AMD Ryzen AI Max PRO 380 vs Intel Core Ultra 5 336H Comparison

Where Each One Wins

The benchmark split between these two mobile processors is unusually clear. The AMD Ryzen AI Max PRO 380 takes only two of the eleven recorded head-to-head tests, while the Intel Core Ultra 5 336H claims the other nine. However, the margin of victory tells a more nuanced story than the raw win count. The AMD part wins its two tests by 28.5% and 4.7%, while Intel's wins range from a razor-thin 0.4% single-thread edge to a commanding 74.9% blowout in prime number finding. The Intel chip clearly dominates in workloads that scale with core count and raw floating-point throughput, while the AMD processor holds a focused advantage in integer-heavy and compression-oriented tasks.

The AMD Ryzen AI Max PRO 380 wins in passmark integer math (79789 versus 62070, a 28.5% lead) and passmark data compression (293595 versus 280340, a 4.7% lead). These are workloads where the Zen 5 architecture's per-core efficiency and the chip's 4.90 GHz boost clock can push ahead despite the core-count disadvantage. The Intel Core Ultra 5 336H, by contrast, wins in floating-point math, encryption, physics simulation, multi-threaded throughput, random string sorting, extended instructions, prime number calculation, and single-thread performance. Its 82.4% lead in floating-point math and 58.2% lead in physics simulation are the kind of margins that matter for rendering and scientific compute.

The overall average benchmark score also favors Intel, though by a smaller margin than the individual test splits suggest. The AMD part posts an average of 48171 across its benchmark suite, while the Intel chip averages 34485. This discrepancy exists because the two processors were tested across different benchmark sets: the AMD data includes only PassMark tests, while the Intel data includes Cinebench R15, R20, and R23 results alongside PassMark. The nearest rivals for each chip confirm their relative market positions. The AMD processor's closest competitor is the Intel Core Ultra 5 235A at 48201 (a 0.1% difference), while the Intel Core Ultra 5 336H sits near the Intel Core i7-13700HX at 34554 (a 0.2% difference). The AMD chip ranks in the 90th percentile of all CPUs, the Intel chip in the 84th.

Architecture Differences

The two processors come from fundamentally different design philosophies. The AMD Ryzen AI Max PRO 380 uses the Zen 5 architecture on TSMC's 4 nm process, with the Strix Halo codename. It is built as a 6-core, 12-thread part with simultaneous multithreading, meaning each physical core can handle two threads. The Intel Core Ultra 5 336H uses the Panther Lake architecture on Intel's own 3 nm process, and it is a 16-core, 16-thread part with no hyperthreading. This means Intel's chip has more physical cores but no SMT, while AMD's chip has fewer physical cores but doubles its thread count.

The cache hierarchy differs substantially. AMD assigns 80 KB of L1 and 1 MB of L2 per core, plus 16 MB of shared L3. Intel assigns 192 KB of L1 and 2.5 MB of L2 per core, plus 18 MB of shared L3. Per-core cache is much larger on the Intel side, which helps explain its single-thread performance edge despite a lower boost clock. The Intel chip boosts to 4.60 GHz versus AMD's 4.90 GHz, yet still edges ahead in single-thread PassMark by a 0.4% margin. The larger per-core L2 and L1 allocations on Intel's design likely compensate for the clock disadvantage.

Process technology and foundry also differ. AMD uses TSMC's 4 nm node, while Intel uses its own 3 nm node. Both are active mobile parts, and neither has an unlocked multiplier. The AMD part uses AMD Socket FP11, the Intel part uses Intel BGA 2540. Memory support diverges as well: AMD supports LPDDR5X only, while Intel supports both DDR5 and LPDDR5X. Both use dual-channel memory buses, but AMD's memory bandwidth is rated at 128.0 GB/s versus Intel's 115.2 GB/s. AMD also supports ECC memory; Intel does not. PCIe connectivity differs, with AMD providing Gen 4 with 16 CPU lanes and Intel providing Gen 5 with 12 CPU lanes.

Integrated graphics also separate the two. AMD pairs the processor with Radeon 8040S graphics, while Intel uses Xe3 Graphics. The database does not include GPU benchmarks for either part, so any comparison of their graphics capabilities must remain qualitative. The TDP figures differ notably, with AMD rated at 55 watts and Intel at 25 watts, though the database does not include thermal or power consumption measurements beyond these rated values.

Head-to-Head Benchmarks

The most decisive Intel win comes in passmark find prime numbers, where the Core Ultra 5 336H scores 299 against AMD's 75, a 74.9% advantage. This workload is highly sensitive to core count and integer throughput, and Intel's 16 physical cores overwhelm AMD's 6. The physics simulation test shows a similar pattern, with Intel scoring 2682 against AMD's 1120, a 58.2% lead. Floating-point math follows with Intel at 82415 and AMD at 53084, a 35.6% margin. These three tests account for the bulk of Intel's overall performance advantage in compute-heavy scenarios.

AMD's largest win is in integer math, where it scores 79789 against Intel's 62070, a 28.5% lead. This is a notable result because it shows the Zen 5 architecture's integer execution units can outperform a chip with more than twice the core count in this specific workload. AMD also wins data compression by 4.7%, scoring 293595 versus 280340. The encryption test goes decisively to Intel, 21291 versus 14502, a 31.9% margin. Random string sorting favors Intel by 9.4% (34402 versus 31153). Extended instructions are essentially tied, with Intel ahead by just 0.9% (24542 versus 24333). Single-thread performance is also nearly tied, with Intel ahead by 0.4% (4013 versus 3995).

The multi-threaded PassMark score favors Intel by 15.1%, 28545 versus 24244. This result is consistent with the core-count advantage, though the margin is smaller than the core ratio might suggest. The AMD chip's SMT and higher clock speed narrow the gap in this mixed workload. Across all head-to-head tests, Intel wins eight of the ten unique PassMark tests (the singlethread and single_thread entries are duplicate results of the same test). The average delta across Intel's wins is roughly 27.7%, while AMD's two wins average 16.6%, indicating that when Intel wins, it tends to win by larger margins.

Specification Differences

| Specification | AMD Ryzen AI Max PRO 380 | Intel Core Ultra 5 336H |

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

| Cores | 6 | 16 |

| Threads | 12 | 16 |

| Base clock | 3.60 GHz | 1.90 GHz |

| Boost clock | 4.90 GHz | 4.60 GHz |

| TDP | 55 W | 25 W |

| Socket | AMD Socket FP11 | Intel BGA 2540 |

| Architecture | Zen 5 | Panther Lake |

| Process node | 4 nm | 3 nm |

| Foundry | TSMC | Intel |

| 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 (shared) | 18 MB (shared) |

| Memory support | LPDDR5X | DDR5, LPDDR5X |

| Memory bandwidth | 128.0 GB/s | 115.2 GB/s |

| ECC memory | Yes | No |

| PCIe | Gen 4, 16 Lanes (CPU only) | Gen 5, 12 Lanes (CPU only) |

| Integrated graphics | Radeon 8040S | Intel Xe3 Graphics |

| Release date | 2025-01-05 | 2026-01-04 |

The core and thread counts are the headline difference: Intel offers 16 cores and 16 threads, AMD offers 6 cores and 12 threads. The base clock difference is also stark, with AMD at 3.60 GHz and Intel at 1.90 GHz, though boost clocks are closer at 4.90 GHz and 4.60 GHz respectively. The TDP ratings suggest very different power envelopes, with AMD at 55 watts and Intel at 25 watts. The process nodes differ by one generation, with Intel on 3 nm and AMD on 4 nm. Memory bandwidth favors AMD at 128.0 GB/s versus 115.2 GB/s, and only AMD supports ECC. PCIe generation favors Intel at Gen 5, though AMD has more lanes at 16 versus 12. The release dates are roughly one year apart, with AMD launching in January 2025 and Intel in January 2026.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 5 336H has 16 cores and 16 threads, while the AMD Ryzen AI Max PRO 380 has 6 cores and 12 threads.

Q: Which chip wins in single-thread performance?

A: The Intel Core Ultra 5 336H edges ahead in PassMark single-thread scoring with 4013 versus AMD's 3995, a 0.4% margin.

Q: Which processor has the higher boost clock?

A: The AMD Ryzen AI Max PRO 380 boosts to 4.90 GHz, while the Intel Core Ultra 5 336H boosts to 4.60 GHz.

Q: Does either chip support ECC memory?

A: Yes, the AMD Ryzen AI Max PRO 380 supports ECC memory. The Intel Core Ultra 5 336H does not.

Q: Which processor has a higher average benchmark score?

A: The AMD Ryzen AI Max PRO 380 has an average benchmark score of 48171, while the Intel Core Ultra 5 336H averages 34485. However, the two chips were tested on different benchmark suites, so this comparison should be treated with caution.

Q: What memory types does each processor support?

A: The AMD chip supports LPDDR5X only. The Intel chip supports both DDR5 and LPDDR5X.

The Verdict

The data points to a clear division of labor. The Intel Core Ultra 5 336H is the stronger choice for workloads that use many cores or heavy floating-point math. Its 16 physical cores drive a 74.9% lead in prime number finding, a 58.2% lead in physics simulation, and a 35.6% lead in floating-point math. It also wins the multi-threaded PassMark test by 15.1% and delivers better encryption performance by 31.9%. The Intel chip's single-thread score is marginally higher, and its 84th percentile ranking places it among capable mobile processors, with nearest rivals including the Intel Core i7-13700HX and AMD Ryzen 7 3700X.

The AMD Ryzen AI Max PRO 380 is the better part for integer-heavy workloads and data compression. Its 28.5% lead in integer math and 4.7% lead in data compression show that the Zen 5 architecture can outperform a higher-core-count rival in specific tasks. The AMD chip also offers higher memory bandwidth at 128.0 GB/s, ECC support, and a 90th percentile ranking among all CPUs, with nearest rivals like the Intel Core Ultra 5 235A and AMD Ryzen 9 7900X3D. Its 4.90 GHz boost clock is the highest of the two.

The power envelope differs significantly, with AMD rated at 55 watts and Intel at 25 watts. Systems designers choosing between these parts will see the Intel chip as the lower-power option with higher core counts, while the AMD chip delivers higher clock speeds, more memory bandwidth, and ECC support within a higher TDP budget. The benchmark results indicate that neither chip is universally faster; the correct choice depends entirely on whether the target workload favors Intel's core-count advantage or AMD's architectural efficiency in integer and compression tasks.