AMD Ryzen AI 9 365 vs Intel Core Ultra 5 228V Comparison

AMD Ryzen AI 9 365 vs Intel Core Ultra 5 228V

The Verdict

The recorded data delivers a clear verdict: the AMD Ryzen AI 9 365 is the dominant processor in this comparison, winning 14 of the 15 head-to-head benchmark tests. The Intel Core Ultra 5 228V takes only a single win. The AMD chip’s overall average benchmark score is 40048, placing it in the 87th percentile of all CPUs, while the Intel chip scores 21440 on average and sits in the 75th percentile. The gap in aggregate performance is substantial, with the AMD part leading by roughly 86.8% based on those average scores.

For workloads that rely on many threads, the choice is unambiguous. The Ryzen AI 9 365 delivers 10 cores and 20 threads, compared to 8 cores and 8 threads for the Intel part. That structural advantage shows up in every multi-threaded test. For single-threaded tasks, the AMD chip still leads, but by a much narrower margin. The Ryzen AI 9 365 wins the single-thread PassMark test by a mere 0.1%, and the single-core Cinebench tests by about 13%. The Intel Core Ultra 5 228V does hold one notable win in prime number computation, but that single result does not offset its losses elsewhere.

The Intel part does have a significantly lower thermal design power (17 watts versus 28 watts), which suggests it may fit into thinner or passively cooled designs, but the performance data shows it cannot match the Ryzen AI 9 365 in most compute tasks. The verdict is straightforward: the AMD Ryzen AI 9 365 is the stronger processor for nearly all benchmarked workloads, while the Intel Core Ultra 5 228V is a lower-power alternative with a narrower performance profile.

Architecture Differences

The two processors come from different design philosophies. The AMD Ryzen AI 9 365 uses the Zen 5 architecture, codenamed Strix Point, and belongs to the Ryzen AI 300 generation which combines Zen 5 and Zen 5c cores. It is built on a 4 nm process at TSMC, with a die size of 233 mm². The Intel Core Ultra 5 228V uses the Lunar Lake architecture, also produced by TSMC but on a finer 3 nm process. Intel’s chip is part of the Core Ultra Series 2 generation.

Core counts differ sharply. The AMD part has 10 physical cores and 20 threads, while the Intel part has 8 cores and 8 threads, meaning no hyperthreading. Cache layouts also diverge. The AMD chip has 80 KB of L1 cache per core, 1 MB of L2 per core, and 16 MB of L3 cache. The Intel chip has 192 KB of L1 per core, 2.5 MB of L2 per core, and 8 MB of shared L3. The larger L3 on the AMD side likely helps in multi-threaded workloads, while Intel’s larger per-core L1 and L2 may benefit single-threaded latency.

Memory support differs as well. The AMD part supports DDR5 and LPDDR5X with dual-channel memory and a recorded bandwidth of 89.6 GB/s. The Intel part’s memory support is listed as dependent on the motherboard, with no bandwidth figure recorded. Both use dual-channel memory buses. PCIe connectivity is also different: the AMD chip offers Gen 4 with 16 CPU lanes, while the Intel chip offers Gen 5 with only 4 CPU lanes. That gives the AMD part more available lanes for expansion, though the Intel part has a newer PCIe standard.

Integrated graphics are present on both. The AMD Ryzen AI 9 365 uses the Radeon 880M, while the Intel Core Ultra 5 228V uses the Arc 130V. The database does not include separate GPU benchmarks, so no performance comparison is possible from the recorded data. Both processors are unlocked for overclocking? No, the multiplier is locked for both. Both are active production parts for the mobile market, with no launch MSRP recorded.

FAQ

Q: Which processor has more cores and threads?

A: The AMD Ryzen AI 9 365 has 10 cores and 20 threads. The Intel Core Ultra 5 228V has 8 cores and 8 threads. The AMD part offers 12 more threads than the Intel part.

Q: What are the base and boost clock speeds?

A: The AMD Ryzen AI 9 365 has a base clock of 2.00 GHz and a boost clock of 5.00 GHz. The Intel Core Ultra 5 228V has a base clock of 2.10 GHz and a boost clock of 4.50 GHz. The Intel part starts slightly higher, but the AMD part boosts higher.

Q: Which processor has a lower thermal design power?

A: The Intel Core Ultra 5 228V has a TDP of 17 watts, while the AMD Ryzen AI 9 365 has a TDP of 28 watts. The Intel part uses 11 watts less, which may affect cooling requirements.

Q: How do their cache sizes compare?

A: The AMD chip has 80 KB of L1 per core, 1 MB of L2 per core, and 16 MB of L3. The Intel chip has 192 KB of L1 per core, 2.5 MB of L2 per core, and 8 MB of shared L3. Total L3 is larger on the AMD side, while per-core L1 and L2 are larger on the Intel side.

Q: Which processor wins the majority of benchmark tests?

A: The AMD Ryzen AI 9 365 wins 14 of 15 head-to-head tests. The Intel Core Ultra 5 228V wins only one test, which is the PassMark find prime numbers benchmark.

Q: What is the average benchmark score for each processor?

A: The AMD Ryzen AI 9 365 has an average benchmark score of 40048, placing it in the 87th percentile. The Intel Core Ultra 5 228V has an average score of 21440, placing it in the 75th percentile.

Specification Differences

| Specification | AMD Ryzen AI 9 365 | Intel Core Ultra 5 228V |

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

| Cores | 10 | 8 |

| Threads | 20 | 8 |

| Base Clock | 2.00 GHz | 2.10 GHz |

| Boost Clock | 5.00 GHz | 4.50 GHz |

| TDP | 28 W | 17 W |

| Socket | AMD Socket FP8 | Intel BGA 2833 |

| Architecture | Zen 5 | Lunar Lake |

| Codename | Strix Point | Lunar Lake |

| Generation | Ryzen AI 300 (Zen 5 / Zen 5c) | Ultra 5 (Lunar Lake) |

| Process Node | 4 nm | 3 nm |

| Die Size | 233 mm² | Not recorded |

| L1 Cache | 80 KB per core | 192 KB per core |

| L2 Cache | 1 MB per core | 2.5 MB per core |

| L3 Cache | 16 MB | 8 MB shared |

| Memory Support | DDR5, LPDDR5X | Depends on motherboard |

| Memory Bandwidth | 89.6 GB/s | Not recorded |

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

| Integrated Graphics | Radeon 880M | Arc 130V |

| Release Date | 2024-06-30 | 2024-09-23 |

| Part Number | 100-000001530 | SRPMVSRPMU |

Head-to-Head Benchmarks

The largest margin in the entire data set comes in the PassMark integer math test. The AMD Ryzen AI 9 365 scores 101831, while the Intel Core Ultra 5 228V scores 39679. That is a delta of 156.6%, meaning the AMD part delivers more than two and a half times the integer math throughput. This result aligns with the core and thread count advantage, as integer math typically scales well with parallelism.

The PassMark data compression test also shows a massive gap. The AMD chip scores 354510 versus 173924 for the Intel chip, a 103.8% difference. Similarly, the Cinebench R23 multi-core test sees the AMD part at 18698 and the Intel part at 9932, an 88.3% lead. The Cinebench R15 multi-core test follows the same pattern: 2842 versus 1502.5, a delta of 89.2%. These results confirm that multi-threaded rendering and compression workloads heavily favor the AMD processor.

In the PassMark random string sorting test, the AMD chip scores 39447 against 21254, a lead of 85.6%. The extended instructions test shows AMD at 25113 versus Intel at 14801, a 69.7% advantage. The PassMark multithread test has AMD at 29467 and Intel at 18227, a 61.7% difference. Data encryption also favors AMD, with scores of 18297 and 13032, a 40.4% lead.

The single-threaded tests are closer. In Cinebench R23 single-core, the AMD chip scores 1992 versus 1758, a 13.3% advantage. The Cinebench R15 single-core test shows 303 versus 267, a 13.5% lead. The PassMark floating point math test has AMD at 62802 versus Intel at 53310, a 17.8% difference. The PassMark physics test is tight: 1704 versus 1538, a 10.8% lead for AMD.

The only Intel win comes in the PassMark find prime numbers test. Here the Intel Core Ultra 5 228V scores 168, while the AMD Ryzen AI 9 365 scores 117. That is a 30.4% advantage for Intel. This specific workload appears to favor Intel’s architecture, possibly due to its larger per-core L1 and L2 caches, though the database does not provide a direct explanation.

The closest overall test is the PassMark single thread test, where AMD scores 3841 and Intel scores 3836, a difference of just 0.1%. That result is essentially a tie, but the recorded winner is the AMD part. The same score appears for the PassMark singlethread test, confirming the near-parity in single-threaded performance between the two chips.

Where Each One Wins

The AMD Ryzen AI 9 365 wins in every category except one. Its largest advantages come in multi-threaded workloads: integer math, data compression, Cinebench multi-core, and random string sorting. These tasks benefit from the 10 cores and 20 threads, which allow more parallel execution than the Intel part’s 8 cores and 8 threads. The AMD chip also leads in floating point math, encryption, extended instructions, and physics, with leads ranging from 10.8% to 40.4%.

For single-threaded tasks, the AMD chip still wins, but by smaller margins. The Cinebench single-core tests show a 13% lead, while the PassMark single thread test shows only a 0.1% difference. This suggests that the two processors have similar per-core performance, with the AMD chip holding a slight edge.

The Intel Core Ultra 5 228V wins only the prime number finding test, where it beats the AMD chip by 30.4%. That is a narrow niche, but it indicates that Intel’s architecture has specific strengths in certain integer-heavy, possibly latency-sensitive tasks. The Intel part also has a lower TDP of 17 watts versus 28 watts, which may make it preferable for systems where power budget and cooling are more critical than raw performance.

In practical terms, the AMD Ryzen AI 9 365 is better suited for workloads such as software compilation, video rendering, data compression, and any multi-threaded application where its 20 threads can be utilized. The Intel Core Ultra 5 228V could be considered for tasks that rely heavily on prime number calculations, though that is a very limited scenario. For general computing, the data consistently points to the AMD processor as the stronger choice. The Intel chip’s single win does not compensate for the large deficits in nearly every other test, especially in multi-threaded performance where the AMD part leads by margins ranging from 61.7% to 156.6%.