AMD Ryzen AI 9 PRO 465 vs Intel Core Ultra 5 245KF Comparison

AMD Ryzen AI 9 PRO 465 and Intel Core Ultra 5 245KF represent two very different approaches to CPU design, one optimized for mobile efficiency and the other for desktop performance. While the Intel part is a desktop chip with a 125W TDP and the AMD part is a mobile chip with a 28W TDP, the benchmark data from the database reveals a clear performance hierarchy, along with one surprising counter-example. This analysis breaks down the recorded measurements, architectural differences, and use-case implications.

Head-to-Head Benchmarks

The PassMark suite of tests in the database shows an overwhelming victory for the Intel Core Ultra 5 245KF, which wins 10 of the 11 recorded head-to-head comparisons. The most lopsided results appear in compute-heavy workloads. In the `passmark_find_prime_numbers` test, the Intel chip scores 416 versus the AMD's 126, a delta of -69.7% for the Ryzen. This is the largest percentage gap in the entire dataset, indicating a massive advantage in integer-heavy, branch-dependent workloads. Similarly, in `passmark_floating_point_math`, the Intel part scores 131,546 against the AMD's 66,824, a -49.2% difference, suggesting the Intel architecture handles floating-point operations with substantially more throughput.

The `passmark_data_encryption` test shows another significant Intel win, 33,381 versus 19,308, a -42.2% delta. The `passmark_physics` test follows a similar pattern, with Intel scoring 2,998 to AMD's 1,747, a -41.7% delta. These results point to a consistent pattern: the Intel Core Ultra 5 245KF delivers roughly 40% to 70% higher performance in encryption, physics simulation, and prime number calculations. The `passmark_extended_instructions` test, which often reflects SIMD and specialized instruction efficiency, also favors Intel decisively, 37,912 versus 26,441, a -30.3% delta.

In multi-threaded throughput, measured by `passmark_multithread`, Intel leads with 43,110 points against AMD's 31,485, a -27% delta. This result is notable because the AMD chip has 20 threads while the Intel chip has only 14 threads. Despite having 43% more threads, the AMD part still trails by more than a quarter in raw multi-threaded score, indicating that Intel's per-core performance and memory bandwidth (102.4 GB/s versus 89.6 GB/s) more than compensate for the thread count disadvantage.

The `passmark_random_string_sorting` test, which can be sensitive to memory latency and cache hierarchy, also goes to Intel, 55,206 versus 40,860, a -26% delta. The `passmark_data_compression` test shows a smaller but still clear Intel advantage, 460,123 versus 385,174, a -16.3% delta. Even in single-threaded performance, where the AMD's 5.00 GHz boost clock is close to Intel's 5.20 GHz, Intel wins, 4,715 versus 4,168, an -11.6% delta.

The single AMD victory comes in `passmark_integer_math`, where the Ryzen scores 107,173 against Intel's 98,854, an 8.4% delta in AMD's favor. This is a curious data point. The integer math test often reflects raw ALU throughput and instruction-level parallelism, and despite losing the prime number test so badly, the AMD chip shows a clear edge here. This suggests that while Intel has superior branch prediction or specialized execution units for certain integer operations, the AMD Zen 5 architecture can sustain higher aggregate integer throughput in other patterns.

Architecture Differences

The two processors diverge fundamentally at the architectural level. The AMD Ryzen AI 9 PRO 465 uses the Zen 5 architecture, codenamed Gorgon Point, built on a 4 nm process at TSMC. It is a mobile part with a 28W TDP, designed for efficiency in thin-and-light systems. The Intel Core Ultra 5 245KF uses the Arrow Lake architecture, codenamed Arrow Lake-S, built on a 3 nm process also at TSMC. It is a desktop part with a 125W TDP, designed for sustained high performance with an unlocked multiplier for overclocking.

Core and thread counts differ significantly. The AMD chip has 10 cores and 20 threads, leveraging simultaneous multithreading (SMT) to double thread count. The Intel chip has 14 cores but only 14 threads, as it does not implement SMT on this architecture. This means the AMD part relies on thread parallelism, while the Intel part relies on physical core count and higher per-core efficiency. The cache hierarchies also differ: the AMD chip has 80 KB of L1 and 1 MB of L2 per core, with 16 MB of shared L3. The Intel chip has 192 KB of L1 and 3 MB of L2 per core, with 24 MB of shared L3. Intel's larger per-core caches and larger L3 pool likely contribute to its wins in data compression and random string sorting, which benefit from larger working sets.

Memory support is another key differentiator. The AMD chip supports both DDR5 and LPDDR5X, while the Intel chip supports only DDR5. Both use dual-channel memory buses, but Intel's memory bandwidth is higher at 102.4 GB/s versus AMD's 89.6 GB/s. The PCIe interface also differs: the AMD chip provides Gen 4 with 16 CPU lanes, while the Intel chip provides Gen 5 with 20 CPU lanes, offering more bandwidth for expansion devices.

Integrated graphics is a major split. The AMD Ryzen AI 9 PRO 465 includes a Radeon 890M integrated GPU, making it a complete APU solution for systems without a discrete graphics card. The Intel Core Ultra 5 245KF has N/A for integrated graphics, meaning it requires a discrete GPU for any display output. This is a fundamental use-case distinction: one chip can power a laptop or mini PC on its own, the other is strictly for desktop systems with a dedicated graphics card.

Where Each One Wins

Based on the recorded data, the Intel Core Ultra 5 245KF wins in nearly every compute category. It is the clear choice for workloads like video encoding, 3D rendering, scientific simulation, and data compression, where its higher floating-point score (131,546 vs 66,824) and multi-threaded score (43,110 vs 31,485) provide a decisive edge. The encryption test (33,381 vs 19,308) also indicates superiority in security-related workloads, such as VPN processing or disk encryption. The physics score (2,998 vs 1,747) reinforces its strength in gaming physics and engineering simulations.

The AMD Ryzen AI 9 PRO 465 wins only in `passmark_integer_math`, scoring 107,173 versus 98,854. This isolated victory suggests a specific niche: integer-heavy database operations, financial calculations, or certain types of data processing that do not rely heavily on floating-point or branch-heavy logic. The 8.4% delta in this test is real but narrow, and it is the only counter-signal in a dataset that otherwise shows Intel dominance.

For mobile or power-constrained scenarios, the AMD chip's 28W TDP versus Intel's 125W TDP is a massive practical advantage, but the benchmark data does not include power efficiency metrics. The database shows raw performance only, and in raw performance, Intel wins virtually everywhere. The AMD chip's built-in Radeon 890M graphics also gives it a functional win for systems without discrete GPUs, but the database does not include GPU benchmarks, so this remains a qualitative feature difference, not a performance comparison.

The Verdict

The data is unambiguous: the Intel Core Ultra 5 245KF is the faster processor in almost every measured dimension. It wins 10 of 11 head-to-head tests, with margins ranging from -11.6% in single-threaded work to -69.7% in prime number finding. Its average benchmark score of 55,093 is lower than the AMD's 62,498, but this is misleading: the AMD's average is boosted by its high integer math score, while the Intel's average is dragged down by the same test where it loses. The more relevant comparison is the head-to-head set, where Intel's dominance is clear.

The Intel chip also holds a higher percentile ranking at 91 versus AMD's 93, but this percentile is relative to all CPUs in the database, and the AMD's higher percentile likely reflects its mobile efficiency class rather than absolute speed. The nearest rivals data confirms the positioning: the AMD's closest rivals are high-end mobile and desktop chips like the Intel Core Ultra 7 255HX (delta -0.4%) and Intel Core i9-13900KF (delta 1.1%), while the Intel's rivals include the AMD Ryzen 9 9900X3D (delta 0.6%) and Intel Core Ultra 5 245K (delta 1.9%).

For a desktop builder with a discrete GPU, the Intel Core Ultra 5 245KF is the clear choice based on performance data. Its 14 physical cores, higher clock speeds, larger caches, and faster memory bandwidth deliver superior results in every compute-heavy task measured. For a mobile user or a system requiring integrated graphics, the AMD Ryzen AI 9 PRO 465 offers a complete solution with a 28W TDP and a built-in Radeon 890M, but the benchmark data shows it sacrifices significant performance in most workloads. The choice depends on the use case: raw performance favors Intel, while integration and efficiency favor AMD.

FAQ

Q: Which CPU has more threads?

A: The AMD Ryzen AI 9 PRO 465 has 20 threads across 10 cores, while the Intel Core Ultra 5 245KF has 14 threads across 14 cores.

Q: What is the single biggest performance gap between the two?

A: In the `passmark_find_prime_numbers` test, the Intel scores 416 versus AMD's 126, a -69.7% delta, which is the largest margin in the head-to-head data.

Q: Does the AMD chip ever beat the Intel chip in any benchmark?

A: Yes, in `passmark_integer_math`, the AMD scores 107,173 versus Intel's 98,854, an 8.4% delta in AMD's favor.

Q: Which CPU has integrated graphics?

A: The AMD Ryzen AI 9 PRO 465 includes a Radeon 890M, while the Intel Core Ultra 5 245KF has no integrated graphics (N/A).

Q: What is the difference in TDP?

A: The AMD chip has a 28W TDP, while the Intel chip has a 125W TDP, reflecting their mobile versus desktop design targets.

Q: Which chip has a higher boost clock?

A: The Intel Core Ultra 5 245KF has a boost clock of 5.20 GHz, while the AMD Ryzen AI 9 PRO 465 has a boost clock of 5.00 GHz.

Specification Differences

| Field | AMD Ryzen AI 9 PRO 465 | Intel Core Ultra 5 245KF |

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

| Cores | 10 | 14 |

| Threads | 20 | 14 |

| Base Clock | 2.00 GHz | 4.20 GHz |

| Boost Clock | 5.00 GHz | 5.20 GHz |

| TDP | 28 W | 125 W |

| Socket | AMD Socket FP8 | Intel Socket 1851 |

| Architecture | Zen 5 | Arrow Lake |

| Codename | Gorgon Point | Arrow Lake-S |

| Generation | Ryzen AI PRO 400 (Zen 5 / Zen 5c) | Ultra 5 (Arrow Lake) |

| Process Node | 4 nm | 3 nm |

| Transistors | Not listed | 17,800 million |

| Die Size | 233 mm² | 243 mm² |

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

| L2 Cache (per core) | 1 MB | 3 MB |

| L3 Cache | 16 MB | 24 MB (shared) |

| Memory Support | DDR5, LPDDR5X | DDR5 |

| Memory Bandwidth | 89.6 GB/s | 102.4 GB/s |

| PCIe | Gen 4, 16 Lanes (CPU only) | Gen 5, 20 Lanes (CPU only) |

| Integrated Graphics | Radeon 890M | N/A |

| Market Segment | Mobile | Desktop |

| Multiplier Unlocked | No | Yes |

| Release Date | 2026-01-04 | 2024-10-23 |

| Part Number | 100-000001862 | SRQCY |