AMD Ryzen AI 9 HX 375 vs Intel Core Ultra 5 245 Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive overall victory for the Intel Core Ultra 5 245, which wins 12 of the 15 shared benchmark comparisons. The AMD Ryzen AI 9 HX 375 takes only 3 wins, but those wins are substantial in their specific domains.

The single-core gap is the most striking difference in the dataset. In Cinebench R23 single-core, Intel scores 4648 against AMD's 1988, a 57.2% advantage. The Cinebench R15 single-core test shows a similar pattern, with Intel at 468 and AMD at 301, a 35.7% delta. The PassMark single-thread test confirms the trend at 4394 versus 3867, a 12% lead for Intel.

Multi-core results are more mixed. Intel wins Cinebench R23 multi-core with 32924 against 21812, a 33.8% margin. However, in Cinebench R15 multi-core, AMD edges ahead with 3334 versus 3318, a narrow 0.5% win. The PassMark multithread test favors Intel at 38706 versus 32916, a 15% gap.

The PassMark integer math test delivers AMD's largest win of the entire comparison. AMD scores 121754 against Intel's 91187, a 33.5% advantage. AMD also wins PassMark data compression at 404918 versus 400942, a 1% margin.

Intel dominates the remaining PassMark workloads. PassMark floating point math shows Intel at 120548 against 75153, a 37.7% lead. PassMark find prime numbers favors Intel massively at 365 versus 122, a 66.6% delta. Data encryption goes to Intel at 30236 versus 20802, a 31.2% margin. Extended instructions show Intel ahead at 33304 versus 29269, a 12.1% gap. Physics tests give Intel 2569 against 1819, a 29.2% lead. Random string sorting favors Intel at 49140 versus 44552, a 9.3% difference.

Where Each One Wins

The AMD Ryzen AI 9 HX 375 concentrates its wins in specific mathematical workloads. Its 33.5% lead in integer math indicates strong general arithmetic throughput. The data compression win, though small at 1%, suggests the Zen 5 architecture handles compression algorithms efficiently. The narrow Cinebench R15 multi-core win (0.5%) shows competitive legacy multi-threaded rendering performance.

The Intel Core Ultra 5 245 claims every other category. Single-core performance across all three tested suites (Cinebench R15, R23, PassMark single-thread) goes to Intel with margins from 12% to 57.2%. Modern multi-core rendering in Cinebench R23 shows Intel ahead by 33.8%. Encryption workloads favor Intel by 31.2%. Floating point math, prime number finding, physics simulation, extended instructions, and random string sorting all go to Intel with margins between 9.3% and 66.6%.

The data splits cleanly: AMD wins integer-heavy and compression tasks, while Intel wins essentially everything else, particularly single-threaded, floating point, and cryptographic workloads.

Architecture Differences

The AMD Ryzen AI 9 HX 375 uses the Zen 5 architecture on TSMC's 4 nm process, with the Strix Point codename and a die size of 233 mm². The chip belongs to the Ryzen AI 300 generation, which combines Zen 5 and Zen 5c cores. The 12 cores and 24 threads operate with a base clock of 2.00 GHz and a boost clock of 5.10 GHz.

The Intel Core Ultra 5 245 uses the Arrow Lake architecture on TSMC's 3 nm process, with the Arrow Lake-S codename and a die size of 243 mm². It belongs to the Core Ultra Series 2 and the Ultra 5 (Arrow Lake) generation. The chip has 14 cores and 14 threads, meaning no hyperthreading. Base clock is 3.50 GHz with the same 5.10 GHz boost as AMD. Intel lists 17,800 million transistors for this part.

Cache configurations differ significantly. AMD provides 80 KB of L1 per core, 1 MB of L2 per core, and 16 MB of L3 cache. Intel provides 192 KB of L1 per core, 3 MB of L2 per core, and 24 MB of shared L3 cache. Intel's larger per-core cache allocations and bigger L3 pool align with the higher single-core scores.

The integrated graphics differ. AMD includes the Radeon 890M, while Intel includes Arc Xe-LPG Graphics with 64 execution units. Memory support differs: AMD supports DDR5 and LPDDR5X, while Intel supports DDR5 only. Both use dual-channel memory buses, but Intel's bandwidth is higher at 102.4 GB/s versus AMD's 89.6 GB/s.

Specification Differences

The core and thread counts differ: 12 cores and 24 threads for AMD versus 14 cores and 14 threads for Intel. Base clocks differ at 2.00 GHz for AMD and 3.50 GHz for Intel, while boost clocks match at 5.10 GHz.

Thermal design power differs substantially: AMD at 28 watts versus Intel at 65 watts. The process nodes differ (4 nm for AMD, 3 nm for Intel), as do the socket types (AMD Socket FP8 versus Intel Socket 1851) and market segments (Mobile for AMD, Desktop for Intel).

PCIe support differs: AMD provides Gen 4 with 16 lanes (CPU only), while Intel provides Gen 5 with 20 lanes (CPU only). ECC memory support differs: AMD does not support ECC, Intel does.

The release dates differ: AMD launched on 2024-06-30, Intel on 2025-01-06. Intel has a launch MSRP of $270. AMD's launch MSRP is not recorded. The part numbers differ (100-000001682 for AMD, SRVFE for Intel). Neither chip has an unlocked multiplier.

FAQ

Q: Which processor has more cores and threads?

A: AMD has 12 cores and 24 threads. Intel has 14 cores and 14 threads. AMD offers more threads despite fewer cores.

Q: Which chip wins single-core benchmarks?

A: Intel leads in every recorded single-core test: Cinebench R15 (468 versus 301), Cinebench R23 (4648 versus 1988), and PassMark single-thread (4394 versus 3867).

Q: How do the two compare in multi-core Cinebench results?

A: Intel wins Cinebench R23 multi-core (32924 versus 21812), but AMD wins Cinebench R15 multi-core by a narrow 0.5% margin (3334 versus 3318).

Q: What is the TDP difference?

A: AMD has a 28 watt TDP, Intel has a 65 watt TDP.

Q: Do both support the same memory types?

A: No. AMD supports DDR5 and LPDDR5X, while Intel supports DDR5 only. Both use dual-channel memory, but Intel's bandwidth is 102.4 GB/s versus AMD's 89.6 GB/s.

Q: Which processor has higher average benchmark scores?

A: Intel has an average benchmark score of 48995, while AMD has 46030. Intel also has a higher percentile ranking at 90 versus AMD's 89.

The Verdict

The Intel Core Ultra 5 245 demonstrates superior performance in 12 of 15 shared benchmarks. Its single-core dominance (57.2% lead in Cinebench R23 single-core, 35.7% in Cinebench R15 single-core) and strong multi-core results (33.8% lead in Cinebench R23 multi-core) make it the clear choice for rendering, single-threaded applications, floating point workloads, encryption, and physics simulation. The 65 watt TDP and desktop market segment position it for performance-oriented desktop builds.

The AMD Ryzen AI 9 HX 375 holds advantages in integer math (33.5% lead) and data compression (1% lead), plus a marginal Cinebench R15 multi-core win. Its 28 watt TDP, mobile segment, and support for LPDDR5X memory indicate a focus on efficient mobile computing. The chip's higher thread count (24 versus 14) does not translate into multi-core wins in the recorded data, as Intel's 14 cores outperform AMD's 12 in most multi-threaded tests.

The average benchmark scores confirm Intel's overall edge: 48995 versus 46030, a difference that places Intel in the 90th percentile versus AMD's 89th. Intel's nearest rival in the database is the AMD Ryzen 9 7900 with a 0.5% higher average score, while AMD's closest comparison is the Intel Core Ultra 5 235 with a 0.1% lower average score. The data points to Intel for users prioritizing raw performance across most workloads, while AMD serves scenarios where integer math, compression, lower power draw, and mobile integration matter more.