AMD Ryzen AI 9 HX 370 vs Intel Core Ultra 5 245 Comparison

The Verdict

The benchmark data splits these two processors into distinct roles. The Intel Core Ultra 5 245 wins 12 of the 15 head-to-head tests, while the AMD Ryzen AI 9 HX 370 wins 3. The Intel part holds a decisive lead in raw compute, particularly in single-threaded and floating-point workloads. Its average benchmark score of 48995 places it in the 90th percentile of all CPUs, while the AMD chip scores 37904 on average and sits in the 86th percentile.

The Intel Core Ultra 5 245 is the choice for users who prioritize peak performance in threaded applications, physics simulation, and encryption. Its Cinebench R23 multicore score of 32924 is 33.9% higher than the AMD part's 21761. The Intel chip also dominates in single-core tasks, with a Cinebench R23 single-core score of 4648 versus 2018 for AMD, a 56.6% gap.

The AMD Ryzen AI 9 HX 370 has a narrower set of advantages, but they are meaningful. It leads in integer math by 34.8% (122933 versus 91187), in data compression by 11.2% (445719 versus 400942), and in Cinebench R15 multicore by 2.8% (3409.5 versus 3318). These wins point to workloads where its 12-core, 24-thread configuration with simultaneous multithreading provides an edge.

The Intel part is a desktop processor with a 65 TDP and a launch MSRP of $270. The AMD part is a mobile processor with a 28 TDP. The data does not support a single universal winner; it supports a split decision based on workload type.

Architecture Differences

The AMD Ryzen AI 9 HX 370 uses the Zen 5 architecture on TSMC's 4 nm process, with a die size of 233 mm². It is built on the Strix Point codename and belongs to the Ryzen AI 300 generation, which combines Zen 5 and Zen 5c cores. The chip has 12 cores and 24 threads, with a base clock of 2.00 GHz and a boost clock of 5.10 GHz. Its cache layout includes 80 KB of L1 per core, 1 MB of L2 per core, and 16 MB of L3 cache. The integrated graphics are Radeon 890M, and the memory interface is dual-channel DDR5 or LPDDR5X with 89.6 GB/s bandwidth.

The Intel Core Ultra 5 245 uses the Arrow Lake architecture on TSMC's 3 nm process, with a die size of 243 mm². It belongs to the Core Ultra Series 2 and the Ultra 5 generation. This processor has 14 cores and 14 threads, meaning no hyperthreading is present. Base clock is 3.50 GHz, boost clock is 5.10 GHz. The cache structure differs substantially: 192 KB of L1 per core, 3 MB of L2 per core, and 24 MB of shared L3. The integrated graphics are Arc Xe-LPG Graphics with 64 execution units. Memory support is DDR5 only, with dual-channel bandwidth of 102.4 GB/s. The Intel chip also supports ECC memory, which the AMD part does not.

The process node difference is notable: TSMC 3 nm for Intel versus TSMC 4 nm for AMD. The Intel die is slightly larger at 243 mm² versus 233 mm², and the transistor count for Intel is listed at 17,800 million. The AMD part's transistor count is not recorded in the database.

PCIe support also separates them. Intel provides Gen 5 with 20 lanes, while AMD provides Gen 4 with 16 lanes. The sockets differ as well: Intel Socket 1851 versus AMD Socket FP8. The AMD chip is a mobile part, and the Intel chip is a desktop part.

FAQ

Q: Which processor has more cores and threads?

A: The AMD Ryzen AI 9 HX 370 has 12 cores and 24 threads. The Intel Core Ultra 5 245 has 14 cores and 14 threads. The AMD part benefits from simultaneous multithreading, while the Intel part does not.

Q: Which processor has the higher boost clock?

A: Both processors have the same boost clock of 5.10 GHz. The base clocks differ: Intel runs at 3.50 GHz, AMD at 2.00 GHz.

Q: Which processor has more L3 cache?

A: The Intel Core Ultra 5 245 has 24 MB of shared L3 cache. The AMD Ryzen AI 9 HX 370 has 16 MB of L3 cache.

Q: Which processor supports ECC memory?

A: Only the Intel Core Ultra 5 245 supports ECC memory. The AMD Ryzen AI 9 HX 370 does not list ECC support.

Q: Which processor has the higher average benchmark score?

A: The Intel Core Ultra 5 245 has an average benchmark score of 48995, placing it in the 90th percentile. The AMD Ryzen AI 9 HX 370 has an average score of 37904, placing it in the 86th percentile.

Q: Which processor has higher memory bandwidth?

A: The Intel Core Ultra 5 245 has 102.4 GB/s of memory bandwidth, while the AMD Ryzen AI 9 HX 370 has 89.6 GB/s.

Specification Differences

The two processors differ in nearly every major specification category. The AMD Ryzen AI 9 HX 370 has 12 cores and 24 threads; the Intel Core Ultra 5 245 has 14 cores and 14 threads. Base clocks are 2.00 GHz for AMD and 3.50 GHz for Intel. Boost clocks are identical at 5.10 GHz. TDP differs sharply: AMD at 28, Intel at 65.

The process node is 4 nm for AMD and 3 nm for Intel. Foundry is TSMC for both, but die sizes differ: 233 mm² for AMD, 243 mm² for Intel. The Intel chip lists 17,800 million transistors; the AMD chip has no recorded transistor count.

Cache structures diverge. AMD uses 80 KB L1 per core, 1 MB L2 per core, and 16 MB L3. Intel uses 192 KB L1 per core, 3 MB L2 per core, and 24 MB shared L3. Memory support: AMD supports DDR5 and LPDDR5X, Intel supports DDR5 only. Memory bandwidth: AMD at 89.6 GB/s, Intel at 102.4 GB/s. ECC memory is available on Intel only.

PCIe capabilities differ: Intel has Gen 5 with 20 lanes, AMD has Gen 4 with 16 lanes. Integrated graphics are Radeon 890M for AMD and Arc Xe-LPG Graphics 64EU for Intel. Sockets are AMD Socket FP8 and Intel Socket 1851. Market segments are Mobile for AMD and Desktop for Intel. Release dates differ: AMD on 2024-06-30, Intel on 2025-01-06. The Intel part has a launch MSRP of $270; the AMD part has no recorded launch MSRP.

Head-to-Head Benchmarks

The Intel Core Ultra 5 245 wins the majority of the head-to-head tests, often by large margins. The largest single-core gap is in Cinebench R23 single-core, where Intel scores 4648 against AMD's 2018, a 56.6% advantage. Cinebench R15 single-core shows a similar pattern: Intel at 468, AMD at 306.5, a 34.5% lead.

In multicore tests, the picture is mixed. Cinebench R23 multicore heavily favors Intel: 32924 versus 21761, a 33.9% margin. However, Cinebench R15 multicore slightly favors AMD: 3409.5 versus 3318, a 2.8% edge. This suggests the AMD chip performs better in the older benchmark's scaling behavior, while the Intel chip dominates in the newer version.

PassMark tests show clear splits. Intel wins floating point math by 36.2% (120548 versus 76892), data encryption by 26.4% (30236 versus 22252), prime number finding by 65.5% (365 versus 126), physics by 26.8% (2569 versus 1881), extended instructions by 5% (33304 versus 31653), and multithread by 9.2% (38706 versus 35148). Intel also edges out AMD in random string sorting by 0.8% (49140 versus 48723) and in single-thread by 9.6% (4394 versus 3973).

AMD wins three tests. The largest is integer math, where AMD scores 122933 against Intel's 91187, a 34.8% advantage. Data compression goes to AMD at 445719 versus 400942, an 11.2% margin. The third win is Cinebench R15 multicore at 2.8%.

The overall win count is 12 for Intel and 3 for AMD. The delta percentages confirm that Intel's victories tend to be larger in magnitude than AMD's, with the exception of integer math.

Where Each One Wins

The Intel Core Ultra 5 245 is the stronger choice for workload types that rely on high single-thread performance and floating-point throughput. Its Cinebench R23 single-core score of 4648 and floating-point math score of 120548 indicate a clear advantage in rendering, simulation, and physics-based applications. The 65 TDP and desktop socket also position it for sustained performance in a stationary system.

The Intel chip also leads in encryption workloads, with a 26.4% margin in data encryption, and in prime number finding, where it outperforms AMD by 65.5%. These results suggest advantages in security-related tasks and mathematical computation. The multithread score of 38706 versus 35148 gives Intel a 9.2% edge in general parallel throughput, despite having fewer threads than the AMD part.

The AMD Ryzen AI 9 HX 370 wins in integer math by 34.8%, the largest margin of any AMD victory. This points to strengths in integer-heavy computation, such as certain types of database processing or compression algorithms. The data compression win at 11.2% reinforces this pattern. The Cinebench R15 multicore win, while small at 2.8%, shows that AMD's 24-thread configuration can outperform in at least one legacy benchmark.

The AMD part's 28 TDP and mobile socket make it suitable for power-constrained environments, while the Intel part's 65 TDP and desktop socket target performance-oriented builds. The Intel chip's higher memory bandwidth (102.4 GB/s versus 89.6 GB/s) and larger L3 cache (24 MB versus 16 MB) support its faster overall throughput. The AMD chip's 24 threads give it a structural advantage in workloads that scale with thread count, though the recorded data shows Intel's 14 threads often prevail.