AMD Ryzen AI Max+ 392 vs Intel Core Ultra 9 285HX Comparison

Head-to-Head Benchmarks

The benchmark data paints a decisive picture: the Intel Core Ultra 9 285HX wins every single head-to-head test recorded in the database. Across 11 comparative benchmarks, Intel takes 11 wins, with AMD failing to secure a single victory. The margins vary from near-parity to substantial, but the direction is consistent throughout.

The largest gap appears in floating-point math. Intel scores 194998 against AMD's 99548, a delta of -48.9%. That is nearly double the throughput, a result that heavily favors Intel for scientific computation, 3D rendering, and any workload relying on vectorized floating-point operations. The Intel part also dominates data encryption, scoring 48567 versus 27784, a -42.8% delta. Encryption workloads, which rely on AES-NI and related instruction paths, clearly favor the Intel architecture.

Multi-threaded performance shows a significant Intel advantage as well. In the passmark_multithread test, Intel records 56902 while AMD manages 45231, a -20.5% delta. The physics test follows a similar pattern: Intel at 3476, AMD at 2887, a -16.9% delta. Random string sorting shows Intel ahead with 77196 against 59487, a -22.9% delta. These results indicate that Intel's 24-core configuration delivers substantially more aggregate throughput in heavily parallel workloads.

The data compression test gives Intel a 631885 score versus AMD's 554760, a -12.2% delta. Prime number generation shows Intel at 460 against AMD's 320, a -30.4% delta, which reflects differences in integer throughput and branch handling. Extended instructions favor Intel by 7.1%, with scores of 49148 and 45666 respectively.

Single-thread performance also favors Intel, though by a more moderate margin. The passmark_single_thread test shows Intel at 4618 and AMD at 3927, a -15% delta. Integer math is the closest contest: Intel scores 155076 versus AMD's 152414, a mere -1.7% delta. This near-tie suggests that for purely scalar integer operations, the two processors are effectively equivalent, with the Intel advantage being marginal.

The average benchmark score confirms the overall picture. Intel's average sits at 76155, while AMD's average is 90541. Despite Intel winning all head-to-head tests, AMD's average score is higher. This discrepancy arises because the two processors were tested across different benchmark suites. AMD's recorded tests include several high-scoring workloads such as data compression at 554760 and integer math at 152414, which pull its average up. Intel's suite includes Cinebench results, which are scored on different scales, and its PassMark scores, while higher than AMD's in each shared test, are averaged across a broader set of measurements. The database's nearest-rival comparisons place AMD's average at the 96th percentile of all CPUs, with Intel at the 95th percentile, so both parts sit near the top of the overall performance distribution.

Where Each One Wins

Based strictly on the recorded data, the Intel Core Ultra 9 285HX wins every workload category that was directly compared. There is no benchmark in the head-to-head set where AMD takes the lead. The Intel processor is faster in data compression, encryption, extended instructions, prime number generation, floating-point math, integer math, multi-threaded workloads, physics simulation, random string sorting, and single-threaded tasks.

The largest Intel advantages come in floating-point math and encryption. These are workloads where Intel's execution resources and instruction set support translate into roughly 49% and 43% higher throughput respectively. For users running financial modeling, cryptography, scientific simulations, or media encoding, the Intel part holds a clear edge.

Intel also shows strong performance in multi-threaded and physics workloads, with advantages of 20.5% and 16.9%. These results suggest better scaling across its 24 cores in parallel compute tasks. The random string sorting result, which Intel wins by 22.9%, points to strong memory subsystem performance in sorting and data manipulation tasks.

AMD's closest showing is in integer math, where the -1.7% delta means the two processors are effectively tied. AMD also comes within 7.1% in extended instructions, a smaller gap than most other categories. These results suggest that AMD's Zen 5 cores are competitive in scalar integer work, but the Intel part pulls ahead when workloads involve floating-point operations, encryption, or heavy multi-threading.

The single-thread result is notable. Intel leads by 15%, which means AMD's architecture does not close the gap in lightly threaded applications. For software that relies on a few fast cores, the Intel processor delivers higher per-core performance according to the PassMark single-thread metric.

Architecture Differences

The two processors take fundamentally different design approaches. AMD uses a 12-core, 24-thread configuration based on the Zen 5 architecture, codenamed Strix Halo. Intel uses a 24-core, 24-thread configuration based on the Arrow Lake architecture, codenamed Arrow Lake-HX. Intel's cores do not support simultaneous multithreading, so its 24 cores map directly to 24 threads. AMD's 12 cores each support two threads, producing the same 24-thread count from half as many physical cores.

The manufacturing process differs. AMD builds on a 4 nm process from TSMC, while Intel uses a 3 nm process, also from TSMC. Intel's smaller process node contributes to its higher transistor count of 17,800 million, compared to AMD's unspecified transistor count. Intel's die size is listed at 243 mm², while AMD uses a dual-die design with two 70.6 mm² chiplets, totaling roughly 141.2 mm².

Cache configurations differ substantially. AMD provides 80 KB of L1 cache per core, 1 MB of L2 per core, and a shared 64 MB L3 cache. Intel provides 192 KB of L1 per core, 3 MB of L2 per core, and a shared 36 MB L3 cache. Intel's per-core caches are larger, but AMD's shared L3 is nearly double Intel's, which can benefit workloads that repeatedly access a large working set.

Memory support also diverges. AMD uses LPDDR5X with a quad-channel memory bus and 256.0 GB/s of bandwidth. Intel uses DDR5 with a dual-channel bus and 102.4 GB/s of bandwidth. AMD's memory bandwidth is exactly double Intel's, which may compensate for some of its core-count disadvantage in memory-intensive workloads, though the benchmark results still favor Intel overall.

PCIe connectivity differs. AMD offers Gen 4 with 16 CPU-only lanes, while Intel offers Gen 5 with 20 CPU-only lanes. Intel's newer PCIe generation and additional lanes provide more headroom for high-bandwidth peripherals such as GPUs and NVMe storage.

Integrated graphics also differ. AMD uses the Radeon 8060S, while Intel uses the Arc Xe-LPG Graphics 64EU. The database does not include graphics benchmarks for either part, so no performance comparison is possible from the recorded data.

Clock speeds favor Intel on boost. Intel's base clock is 2.80 GHz with a 5.50 GHz boost, while AMD runs at 3.20 GHz base and 5.00 GHz boost. AMD has a higher base clock, but Intel's boost clock is 500 MHz higher.

Both processors carry a 55 W TDP, support ECC memory, and are classified as mobile parts. AMD uses socket FP11, while Intel uses BGA 2114. Intel's multiplier is unlocked, while AMD's is not. AMD's release date is listed as January 5, 2026, while Intel's is January 12, 2025.

FAQ

Q: Which processor wins the most benchmarks?

A: The Intel Core Ultra 9 285HX wins all 11 head-to-head benchmark comparisons recorded in the database. AMD does not win any of the shared tests.

Q: What is the largest performance gap between the two?

A: The largest gap is in floating-point math, where Intel scores 194998 versus AMD's 99548, a delta of -48.9%. The encryption test shows the second-largest gap at -42.8%.

Q: Are the two processors close in any workload?

A: The closest result is in integer math, where Intel scores 155076 and AMD scores 152414, a delta of only -1.7%. Extended instructions are also relatively close, with Intel ahead by 7.1%.

Q: How do the core and thread counts compare?

A: AMD has 12 cores and 24 threads, relying on simultaneous multithreading. Intel has 24 cores and 24 threads, with no multithreading support. Both present 24 threads to the operating system.

Q: Which processor has higher memory bandwidth?

A: AMD supports LPDDR5X with a quad-channel bus and 256.0 GB/s of bandwidth. Intel supports DDR5 with a dual-channel bus and 102.4 GB/s of bandwidth. AMD's bandwidth is double Intel's.

Q: What are the clock speed differences?

A: AMD has a base clock of 3.20 GHz and a boost clock of 5.00 GHz. Intel has a base clock of 2.80 GHz and a boost clock of 5.50 GHz. Intel's boost is higher by 500 MHz, while AMD's base is higher by 400 MHz.

Specification Differences

| Specification | AMD Ryzen AI Max+ 392 | Intel Core Ultra 9 285HX |

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

| Cores | 12 | 24 |

| Threads | 24 | 24 |

| Base clock | 3.20 GHz | 2.80 GHz |

| Boost clock | 5.00 GHz | 5.50 GHz |

| Socket | AMD Socket FP11 | Intel BGA 2114 |

| Architecture | Zen 5 | Arrow Lake |

| Codename | Strix Halo | Arrow Lake-HX |

| Process node | 4 nm | 3 nm |

| Transistors | Not listed | 17,800 million |

| Die size | 2x 70.6 mm² | 243 mm² |

| L1 cache | 80 KB per core | 192 KB per core |

| L2 cache | 1 MB per core | 3 MB per core |

| L3 cache | 64 MB shared | 36 MB shared |

| Memory support | LPDDR5X | DDR5 |

| Memory bus | Quad-channel | Dual-channel |

| Memory bandwidth | 256.0 GB/s | 102.4 GB/s |

| PCIe | Gen 4, 16 lanes | Gen 5, 20 lanes |

| Integrated graphics | Radeon 8060S | Arc Xe-LPG Graphics 64EU |

| Multiplier unlocked | No | Yes |

| Release date | 2026-01-05 | 2025-01-12 |

| PassMark single-thread | 3927 | 4618 |

| PassMark multi-thread | 45231 | 56902 |

| Average benchmark score | 90541 | 76155 |

| Percentile vs all CPUs | 96 | 95 |

The Verdict

The recorded data shows a clear winner for raw compute performance. The Intel Core Ultra 9 285HX outperforms the AMD Ryzen AI Max+ 392 in every directly compared benchmark. Users who prioritize floating-point math, encryption, multi-threaded throughput, or single-thread speed should select the Intel part based on these results.

The Intel processor's 24 physical cores deliver higher multi-thread scores despite lacking simultaneous multithreading. Its 5.50 GHz boost clock and 3 nm process node contribute to a 15% single-thread advantage. The -48.9% delta in floating-point math and -42.8% delta in encryption are the standout margins, making Intel the stronger choice for compute-heavy mobile workloads.

The AMD processor is not without merits, though they do not appear in the head-to-head results. Its 256.0 GB/s memory bandwidth is double Intel's, and its 64 MB L3 cache is larger. The integer math result shows near-parity with Intel, and the extended instructions gap is modest. AMD's average benchmark score of 90541 is higher than Intel's 76155, and its 96th percentile ranking edges Intel's 95th. However, these aggregate figures reflect different test suites rather than direct performance equivalence.

For any user choosing between these two mobile processors based strictly on the benchmark data, the Intel Core Ultra 9 285HX is the faster CPU in every measured category. The AMD Ryzen AI Max+ 392 offers higher memory bandwidth and a larger shared cache, but the database records no workload where those features translate into a benchmark win against Intel.