Intel Core Ultra 7 265K vs Intel Core Ultra X7 358H Comparison

The Intel Core Ultra 7 265K and the Intel Core Ultra X7 358H occupy different corners of the performance spectrum, one built for desktop workloads and the other for mobile efficiency. The recorded data shows a clear split: the 265K dominates in nearly every measured category, while the 358H claims a single, narrow victory in one Cinebench test. Their architectural blueprints, from process node to memory support, reinforce this division.

Where Each One Wins

The use-case split is stark, with the Intel Core Ultra 7 265K winning 16 of 17 head-to-head comparisons. Its largest advantages appear in content creation and data-intensive tasks. In Cinebench R23 multicore, the 265K scores 35850 against the 358H's 18747, a 91.2% lead. This pattern repeats across PassMark workloads: data compression shows a 100.2% advantage (665554 vs 332508), and extended instructions show a 99.2% gap (54333 vs 27274). These results indicate a processor built for sustained, heavy parallel workloads.

The Intel Core Ultra X7 358H claims one win: Cinebench R23 singlecore, with a score of 2080 versus 2020, a 2.9% margin. This is the only test where the mobile chip outpaces the desktop part. In other single-thread tests, the 265K remains ahead. PassMark single thread shows the 265K at 4928 versus 4124, a 19.5% advantage. The 358H's single-core strength in one benchmark does not translate into broader single-thread dominance.

For tasks like physics simulation, the 265K leads by 23.5% (3731 vs 3021). Integer math shows a 72.3% gap (143242 vs 83147), and floating point math shows an 82.6% gap (189629 vs 103842). The mobile chip's wins are limited to a single test, indicating that its architecture favors short bursts of single-core activity rather than sustained multithreaded throughput.

Architecture Differences

The two processors diverge at the silicon level. The Intel Core Ultra 7 265K uses the Arrow Lake architecture, also known by the codename Arrow Lake-S, and belongs to the Core Ultra Series 2. It is fabricated on a 3 nm process by TSMC and contains 17,800 million transistors on a 243 mm² die. The Intel Core Ultra X7 358H uses the Panther Lake codename with the Panther Lake-H generation designation, part of the Core Ultra Series 3. It is also on a 3 nm process, but fabricated by Intel rather than TSMC. The database records no transistor count or die size for the 358H.

Core configuration differs significantly. The 265K provides 20 cores and 20 threads, while the 358H provides 16 cores and 16 threads. Neither uses simultaneous multithreading. Cache hierarchies share the same per-core L1 (192 KB per core) and L2 (3 MB per core) allocations, but the shared L3 cache differs: 30 MB on the 265K versus 18 MB on the 358H.

Memory architecture separates the two further. The 265K supports DDR5 memory on a dual-channel bus with a recorded bandwidth of 102.4 GB/s and ECC support. The 358H supports LPDDR5X on a dual-channel bus with a higher recorded bandwidth of 153.6 GB/s but no ECC support. The mobile part uses more bandwidth-efficient memory, though the desktop part offers error correction. PCIe connectivity also differs: the 265K provides Gen 5 with 20 CPU lanes, while the 358H provides Gen 5 with 4 CPU lanes.

The integrated graphics differ as well. The 265K uses Arc Xe-LPG Graphics with 64 execution units, while the 358H uses Arc B390. The 265K has an unlocked multiplier, whereas the 358H is locked. The 265K uses Intel Socket 1851, the 358H uses Intel BGA 2540, reflecting their desktop and mobile placements.

FAQ

Q: Which processor has the higher boost clock?

A: The Intel Core Ultra 7 265K has a boost clock of 5.50 GHz, compared to the Intel Core Ultra X7 358H's 4.80 GHz.

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

A: The Intel Core Ultra 7 265K scores 35850 against the 358H's 18747, a 91.2% advantage for the desktop part.

Q: Does the mobile processor win any benchmark?

A: Yes, the Intel Core Ultra X7 358H wins Cinebench R23 singlecore with a score of 2080 versus 2020, a 2.9% margin.

Q: What is the TDP difference between the two?

A: The Intel Core Ultra 7 265K has a TDP of 125 W, while the Intel Core Ultra X7 358H has a TDP of 25 W.

Q: Which processor supports ECC memory?

A: The Intel Core Ultra 7 265K supports ECC memory; the Intel Core Ultra X7 358H does not.

Q: How much L3 cache does each processor have?

A: The Intel Core Ultra 7 265K has 30 MB of shared L3 cache, while the Intel Core Ultra X7 358H has 18 MB.

Specification Differences

The two processors differ across nearly every major specification category. The 265K has 20 cores and 20 threads, while the 358H has 16 cores and 16 threads. Base clocks are 3.90 GHz for the 265K and 1.90 GHz for the 358H. Boost clocks are 5.50 GHz and 4.80 GHz, respectively. TDP is 125 W for the desktop chip and 25 W for the mobile chip.

Socket types reflect their platforms: Intel Socket 1851 for the 265K, Intel BGA 2540 for the 358H. The 265K uses the Arrow Lake architecture with the codename Arrow Lake-S, while the 358H uses the Panther Lake codename. The 265K is fabricated by TSMC, the 358H by Intel, both on a 3 nm process. The 265K has 17,800 million transistors and a 243 mm² die size; the database records no such figures for the 358H.

L3 cache is 30 MB on the 265K versus 18 MB on the 358H. Memory support is DDR5 for the 265K and LPDDR5X for the 358H. Memory bandwidth is 102.4 GB/s for the 265K and 153.6 GB/s for the 358H. ECC memory is supported on the 265K but not the 358H. PCIe lanes are 20 for the 265K and 4 for the 358H, both Gen 5. Integrated graphics are Arc Xe-LPG 64EU on the 265K and Arc B390 on the 358H. The 265K has an unlocked multiplier; the 358H does not. The 265K has a launch MSRP of $394; the 358H has no recorded launch MSRP.

Head-to-Head Benchmarks

The largest single win for the Intel Core Ultra 7 265K comes in PassMark data compression, where it scores 665554 against 332508, a 100.2% advantage. PassMark random string sorting shows a 97.6% gap (79752 vs 40357). PassMark extended instructions shows 54333 vs 27274, a 99.2% lead. These three tests demonstrate the 265K's strength in data manipulation and instruction-heavy workloads.

Cinebench results follow the same pattern. R15 multicore shows 5020 vs 3027, a 65.8% lead. R20 multicore shows 20918 vs 12011, a 74.2% lead. R23 multicore shows the largest Cinebench gap at 91.2% (35850 vs 18747). Single-core Cinebench results are closer in R23, where the 358H wins 2080 vs 2020, a 2.9% margin. In R15 singlecore, however, the 265K leads by 134.8% (708 vs 301.5), and in R20 singlecore by 74.2% (2953 vs 1695).

PassMark math workloads show consistent 265K advantages. Floating point math: 189629 vs 103842, an 82.6% lead. Integer math: 143242 vs 83147, a 72.3% lead. Prime number finding: 491 vs 337, a 45.7% lead. Data encryption: 48246 vs 26046, an 85.2% lead. Physics: 3731 vs 3021, a 23.5% lead. Multithread: 58594 vs 33802, a 73.3% lead. PassMark single thread: 4928 vs 4124, a 19.5% lead.

The overall averages reflect the gap. The 265K has an average benchmark score of 70879, while the 358H averages 40967. The 265K sits at the 94th percentile among all CPUs, the 358H at the 87th. The 265K's nearest rivals include the Intel Xeon 6511P at 71051 (0.2% higher) and the Intel Core i7-14700KF at 70163 (1% lower). The 358H's nearest rivals include the AMD Ryzen AI 5 PRO 440 at 41208 (0.6% higher) and the Intel Core Ultra 7 356H at 41215 (0.6% higher). The data shows that the 265K competes with high-end desktop and server parts, while the 358H sits among mid-range mobile processors, a full 73% behind the 265K in average score.