AMD Ryzen AI 7 345 vs Intel Core 5 120 Comparison

FAQ

Q: Which processor has the higher average benchmark score?

A: The AMD Ryzen AI 7 345 has an average benchmark score of 29,461, while the Intel Core 5 120 scores 25,362. The AMD part sits at the 81st percentile of all CPUs, with the Intel part at the 77th percentile.

Q: How does the AMD Ryzen AI 7 345 compare to its nearest rivals?

A: The database places the AMD chip within 0.7% of the AMD Ryzen 7 3800X (29,447), the AMD EPYC 9654 (29,409), and the Intel Core i5-13500HX (29,270). It trails the AMD Ryzen 7 PRO 5755GE by 0.7% (29,656).

Q: What are the core and thread counts for both processors?

A: Both processors use 6 cores and 12 threads. The AMD Ryzen AI 7 345 is a mobile part, while the Intel Core 5 120 is a desktop part.

Q: Which processor wins in single-thread performance?

A: The AMD Ryzen AI 7 345 wins the Cinebench R15 single-core test (271 vs 259, a 4.6% lead) and the PassMark single-thread test (3,875 vs 3,595, a 7.8% lead). However, the Intel Core 5 120 wins Cinebench R23 single-core (2,577 vs 1,818, a 29.5% lead).

Q: What is the launch MSRP of the Intel Core 5 120?

A: The launch MSRP is $211. The AMD Ryzen AI 7 345 has no launch MSRP listed in the database.

Q: Which processor has the higher boost clock?

A: The AMD Ryzen AI 7 345 has a boost clock of 4.60 GHz, while the Intel Core 5 120 boosts to 4.50 GHz. The Intel part has a higher base clock at 2.50 GHz versus 2.00 GHz.

Where Each One Wins

The AMD Ryzen AI 7 345 takes 9 of the 15 head-to-head benchmark comparisons. Its wins cluster around data manipulation and integer workloads. The PassMark data compression test shows a 8.2% lead (237,484 vs 219,535), and data encryption comes in 6.1% ahead (11,814 vs 11,131). Extended instructions deliver a 19.2% advantage (17,003 vs 14,264), and random string sorting is 18.3% faster (25,435 vs 21,499). Integer math wins by 5% (63,475 vs 60,462), and the PassMark multithread score is 7.2% higher (19,927 vs 18,597). The AMD chip also leads single-thread PassMark by 7.8% (3,875 vs 3,595) and Cinebench R15 single-core by 4.6% (271 vs 259).

The Intel Core 5 120 wins 6 comparisons, and its victories are concentrated in rendering and physics workloads. The Cinebench R23 multicore test shows a massive 37.2% lead (18,255 vs 11,461), and R23 single-core is 29.5% ahead (2,577 vs 1,818). Cinebench R15 multicore goes to Intel by 7% (1,840 vs 1,712). PassMark physics favors Intel by 18.3% (1,333 vs 1,089), and find prime numbers shows a 19.5% edge (77 vs 62). Floating point math is 6.1% higher (45,383 vs 42,621).

The split is clean: AMD wins nearly every memory-bandwidth-sensitive and integer-heavy task, while Intel dominates Cinebench rendering and physics simulation. The AMD part is better for compression, encryption, sorting, and general multithreaded system responsiveness. The Intel part is the stronger choice for 3D rendering, prime-number sieving, and physics calculations.

Architecture Differences

The AMD Ryzen AI 7 345 uses the Krackan Point codename and belongs to the Ryzen AI 300 generation built on Zen 5 and Zen 5c cores. It is manufactured on a 4 nm process at TSMC. The Intel Core 5 120 uses the Raptor Lake architecture with the Raptor Lake-R codename, part of the Core 5 generation (Raptor Lake Refresh). Intel fabricates this chip on a 10 nm process at its own foundry.

Cache layouts differ substantially. The AMD part has 80 KB of L1 per core and 1 MB of L2 per core, with only 4 MB of L3 cache. The Intel part also has 80 KB of L1 per core but a larger 1.25 MB of L2 per core and 18 MB of shared L3 cache. The Intel die size is 163 mm², while the AMD die size is not recorded in the database.

Memory support diverges as well. The AMD chip supports DDR5 and LPDDR5X with dual-channel memory, while the Intel chip supports DDR4 and DDR5 with dual-channel memory. The AMD part lists memory bandwidth at 89.6 GB/s, but the Intel part has no bandwidth figure recorded. Neither processor supports ECC memory.

PCIe connectivity differs. The AMD Ryzen AI 7 345 provides Gen 4 with 14 lanes (CPU only), while the Intel Core 5 120 provides Gen 5 with 16 lanes (CPU only). The integrated graphics also differ: AMD uses the Radeon 840M, while Intel uses UHD Graphics 730.

The market segments reflect the intended use: AMD positions the Ryzen AI 7 345 as a mobile processor on AMD Socket FP8, while Intel positions the Core 5 120 as a desktop processor on Intel Socket 1700. The production status for both is active.

Specification Differences

The base clock differs: AMD runs at 2.00 GHz, Intel at 2.50 GHz. Boost clocks are close, with AMD at 4.60 GHz and Intel at 4.50 GHz. Thermal design power shows a wide gap: the AMD part is rated at 28 W, while the Intel part is rated at 65 W.

Process node: AMD uses 4 nm from TSMC, Intel uses 10 nm from Intel. The Intel die is 163 mm²; AMD has no recorded die size.

L2 cache per core: AMD has 1 MB, Intel has 1.25 MB. L3 cache: AMD has 4 MB, Intel has 18 MB shared.

Memory support: AMD accepts DDR5 and LPDDR5X, Intel accepts DDR4 and DDR5. Memory bandwidth: AMD records 89.6 GB/s, Intel records none.

PCIe: AMD is Gen 4 with 14 lanes, Intel is Gen 5 with 16 lanes.

Integrated graphics: AMD Radeon 840M versus Intel UHD Graphics 730.

Socket: AMD Socket FP8 versus Intel Socket 1700.

Release dates: AMD launched on 2025-01-14, Intel on 2025-07-30. The Intel part has a launch MSRP of $211; AMD has none listed. Part numbers are 100-000002122 for AMD and SA35V for Intel.

Head-to-Head Benchmarks

The largest single win in the entire comparison belongs to the Intel Core 5 120 in Cinebench R23 multicore. Intel scores 18,255 against AMD's 11,461, a 37.2% advantage. This result aligns with the Intel chip's larger 18 MB L3 cache and higher 65 W TDP, which allow sustained multi-threaded rendering performance. The same pattern appears in Cinebench R23 single-core, where Intel leads 2,577 to 1,818, a 29.5% margin.

Cinebench R15 shows a different split. Intel wins multicore by 7% (1,840 vs 1,712), but AMD wins single-core by 4.6% (271 vs 259). This suggests the AMD architecture has a stronger single-core showing in the older R15 test, while the newer R23 test favors Intel's higher clock speed and larger cache.

PassMark physics goes to Intel by 18.3% (1,333 vs 1,089), and find prime numbers also favors Intel by 19.5% (77 vs 62). These results indicate Intel's integer-heavy scalar execution is strong in specific algorithmic workloads.

AMD's biggest wins come in extended instructions and random string sorting, each at 19.2% and 18.3% respectively. The extended instructions score of 17,003 versus 14,264 shows AMD's newer Zen 5 cores handle advanced instruction sets more efficiently. Random string sorting (25,435 vs 21,499) points to better memory access patterns for the AMD chip despite its smaller L3 cache.

Data compression gives AMD an 8.2% lead (237,484 vs 219,535), and data encryption follows at 6.1% (11,814 vs 11,131). Integer math goes to AMD by 5% (63,475 vs 60,462). The PassMark multithread score favors AMD by 7.2% (19,927 vs 18,597), indicating the overall throughput of the AMD chip is higher across mixed workloads.

PassMark single-thread shows AMD ahead by 7.8% (3,875 vs 3,595), which is consistent with the Cinebench R15 single-core result. Floating point math is the only computational test where Intel wins by a smaller margin: 6.1% (45,383 vs 42,621).

The average benchmark scores confirm the AMD chip's overall position: 29,461 versus 25,362, a difference of roughly 16%. The AMD chip ranks at the 81st percentile of all CPUs, while the Intel chip ranks at the 77th percentile. The nearest rivals for AMD include the Ryzen 7 3800X and EPYC 9654, while Intel's nearest rivals include the Ryzen 5 5600X3D and Core i7-11700KF, showing both chips compete at different tiers of the desktop and mobile landscape.