AMD Ryzen AI 7 450 vs Intel Core 5 120 Comparison

Head-to-Head Benchmarks

The head-to-head comparison between the AMD Ryzen AI 7 450 and the Intel Core 5 120 is lopsided in favor of the AMD part, which claims 13 wins out of 15 recorded tests. The Intel processor manages only two victories, both in single-core Cinebench workloads.

The largest margin in the entire comparison belongs to the AMD Ryzen AI 7 450 in PassMark random string sorting, where it scores 35648 against Intel's 21499, a delta of 65.8%. That is a substantial gap for a memory-intensive sorting workload, and it suggests the AMD chip's memory subsystem handles pointer-chasing and random access patterns more efficiently. The second-largest win is in extended instructions, where AMD scores 22400 versus 14264, a 57% advantage. This workload exercises SIMD and encryption-related instruction sets, and the data indicates the Zen 5 architecture extracts considerably more throughput from these operations.

Data encryption also shows a massive gap. AMD's 16247 score beats Intel's 11131 by 46%. Integer math follows a similar pattern, with AMD at 88531 versus 60462, a 46.4% delta. Data compression is another decisive AMD win, 315906 against 219535, a 43.9% margin. These PassMark results are consistent across the board: AMD wins floating point math by 20% (54447 vs 45383), physics by 18.4% (1578 vs 1333), and prime number finding by 15.6% (89 vs 77).

The multithreaded PassMark score reinforces this picture. AMD records 26350 versus Intel's 18597, a 41.7% advantage. Even the single-thread PassMark test, which is often expected to favor Intel given its Cinebench single-core wins, goes to AMD by 8.5%, with 3901 versus 3595.

The Cinebench results tell a more nuanced story. In Cinebench R23 multicore, the two processors are nearly inseparable: AMD scores 18316, Intel scores 18255, a margin of just 0.3%. That is effectively a tie, and it is surprising given the AMD chip's large PassMark multithread lead. The R15 multicore test, however, is a different matter entirely. AMD scores 2713 against Intel's 1840, a 47.4% win. This discrepancy between the two Cinebench versions is notable; the older R15 test appears to reward the AMD chip's architecture far more than the newer R23 test.

Intel's wins come in single-core Cinebench tests. In R15 single-core, Intel scores 259 versus AMD's 215, a 17% advantage. In R23 single-core, Intel extends this to 2577 versus 2038, a 20.9% margin. These are meaningful gaps, and they indicate that Intel's Raptor Lake cores have a per-thread performance edge in lightly threaded rendering workloads. Yet the PassMark single-thread test contradicts this trend, showing AMD ahead by 8.5%. The data suggests that single-thread performance is workload-dependent: Intel leads in Cinebench's rendering-specific single-thread test, while AMD leads in the broader PassMark single-thread suite.

Architecture Differences

The two processors represent fundamentally different design philosophies. The AMD Ryzen AI 7 450 uses the Zen 5 architecture, codenamed Gorgon Point, built on a 4 nm TSMC process. It belongs to the Ryzen AI 400 generation, which combines Zen 5 and Zen 5c cores. The Intel Core 5 120 uses Raptor Lake, specifically Raptor Lake-R, on a 10 nm Intel process. The process node difference alone, 4 nm versus 10 nm, explains much of the efficiency and thermal behavior observed in the benchmarks.

Core counts differ significantly. AMD provides 8 cores and 16 threads, while Intel provides 6 cores and 12 threads. That two-core, four-thread advantage helps explain AMD's dominance in multithreaded PassMark workloads, though it does not fully explain the narrow Cinebench R23 multicore result. The AMD chip's die size is 195 mm², while Intel's is 163 mm².

Cache hierarchies also diverge. Both use 80 KB of L1 per core. For L2, AMD uses 1 MB per core, while Intel uses 1.25 MB per core, a slight Intel advantage per core. The L3 cache shows the biggest difference: AMD has 8 MB total, while Intel has 18 MB shared. That larger Intel L3 cache may contribute to its single-core Cinebench wins, as more data can reside closer to the cores.

Memory support differs in scope. AMD supports DDR5 and LPDDR5X, with dual-channel access and a measured memory bandwidth of 89.6 GB/s. Intel supports both DDR4 and DDR5, also dual-channel, but the database records no memory bandwidth figure for it. AMD also supports ECC memory, while Intel does not. This makes the AMD chip more suitable for error-sensitive workloads, though its mobile classification and FP8 socket suggest a different target market.

PCIe capabilities favor Intel. The Intel part uses Gen 5 with 16 lanes (CPU only), while AMD uses Gen 4 with 16 lanes (CPU only). The integrated graphics differ as well: AMD pairs with Radeon 860M, while Intel includes UHD Graphics 730. The AMD chip's socket is AMD Socket FP8, indicating a mobile platform, while Intel uses Socket 1700, a desktop platform. This is reflected in TDP: AMD is rated at 28 watts, Intel at 65 watts. Clock speeds also differ, with AMD base at 2.00 GHz and boost at 5.10 GHz, while Intel bases at 2.50 GHz and boosts to 4.50 GHz. The AMD chip boosts higher, but the Intel chip has a higher base clock.

The Verdict

The data points to two very different usage profiles. The AMD Ryzen AI 7 450 is the superior processor for multithreaded and data-intensive workloads. Its PassMark multithread score is 41.7% higher, its integer math score is 46.4% higher, and its data compression score is 43.9% higher. For encryption, extended instructions, and random string sorting, it leads by margins between 46% and 65.8%. The 8-core, 16-thread configuration, combined with Zen 5's architectural efficiency on a 4 nm process, delivers consistent wins across almost every PassMark category.

The Intel Core 5 120 is the choice for single-core Cinebench rendering performance. Its R23 single-core score of 2577 beats AMD's 2038 by 20.9%, and its R15 single-core score of 259 beats AMD's 215 by 17%. The larger 18 MB L3 cache and higher 2.50 GHz base clock likely contribute to this. However, the PassMark single-thread test shows AMD ahead by 8.5%, so Intel's advantage is not universal.

The percentile rankings reflect the overall performance gap. AMD sits at the 87th percentile of all CPUs, while Intel sits at the 77th percentile. AMD's average benchmark score is 39485, against Intel's 25362. The AMD chip's nearest rivals include the AMD Ryzen 7 PRO 8840HS (0.3% lower average score), the Ryzen 7 9800X3D (0.7% higher), and the EPYC 4245P (0.7% higher). Intel's nearest rivals include the Ryzen 5 5600X3D (identical average score), the Core i7-11700KF (0.2% higher), and the Core i5-13400F (0.3% higher). These rival clusters show that AMD's chip competes with upper-midrange desktop and mobile parts, while Intel's chip sits alongside older desktop processors.

The TDP difference is stark: 28 watts for AMD versus 65 watts for Intel. The AMD chip delivers higher average benchmark scores while being rated for less than half the power. This is a direct consequence of the 4 nm process versus 10 nm process. For systems where thermal headroom and power draw matter, such as thin laptops (given the FP8 socket), the AMD chip is clearly the more efficient option.

Specification Differences

The two processors differ across nearly every major specification field. The AMD Ryzen AI 7 450 uses 8 cores and 16 threads, while the Intel Core 5 120 uses 6 cores and 12 threads. AMD's base clock is 2.00 GHz versus Intel's 2.50 GHz, a 0.50 GHz Intel advantage. AMD's boost clock is 5.10 GHz versus Intel's 4.50 GHz, a 0.60 GHz AMD advantage. TDP is 28 watts for AMD and 65 watts for Intel.

The manufacturing process is 4 nm (TSMC) for AMD and 10 nm (Intel) for Intel. Die size is 195 mm² for AMD and 163 mm² for Intel. L2 cache is 1 MB per core for AMD and 1.25 MB per core for Intel. L3 cache is 8 MB for AMD and 18 MB shared for Intel. Memory support includes DDR5 and LPDDR5X for AMD, versus DDR4 and DDR5 for Intel. Memory bandwidth is recorded at 89.6 GB/s for AMD, with no figure for Intel. ECC memory is supported by AMD only. PCIe is Gen 4 with 16 lanes for AMD, Gen 5 with 16 lanes for Intel. Integrated graphics are Radeon 860M for AMD and UHD Graphics 730 for Intel. The socket is AMD Socket FP8 for AMD and Intel Socket 1700 for Intel. Market segment is Mobile for AMD and Desktop for Intel. Release dates are January 2026 for AMD and July 2025 for Intel. The Intel part has a launch MSRP of $211. The AMD part has no recorded launch MSRP.

FAQ

Q: Which processor wins the most head-to-head benchmarks?

A: The AMD Ryzen AI 7 450 wins 13 of the 15 recorded head-to-head tests, while the Intel Core 5 120 wins 2.

Q: What are the largest performance margins in the comparison?

A: The AMD chip wins random string sorting by 65.8%, extended instructions by 57%, data encryption by 46%, and integer math by 46.4%. The Intel chip wins Cinebench R23 single-core by 20.9% and R15 single-core by 17%.

Q: How do the two chips compare in Cinebench R23 multicore?

A: They are nearly identical. AMD scores 18316 and Intel scores 18255, a difference of only 0.3% in AMD's favor.

Q: What is the difference in core and thread counts?

A: The AMD Ryzen AI 7 450 has 8 cores and 16 threads. The Intel Core 5 120 has 6 cores and 12 threads.

Q: Which processor has a higher boost clock?

A: The AMD Ryzen AI 7 450 boosts to 5.10 GHz, while the Intel Core 5 120 boosts to 4.50 GHz.

Q: Do both processors support ECC memory?

A: No. The AMD Ryzen AI 7 450 supports ECC memory. The Intel Core 5 120 does not.

Where Each One Wins

The AMD Ryzen AI 7 450 wins in every multithreaded PassMark workload recorded: multithread (26350 vs 18597), integer math (88531 vs 60462), floating point math (54447 vs 45383), data compression (315906 vs 219535), data encryption (16247 vs 11131), extended instructions (22400 vs 14264), random string sorting (35648 vs 21499), physics (1578 vs 1333), and prime number finding (89 vs 77). It also wins the PassMark single-thread test (3901 vs 3595) and Cinebench R15 multicore (2713 vs 1840). Its 87th percentile ranking and 39485 average benchmark score place it well above Intel's 77th percentile and 25362 average.

The Intel Core 5 120 wins only the two Cinebench single-core tests: R15 single-core (259 vs 215) and R23 single-core (2577 vs 2038). It also matches the AMD chip nearly exactly in Cinebench R23 multicore (18255 vs 18316), though it does not win that test. Intel's 18 MB L3 cache, higher base clock, and desktop-oriented 65 watt design give it a per-core rendering edge, but the data shows this advantage does not extend to the broader PassMark suite. The AMD chip's 8 cores, 16 threads, 4 nm process, and 28 watt TDP make it the dominant choice for data-heavy, multithreaded, and efficiency-sensitive scenarios.