences matter for system design. The Intel's higher memory bandwidth of 136.5 GB/s versus 89.6 GB/s for the AMD could benefit memory-bound tasks, though the benchmark data does not isolate this effect. The Intel's PCIe Gen 5 support with 4 lanes contrasts with the AMD's PCIe Gen 4 with 16 lanes, which affects expansion options rather than raw CPU compute.

The Verdict

Benchmark data clearly favors the AMD Ryzen AI 9 HX 370 for multi-threaded performance. With 12 cores and 24 threads, it delivers more than double the Cinebench R23 multicore score of the Intel Core Ultra 9 288V, and it maintains leads of over 100% in PassMark integer math, data compression, and extended instructions. The average benchmark score of 37904 versus 23219, and the 86th versus 76th percentile placement, confirm the AMD's overall performance advantage.

The Intel Core Ultra 9 288V has specific strengths in single-threaded integer tasks. Its PassMark single-thread score of 4274 outperforms the AMD by 7%, and its prime number search result shows a 35.4% improvement. These wins indicate that the Intel chip handles certain latency-sensitive, single-thread workloads more efficiently. Its higher base clock of 3.30 GHz versus 2.00 GHz for the AMD likely contributes to this.

For system integrators, the choice depends on workload profile. The AMD suits multi-core-heavy applications, rendering, and parallel data processing. The Intel suits single-threaded responsiveness and workloads that rely on fast integer operations. The Intel's higher memory bandwidth and PCIe Gen 5 support add platform-level differentiation, but the recorded benchmarks do not show these translating into CPU compute advantages.

The win count of 12 to 3 in head-to-head tests, combined with the magnitude of the multi-threaded margins, makes the AMD the stronger all-around processor in the database's measurements. The Intel remains competitive only in specific single-thread scenarios, which are narrower in scope than the AMD's broad multi-threaded dominance.