AMD Ryzen AI 9 HX 470 vs Intel Core Ultra 5 225 Comparison

AMD
AMD

AMD Ryzen AI 9 HX 470

CORE STATE Gorgon Point
CORE SPECS 12 Cores / 24 Threads
CLOCK SPEED 2 Base / 5.2 GHz Turbo
CACHE 16 MB
MAX TDP 28W
ARCHITECTURE Zen 5
nm
PROCESS 4 nm
LAUNCH DATE 2026
VS
Intel
INTEL

Core Ultra 5 225

CORE STATE Arrow Lake-S
CORE SPECS 10 Cores / 10 Threads
CLOCK SPEED 3.3 Base / 4.9 GHz Turbo
CACHE 20 MB (shared)
MAX TDP 65W
ARCHITECTURE Arrow Lake
nm
PROCESS 3 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

cinebench_cinebench_r15_multicore
3,518
2,609
cinebench_cinebench_r15_singlecore
317
368
cinebench_cinebench_r23_multicore
23,491.5
25,891
cinebench_cinebench_r23_singlecore
2,066
3,655
passmark_data_compression
484,584
302,811
passmark_data_encryption
23,746
22,285
passmark_extended_instructions
34,365
27,162
passmark_find_prime_numbers
125
358
passmark_floating_point_math
81,320
92,038
passmark_integer_math
130,171
65,345
passmark_multithread
37,010
30,459
passmark_physics
1,851
2,342
passmark_random_string_sorting
51,576
36,590
passmark_single_thread
4,124
4,412
passmark_singlethread
4,124
4,412
cinebench_cinebench_r20_multicore
N/A
6,317
cinebench_cinebench_r20_singlecore
N/A
891

Analysis: AMD Ryzen AI 9 HX 470 vs Intel Core Ultra 5 225

AMD Ryzen AI 9 HX 470 and Intel Core Ultra 5 225 occupy different corners of the processor market, and the benchmark data reflects that split cleanly. The AMD part is a 12-core, 24-thread mobile processor built for high throughput in constrained power envelopes, while the Intel part is a 10-core, 10-thread desktop chip with a higher thermal ceiling and stronger single-thread performance. Across the 15 recorded head-to-head tests, the Intel Core Ultra 5 225 takes 8 wins, and the AMD Ryzen AI 9 HX 470 takes 7. The scoreboard is close, but the nature of those wins is not: the AMD chip dominates in integer-heavy and data-intensive workloads, while the Intel chip wins in floating-point, physics, and single-thread tests. The average benchmark score tells the broader story. The AMD processor posts an average of 58826, which places it in the 92nd percentile of all CPUs in the database, while the Intel processor averages 36938, sitting in the 85th percentile. Those averages put the two chips in very different competitive neighborhoods, with the AMD part rivaling workstation-class Xeon and Ryzen X3D parts, and the Intel part trading blows with older Ryzen 5 and Core i9 parts.

Where Each One Wins

The AMD Ryzen AI 9 HX 470 is the clear winner in workloads that stress integer arithmetic, data compression, and parallel thread execution. Its 99.2% lead over the Intel chip in PassMark integer math is the single largest margin in the entire comparison, and it also wins data compression by 60%, random string sorting by 41%, and extended instructions by 26.5%. The PassMark multithread score of 37010 versus 30459 confirms that the AMD chip handles heavily threaded workloads with more headroom, a result that follows from its 12 cores and 24 threads. The AMD chip also wins the Cinebench R15 multicore test by 34.8%, indicating strong scaling in shorter render tasks, though it loses the newer Cinebench R23 multicore test by 9.3%. That split suggests the AMD chip's advantage is not universal across all render workloads, but its overall throughput profile is clearly oriented toward parallel integer work.

The Intel Core Ultra 5 225 wins in single-thread performance, physics simulation, and floating-point math. It leads Cinebench R23 single-core by 43.5%, Cinebench R15 single-core by 13.9%, and PassMark single-thread by 6.5%. Its PassMark physics score of 2342 is 21% higher than the AMD chip's 1851, and its floating-point math score of 92038 is 11.6% ahead. The Intel chip also wins the prime number search test by 65.1%, which is a notable result because that workload tends to reward per-core efficiency and clock speed over raw thread count. The Intel chip's wins are concentrated in workloads that rely on fewer, faster cores, which aligns with its higher base clock of 3.30 GHz and boost clock of 4.90 GHz compared to the AMD chip's 2.00 GHz base and 5.20 GHz boost. The Intel chip's Cinebench R23 multicore win of 9.3% is its only multicore victory, and it shows that the desktop chip can also hold its own in some all-core render workloads despite having fewer threads.

FAQ

Q: Which processor has the higher average benchmark score?

A: The AMD Ryzen AI 9 HX 470 has an average benchmark score of 58826, compared to 36938 for the Intel Core Ultra 5 225. The AMD chip also ranks higher in the database, sitting in the 92nd percentile of all CPUs versus the 85th percentile for the Intel chip.

Q: How do the two chips compare in single-thread performance?

A: The Intel Core Ultra 5 225 wins every single-thread test in the comparison. It leads Cinebench R23 single-core by 43.5%, Cinebench R15 single-core by 13.9%, and PassMark single-thread by 6.5%.

Q: Which processor is better for data compression workloads?

A: The AMD Ryzen AI 9 HX 470 is substantially better, scoring 484584 in PassMark data compression versus 302811 for the Intel chip, a 60% lead. It also wins random string sorting by 41%.

Q: Does the Intel chip win any multicore tests?

A: Yes, the Intel Core Ultra 5 225 wins Cinebench R23 multicore by 9.3%, scoring 25891 against 23491.5. However, the AMD chip wins Cinebench R15 multicore by 34.8% and PassMark multithread by 21.5%.

Q: What is the largest benchmark margin in either direction?

A: The AMD Ryzen AI 9 HX 470 leads PassMark integer math by 99.2%, scoring 130171 versus 65345. The Intel Core Ultra 5 225's largest win is 65.1% in PassMark find prime numbers, 358 versus 125.

Q: How do the nearest rivals compare for each processor?

A: The AMD chip's closest rival, the AMD Ryzen 5 PRO 9645, has an average score of 58916, a 0.2% difference. The Intel chip's closest rival, the AMD Ryzen 5 5600F, has an average score of 36945, effectively a 0% difference. The AMD chip also sits near the Intel Xeon w5-2545, AMD Ryzen 7 9850X3D, and Intel Xeon Platinum 8260M, all within 0.9%. The Intel chip sits near the AMD Ryzen 5 5500X3D, AMD Ryzen AI 7 PRO 450, and Intel Core i9-12900T, all within 0.5%.

Head-to-Head Benchmarks

The most decisive AMD victories are in integer math and data compression. The PassMark integer math score of 130171 versus 65345 is a 99.2% advantage, effectively double the throughput. Data compression shows a 60% lead, 484584 versus 302811, and random string sorting follows at 41%, 51576 versus 36590. Extended instructions come in at 26.5% ahead, 34365 versus 27162, and data encryption is a closer 6.6% win, 23746 versus 22285. The PassMark multithread score of 37010 versus 30459 is a 21.5% margin, and Cinebench R15 multicore shows 3518 versus 2609, a 34.8% win. These results show consistent AMD strength across integer, memory, and parallel workloads.

The Intel victories are equally clear in their own domains. Cinebench R23 single-core shows 3655 versus 2066, a 43.5% lead. Cinebench R15 single-core is 368 versus 317, a 13.9% margin. PassMark single-thread is 4412 versus 4124, a 6.5% win. The find prime numbers test is the most lopsided Intel win: 358 versus 125, a 65.1% advantage. Floating-point math goes to Intel at 92038 versus 81320, an 11.6% lead, and physics follows at 2342 versus 1851, a 21% margin. The Cinebench R23 multicore result is Intel's only multicore win, 25891 versus 23491.5, a 9.3% edge that partially offsets the AMD win in the older R15 multicore test.

The pattern is consistent across both benchmark suites. The AMD chip wins 7 tests, and the Intel chip wins 8. The AMD wins tend to be larger, with four margins above 20%, while the Intel wins include the largest single margin in the prime number test at 65.1% and the Cinebench R23 single-core margin at 43.5%. The average benchmark score gap, 58826 versus 36938, reflects the fact that the AMD chip's wins are concentrated in heavy throughput workloads that carry more weight in the aggregate score.

Specification Differences

The core and thread counts differ substantially. The AMD Ryzen AI 9 HX 470 has 12 cores and 24 threads, while the Intel Core Ultra 5 225 has 10 cores and 10 threads. The AMD chip has no hyperthreading equivalent in the Intel design, so the Intel chip's thread count equals its core count. Clock speeds also differ: the AMD chip has a 2.00 GHz base clock and 5.20 GHz boost clock, while the Intel chip has a 3.30 GHz base clock and 4.90 GHz boost clock. The Intel chip starts at a much higher base frequency but boosts to a lower peak.

Thermal design power is another major split. The AMD chip is rated at 28 W TDP, while the Intel chip is rated at 65 W TDP. The AMD chip is a mobile part, and the Intel chip is a desktop part. The sockets differ: AMD uses Socket FP8, and Intel uses Socket 1851. The memory support also differs. The AMD chip supports DDR5 and LPDDR5X, while the Intel chip supports DDR5 only. Both use dual-channel memory, but the memory bandwidth is different: the AMD chip has 89.6 GB/s, and the Intel chip has 102.4 GB/s. Neither supports ECC memory.

PCIe support differs as well. The AMD chip uses Gen 4 with 16 lanes, while the Intel chip uses Gen 5 with 20 lanes. The integrated graphics are different: the AMD chip uses Radeon 890M, and the Intel chip uses Arc Xe-LPG Graphics 16EU. The AMD chip has a release date of 2025-12-31, while the Intel chip has a release date of 2025-01-06. The Intel chip has a launch MSRP of $246. Neither chip has an unlocked multiplier. The AMD part number is 100-000001936, and the Intel part number is SRQCZSRVF7.

Architecture Differences

The AMD Ryzen AI 9 HX 470 is built on the Zen 5 architecture with the codename Gorgon Point and belongs to the Ryzen AI 400 generation, which uses a Zen 5 / Zen 5c hybrid core layout. It is manufactured on a 4 nm process at TSMC with a die size of 233 mm². The cache layout is per-core: 80 KB of L1 per core, 1 MB of L2 per core, and 16 MB of L3.

The Intel Core Ultra 5 225 is built on the Arrow Lake architecture with the codename Arrow Lake-S and belongs to the Core Ultra Series 2, Ultra 5 generation. It is manufactured on a 3 nm process at TSMC, with 17,800 million transistors and a die size of 243 mm². The cache layout differs significantly: 192 KB of L1 per core, 3 MB of L2 per core, and 20 MB of shared L3.

The node difference is 4 nm versus 3 nm, which gives the Intel chip a denser process, though the AMD chip uses a smaller die. The Intel chip's larger L2 and L3 caches, 3 MB per core and 20 MB shared respectively, likely contribute to its single-thread advantage in the benchmark data. The AMD chip's smaller 16 MB L3 and per-core L1 of 80 KB reflect a different cache strategy tuned for its mobile power envelope. The transistor count for the AMD chip is not recorded, while the Intel chip lists 17,800 million transistors. The AMD chip's Zen 5 / Zen 5c hybrid design allows it to pack 12 cores into a 28 W TDP, while the Intel chip's 10 cores at 65 W TDP are built for sustained desktop performance.

The Verdict

The data points to two distinct use cases. The AMD Ryzen AI 9 HX 470 is the stronger choice for integer-heavy parallel workloads. Its 99.2% lead in integer math, 60% lead in data compression, 41% lead in random string sorting, and 21.5% lead in multithread performance make it the better fit for data processing, compression, and heavily threaded productivity tasks. Its 34.8% win in Cinebench R15 multicore reinforces that position, though the 9.3% loss in Cinebench R23 multicore shows it does not dominate every render workload. The 92nd percentile ranking and average score of 58826 place it alongside workstation-class processors, and its nearest rivals include the Intel Xeon w5-2545 and AMD Ryzen 7 9850X3D, both within 0.9%.

The Intel Core Ultra 5 225 is the stronger choice for single-thread performance and floating-point work. Its 43.5% lead in Cinebench R23 single-core, 13.9% lead in Cinebench R15 single-core, and 6.5% lead in PassMark single-thread make it the better pick for applications that rely on per-core speed. Its 65.1% win in prime number searching and 21% win in physics further support that profile. The 9.3% win in Cinebench R23 multicore is a notable exception to its single-thread-focused pattern, showing that the desktop chip can also handle some all-core render tasks. The 85th percentile ranking and average score of 36938 place it in range of the AMD Ryzen 5 5600F and Intel Core i9-12900T, both within 0.5%.

The benchmark results indicate that the AMD chip's higher average score and percentile ranking come from its strength in the heaviest throughput workloads, while the Intel chip's wins are concentrated in lighter, more latency-sensitive tasks. The 28 W TDP of the AMD chip versus the 65 W TDP of the Intel chip further separates them, with the mobile AMD part delivering more threads per watt and the desktop Intel part delivering higher per-core performance. The record shows no single overall winner, only a clear division of labor: AMD for parallel integer throughput, Intel for single-thread and floating-point speed.

DETAILED SPECIFICATIONS

SPECIFICATION
AI 9 HX 470
Ultra 5 225
Core Specs
Cores
12
10 -16.7%
Threads
24
10 -58.3%
Base Clock (GHz)
2
3.3 +65.0%
Boost Clock (GHz)
5.2
4.9 -5.8%
Frequency (GHz)
2
3.3 +65.0%
Turbo Clock (GHz)
5.2
4.9 -5.8%
Multiplier
20
33 +65.0%
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
16 MB
20 MB (shared)
Power
TDP (W)
28
65 +132.1%
PL1
—
65 W
PL2
—
121 W
Configurable TDP
15-54 W
—
Architecture
Architecture
Zen 5
Arrow Lake
Codename
Gorgon Point
Arrow Lake-S
Generation
Ryzen AI 400 (Zen 5 / Zen 5c)
Ultra 5 (Arrow Lake)
Process Size
4 nm
3 nm
Transistors
—
17,800 million
Die Size
233 mm²
243 mm²
Foundry
TSMC
TSMC
Memory
Memory Support
DDR5, LPDDR5X
DDR5
Memory Bus
Dual-channel
Dual-channel
Memory Bandwidth
89.6 GB/s
102.4 GB/s
ECC Memory
No
No
Platform
Socket
AMD Socket FP8
Intel Socket 1851
Chipsets
—
Z890, B860, W880, Q870, H810
PCIe
Gen 4, 16 Lanes(CPU only)
Gen 5, 20 Lanes(CPU only)
Intel Hybrid
Hybrid Cores
4 + 8
P-Cores: 6 E-Cores: 4
E-Core Frequency
2000 MHz up to 3.3 GHz
2.7 GHz up to 4.4 GHz
P-Core Turbo
—
4.7 GHz
AI/NPU
NPU
Yes / 55 TOPS
—
Graphics
Integrated Graphics
Radeon 890M
Arc Xe-LPG Graphics 16EU
Other
Market
Mobile
Desktop
Production Status
Active
Active
Launch Price
—
$246
Part Number
100-000001936
SRQCZSRVF7
Package
FP8
FC-LGA18W
Tj Max
100°C
105°C
View Ryzen AI 9 HX 470 Details View Core Ultra 5 225 Details