AMD Ryzen AI Max PRO 390 vs Intel Core Ultra 7 270HX Plus Comparison

AMD
AMD

AMD Ryzen AI Max PRO 390

CORE STATE Strix Halo
CORE SPECS 12 Cores / 24 Threads
CLOCK SPEED 3.2 Base / 5 GHz Turbo
CACHE 64 MB (shared)
MAX TDP 55W
ARCHITECTURE Zen 5
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
Intel
INTEL

Core Ultra 7 270HX Plus

CORE STATE Arrow Lake-HX Refresh
CORE SPECS 20 Cores / 20 Threads
CLOCK SPEED 2.4 Base / 5.3 GHz Turbo
CACHE 30 MB (shared)
MAX TDP 55W
ARCHITECTURE Arrow Lake-HX Refresh
nm
PROCESS 3 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

cinebench_cinebench_r15_multicore
3,918
4,224
cinebench_cinebench_r15_singlecore
303
596
cinebench_cinebench_r23_multicore
24,828
41,913
cinebench_cinebench_r23_singlecore
1,976
5,917
passmark_data_compression
506,170
493,179
passmark_data_encryption
26,027
37,813
passmark_extended_instructions
40,888
39,283
passmark_find_prime_numbers
323
482
passmark_floating_point_math
94,666
163,567
passmark_integer_math
148,508
122,449
passmark_multithread
42,912
48,270
passmark_physics
2,773
3,843
passmark_random_string_sorting
55,248
60,020
passmark_single_thread
3,967
4,764
passmark_singlethread
3,967
4,764
cinebench_cinebench_r20_multicore
N/A
17,603
cinebench_cinebench_r20_singlecore
N/A
2,485

Analysis: AMD Ryzen AI Max PRO 390 vs Intel Core Ultra 7 270HX Plus

Head-to-Head Benchmarks

The benchmark data presents a clear overall winner in the Intel Core Ultra 7 270HX Plus, which takes 12 of the 15 recorded comparisons. The most dramatic gap appears in Cinebench R23 single-core, where the Intel part scores 5917 against AMD's 1976, a 66.6% deficit for the Ryzen AI Max PRO 390. That is the largest single delta in the head-to-head set, and it signals a fundamental difference in how these two mobile processors approach single-threaded performance.

The multi-core Cinebench R23 result follows the same pattern, though not as severely. Intel's 41913 score beats AMD's 24828 by 40.8%, a substantial margin for heavily threaded rendering workloads. Cinebench R15 multicore shows a smaller but still decisive Intel advantage: 4224 versus 3918, a 7.2% lead. Single-core R15 tells a similar story to R23, with Intel ahead by 49.2% (596 versus 303). The data suggests that for any Cinebench workload, the Intel Core Ultra 7 270HX Plus is the clear choice.

Outside of Cinebench, the results are more mixed. AMD wins three tests, and those wins are not trivial. PassMark integer math shows the Ryzen AI Max PRO 390 scoring 148508 against Intel's 122449, a 21.3% lead. That is a significant advantage for workloads that rely heavily on integer arithmetic. AMD also leads in data compression by 2.6% (506170 versus 493179) and in extended instructions by 4.1% (40888 versus 39283). These wins indicate that AMD's Zen 5 architecture handles certain instruction streams more efficiently than Intel's Arrow Lake-HX Refresh design.

However, Intel dominates the remaining PassMark tests. Floating point math goes to Intel by 42.1% (163567 versus 94666), a massive margin that likely reflects the higher core count and clock speeds. Prime number finding favors Intel by 33% (482 versus 323), data encryption by 31.2% (37813 versus 26027), and physics by 27.8% (3843 versus 2773). Intel also leads in multithread score by 11.1% (48270 versus 42912), random string sorting by 8% (60020 versus 55248), and both single-thread tests by 16.7% (4764 versus 3967).

The average benchmark scores place the two processors very close in overall standing. AMD's average is 63765 with a 93rd percentile ranking among all CPUs, while Intel's average is 61834, also at the 93rd percentile. The nearest rivals list reinforces this parity: the AMD chip sits near the Intel Core i9-13900KS (0.4% below) and the AMD Ryzen AI 7 450G (0.7% above), while Intel's part is essentially tied with the Core i9-13900KF (0% delta). Both processors are clearly high-end mobile parts, but their strength profiles diverge sharply.

Architecture Differences

The two chips could hardly be more different in construction. AMD's Ryzen AI Max PRO 390 uses a 12-core, 24-thread design built on the Zen 5 architecture with the Strix Halo codename. Intel's Core Ultra 7 270HX Plus packs 20 cores but only 20 threads, meaning no hyperthreading, on the Arrow Lake-HX Refresh codename. That core count difference partially explains Intel's multi-core victories, but the thread count disparity is curious: AMD has more threads yet still loses in heavily threaded tests by large margins.

Process technology also differs. AMD is on a 4 nm node from TSMC, while Intel uses a 3 nm node, also from TSMC. The smaller node gives Intel a potential density and efficiency advantage, though the recorded TDP is identical at 55 watts for both. Cache configurations show stark differences. AMD allocates 80 KB of L1 per core, 1 MB of L2 per core, and a large 64 MB shared L3 cache. Intel provides 192 KB of L1 per core, 3 MB of L2 per core, but only 30 MB of shared L3. The L3 advantage for AMD is substantial, yet it does not translate into wins in most benchmark categories.

Memory support splits the field. AMD uses LPDDR5X with a quad-channel bus and 256.0 GB/s of bandwidth, while Intel uses DDR5 with a dual-channel bus and 102.4 GB/s. AMD's memory bandwidth is exactly double Intel's, which likely contributes to its wins in data compression and integer math, where memory access patterns matter heavily. Intel counters with ECC memory support absent (AMD has it) and a faster PCIe implementation: Gen 5 with 20 lanes versus AMD's Gen 4 with 16 lanes.

The integrated graphics differ as well. AMD includes a Radeon 8050S, while Intel ships Arc Xe-LPG Graphics with 64 execution units. No benchmark scores for graphics appear in the data, so a direct comparison is not possible, but the silicon differences are notable. Intel also reports 17,800 million transistors on a 243 mm² die, while AMD's transistor count and die size are not recorded. The release dates are far apart: AMD launched on January 5, 2025, and Intel on March 16, 2026, making Intel a newer design by over a year.

FAQ

Q: Which processor has the higher single-core Cinebench R23 score?

A: The Intel Core Ultra 7 270HX Plus scores 5917, which is 66.6% higher than the AMD Ryzen AI Max PRO 390's 1976.

Q: Does the AMD chip win any benchmark against the Intel chip?

A: Yes, AMD wins three tests: PassMark data compression (506170 versus 493179, a 2.6% lead), PassMark extended instructions (40888 versus 39283, a 4.1% lead), and PassMark integer math (148508 versus 122449, a 21.3% lead).

Q: What is the memory bandwidth difference between the two?

A: AMD's quad-channel LPDDR5X setup provides 256.0 GB/s, exactly double Intel's dual-channel DDR5 bandwidth of 102.4 GB/s.

Q: How do the core and thread counts compare?

A: Intel has 20 cores and 20 threads, while AMD has 12 cores and 24 threads. Intel has more physical cores, but AMD has more threads.

Q: Are both processors in the same performance percentile?

A: Yes, both sit at the 93rd percentile among all CPUs, though AMD's average benchmark score of 63765 is slightly higher than Intel's 61834.

Q: Which processor has the larger L3 cache?

A: AMD offers 64 MB of shared L3 cache, more than double Intel's 30 MB shared L3.

The Verdict

The data points to a clear split: the Intel Core Ultra 7 270HX Plus is the stronger all-around performer in most measured workloads, particularly those that benefit from raw core count and high clock speeds. Its 20 cores and 5.30 GHz boost clock deliver dominant Cinebench results and large wins in floating point, encryption, and physics simulations. The 66.6% single-core R23 lead is difficult to overstate; for any application that is not fully parallel, Intel is the obvious choice.

However, the AMD Ryzen AI Max PRO 390 is not without merit. Its 21.3% integer math lead and wins in data compression and extended instructions suggest that certain computational patterns, likely memory-bandwidth-bound or integer-heavy streams, respond better to AMD's design. The 256.0 GB/s memory bandwidth and 64 MB L3 cache are clear advantages that show up in specific workloads.

For a buyer who prioritizes rendering, physics, encryption, or general productivity, the Intel chip wins on nearly every relevant metric. For workloads that are known to favor integer throughput, large caches, or memory bandwidth, the AMD part holds a niche advantage. The 93rd percentile ranking for both means neither is a slouch, but the benchmark results indicate that Intel's architecture is more broadly effective in the tested scenarios.

Specification Differences

| Specification | AMD Ryzen AI Max PRO 390 | Intel Core Ultra 7 270HX Plus |

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

| Cores | 12 | 20 |

| Threads | 24 | 20 |

| Base Clock | 3.20 GHz | 2.40 GHz |

| Boost Clock | 5.00 GHz | 5.30 GHz |

| Process Node | 4 nm | 3 nm |

| Transistors | Not recorded | 17,800 million |

| Die Size | Not recorded | 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) | 30 MB (shared) |

| Memory Support | LPDDR5X | DDR5 |

| Memory Bus | Quad-channel | Dual-channel |

| Memory Bandwidth | 256.0 GB/s | 102.4 GB/s |

| ECC Memory | Yes | No |

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

| Integrated Graphics | Radeon 8050S | Arc Xe-LPG 64EU |

| Socket | AMD Socket FP11 | Intel BGA 2114 |

| Multiplier Unlocked | No | Yes |

| Release Date | 2025-01-05 | 2026-03-16 |

Where Each One Wins

The Intel Core Ultra 7 270HX Plus is the winner for any workload that shows up in Cinebench, which typically translates to video rendering, 3D modeling, and other heavily threaded creative tasks. Its 40.8% R23 multi-core lead and 49.2% R15 single-core lead make it the default recommendation for content creation. The 42.1% floating point advantage also points to scientific computing, financial modeling, and any math-heavy simulation. Encryption tasks favor Intel by 31.2%, and physics engines, which appear in both engineering simulations and gaming physics, go to Intel by 27.8%. The 11.1% multithread score and 8% random string sorting lead round out a broad productivity advantage.

The AMD Ryzen AI Max PRO 390 wins specifically where its architectural strengths align. The 21.3% integer math lead suggests it excels in database operations, financial integer calculations, and certain compression algorithms. Its 2.6% data compression win and 4.1% extended instructions lead show that specialized instruction sets, possibly including AVX-512 or similar, are handled efficiently. The quad-channel memory and 64 MB L3 cache make it a candidate for workloads that are memory-latency-sensitive or require large working sets, even if the overall benchmark average is slightly higher for AMD.

For users who must choose between the two, the decision hinges on workload composition. A machine running primarily Cinebench-class rendering and physics should pick Intel. A system dedicated to integer-heavy data processing, compression tasks, or extended instruction streams could justify AMD, especially given its higher average benchmark score of 63765 versus Intel's 61834. The 93rd percentile for both means neither will disappoint, but the recorded data shows Intel winning 12 of 15 head-to-head tests, which is a decisive statistical verdict.

DETAILED SPECIFICATIONS

SPECIFICATION
AI Max PRO 390
Ultra 7 270HX Plus
Core Specs
Cores
12
20 +66.7%
Threads
24
20 -16.7%
Base Clock (GHz)
3.2
2.4 -25.0%
Boost Clock (GHz)
5
5.3 +6.0%
Frequency (GHz)
3.2
2.4 -25.0%
Turbo Clock (GHz)
5
5.3 +6.0%
Multiplier
32
24 -25.0%
SMP CPUs
1
1 0.0%
Cache
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)
30 MB (shared)
Power
TDP (W)
55
55 0.0%
PL1
—
55 W
PL2
—
160 W
Configurable TDP
45-120 W
—
Architecture
Architecture
Zen 5
—
Codename
Strix Halo
Arrow Lake-HX Refresh
Generation
Ryzen AI Max PRO (Zen 5)
Ultra 7 (Arrow Lake-HX)
Process Size
4 nm
3 nm
Transistors
—
17,800 million
Die Size
—
243 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
LPDDR5X
DDR5
Memory Bus
Quad-channel
Dual-channel
Memory Bandwidth
256.0 GB/s
102.4 GB/s
ECC Memory
Yes
No
Platform
Socket
AMD Socket FP11
Intel BGA 2114
Chipsets
—
WM880, HM870
PCIe
Gen 4, 16 Lanes(CPU only)
Gen 5, 20 Lanes(CPU only)
Intel Hybrid
Hybrid Cores
—
P-Cores: 8 E-Cores: 12
E-Core Frequency
—
1800 MHz up to 4.7 GHz
AI/NPU
NPU
Yes / 50 TOPS
Yes / 13 TOPS
Graphics
Integrated Graphics
Radeon 8050S
Arc Xe-LPG Graphics 64EU
Other
Market
Mobile
Mobile
Production Status
Active
Active
Part Number
100-000001421
SADST
Package
FC-BGA
FC-BGA
Tj Max
100°C
105°C
View Ryzen AI Max PRO 390 Details View Core Ultra 7 270HX Plus Details