Intel Core Ultra 7 265 vs Intel Core Ultra X9 378H Comparison

Head-to-Head Benchmarks

The benchmark data records 17 head-to-head comparisons between the Intel Core Ultra 7 265 and the Intel Core Ultra X9 378H. The Core Ultra 7 265 wins 14 of those tests, while the Core Ultra X9 378H wins 3. The average benchmark score tells the same story: 64,640 for the Core Ultra 7 265 versus 47,468 for the Core Ultra X9 378H, a gap of roughly 36 percent.

The most decisive victories for the Core Ultra 7 265 come in compute-heavy workloads. In PassMark floating point math, it scores 172,776 against 114,500, a delta of 50.9 percent. Integer math shows a 45.5 percent advantage, with 134,773 versus 92,603. Data encryption favors the desktop part by 35.6 percent (40,456 versus 29,840), and data compression by 35.3 percent (522,983 versus 386,591). Random string sorting delivers a 43 percent lead for the Core Ultra 7 265, at 63,833 versus 44,648.

CineBench results are split by generation of the test. In CineBench R15, the Core Ultra 7 265 leads by 29.7 percent in multicore (4,255 versus 3,281) and by 29.9 percent in singlecore (600 versus 462). CineBench R23 shows the same pattern, with the Core Ultra 7 265 ahead by 29.7 percent in both multicore (42,216 versus 32,553) and singlecore (5,960 versus 4,595). However, CineBench R20 reverses the result dramatically. The Core Ultra X9 378H scores 13,672 in multicore versus 6,268 for the Core Ultra 7 265, a 54.2 percent swing. Singlecore R20 also favors the mobile part, 1,929 versus 884, again a 54.2 percent delta. This inconsistency across CineBench versions suggests workload scaling differences that favor the newer Panther Lake architecture in that specific test version.

PassMark multithread confirms the general trend, with the Core Ultra 7 265 ahead by 29.7 percent (49,682 versus 38,298). Extended instructions give the desktop chip a 32.5 percent edge (41,478 versus 31,315). Prime number finding shows a narrower 17.1 percent advantage for the Core Ultra 7 265 (418 versus 357). Single-thread PassMark is close, only 5.3 percent apart, with 4,689 versus 4,453 favoring the Core Ultra 7 265.

The Core Ultra X9 378H takes three wins. Besides the two CineBench R20 results, it wins PassMark physics by 14.1 percent, scoring 3,404 versus 2,923. That physics result is notable because it is the only PassMark test where the mobile chip outperforms the desktop chip, and it suggests the Panther Lake architecture handles certain simulation workloads more efficiently.

Architecture Differences

The two processors come from different Intel generations. The Core Ultra 7 265 uses Arrow Lake-S, part of Core Ultra Series 2, built on a 3 nm process by TSMC. It packs 17,800 million transistors on a 243 mm² die. The Core Ultra X9 378H uses Panther Lake-H, part of Core Ultra Series 3, also on a 3 nm process but manufactured by Intel's own foundry. The database does not record transistor count or die size for the mobile part.

Core configuration differs significantly. The Core Ultra 7 265 has 20 cores and 20 threads, all physical with no hyperthreading overhead. The Core Ultra X9 378H has 16 cores and 16 threads. Both use a per-core L1 cache of 192 KB. L2 cache is 3 MB per core on the desktop chip versus 2.5 MB per core on the mobile chip. L3 cache is 30 MB shared on the Core Ultra 7 265 versus 18 MB shared on the Core Ultra X9 378H.

Clock speeds favor the desktop part. The Core Ultra 7 265 runs a 2.40 GHz base clock with a 5.30 GHz boost. The Core Ultra X9 378H has a 2.00 GHz base and 5.00 GHz boost. Power draw is heavily skewed toward the desktop chip, with a 65 W TDP versus 25 W for the mobile part.

Memory support separates the two clearly. The Core Ultra 7 265 uses DDR5 with dual-channel memory and a recorded bandwidth of 102.4 GB/s. The Core Ultra X9 378H uses LPDDR5X, also dual-channel, but with a higher recorded bandwidth of 153.6 GB/s. Neither supports ECC memory.

PCIe lane counts differ substantially. The Core Ultra 7 265 provides Gen 5 with 20 lanes from the CPU. The Core Ultra X9 378H provides Gen 5 with 4 lanes from the CPU. This reflects the desktop part's role in a full tower with expansion cards versus the mobile part's integrated system design.

Integrated graphics also differ. The Core Ultra 7 265 carries Arc Xe-LPG Graphics with 32 execution units. The Core Ultra X9 378H carries Arc B390, a newer generation part. The database does not list execution unit counts for the mobile GPU.

Where Each One Wins

The Core Ultra 7 265 dominates in almost every recorded benchmark category. Its wins span CineBench R15 and R23, PassMark compression, encryption, extended instructions, prime finding, floating point, integer math, multithread, random string sorting, and single-thread tests. This makes it the stronger choice for general desktop productivity, content creation, and heavily threaded workloads where the extra 4 cores and 12 MB of L3 cache provide a measurable advantage.

The Core Ultra X9 378H wins in CineBench R20 both multicore and singlecore, plus PassMark physics. The R20 results indicate that the Panther Lake architecture can deliver higher per-thread performance in certain synthetic rendering loads despite lower clock speeds. The physics win suggests the mobile chip's architecture handles particle or constraint simulations more efficiently per watt. However, these wins are isolated. The Core Ultra X9 378H also sits in the 89th percentile of all CPUs, while the Core Ultra 7 265 sits in the 93rd percentile, so the overall performance ceiling clearly belongs to the desktop part.

For a desktop system with access to a 65 W power budget, the Core Ultra 7 265 is the obvious choice across the recorded metrics. For a mobile platform where power draw matters and the integrated GPU needs to be more modern, the Core Ultra X9 378H offers a different tradeoff, but the benchmark data does not show it as a general performance winner.

Specification Differences

| Specification | Intel Core Ultra 7 265 | Intel Core Ultra X9 378H |

|---|---|---|

| Series | Core Ultra Series 2 | Core Ultra Series 3 |

| Cores | 20 | 16 |

| Threads | 20 | 16 |

| Base clock | 2.40 GHz | 2.00 GHz |

| Boost clock | 5.30 GHz | 5.00 GHz |

| TDP | 65 W | 25 W |

| Socket | Intel Socket 1851 | Intel BGA 2540 |

| Codename | Arrow Lake-S | Panther Lake |

| Foundry | TSMC | Intel |

| L2 cache | 3 MB (per core) | 2.5 MB (per core) |

| L3 cache | 30 MB (shared) | 18 MB (shared) |

| Memory support | DDR5 | LPDDR5X |

| Memory bandwidth | 102.4 GB/s | 153.6 GB/s |

| PCIe | Gen 5, 20 Lanes (CPU only) | Gen 5, 4 Lanes (CPU only) |

| Integrated graphics | Arc Xe-LPG Graphics 32EU | Arc B390 |

| Market segment | Desktop | Mobile |

| Release date | 2025-01-06 | 2026-04-03 |

| Launch MSRP | $394 | Not recorded |

The transistor count, die size, and part number for the Core Ultra X9 378H are not recorded in the database. Both processors have 192 KB of L1 cache per core, both are dual-channel, and neither supports ECC memory. Both use a 3 nm process node. Neither has an unlocked multiplier.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 7 265 has 20 cores and 20 threads. The Intel Core Ultra X9 378H has 16 cores and 16 threads.

Q: How much faster is the Core Ultra 7 265 in PassMark floating point math?

A: The Core Ultra 7 265 scores 172,776 versus 114,500 for the Core Ultra X9 378H, a 50.9 percent advantage.

Q: Why does the Core Ultra X9 378H win in CineBench R20?

A: The Core Ultra X9 378H scores 13,672 in R20 multicore versus 6,268 for the Core Ultra 7 265, a 54.2 percent swing. The singlecore R20 result is 1,929 versus 884, also a 54.2 percent swing. This indicates workload-specific scaling differences in that test version.

Q: Which processor has higher memory bandwidth?

A: The Core Ultra X9 378H has a recorded memory bandwidth of 153.6 GB/s with LPDDR5X. The Core Ultra 7 265 has 102.4 GB/s with DDR5.

Q: What is the TDP difference?

A: The Core Ultra 7 265 has a TDP of 65 W. The Core Ultra X9 378H has a TDP of 25 W.

Q: How do the two compare in PassMark physics?

A: The Core Ultra X9 378H wins that test, scoring 3,404 versus 2,923 for the Core Ultra 7 265, a 14.1 percent advantage.

The Verdict

The recorded data points to the Intel Core Ultra 7 265 as the stronger processor for almost all measured workloads. It wins 14 of 17 head-to-head tests, holds a 93rd percentile ranking against all CPUs versus 89th for the mobile part, and delivers leads of 30 to 50 percent across most PassMark categories. Its higher core count, larger L3 cache, and higher clock speeds translate into broad performance advantages in the database's recorded benchmarks.

The Intel Core Ultra X9 378H is not without merit. It wins CineBench R20 in both multicore and singlecore by a wide margin, and it wins PassMark physics. Its memory bandwidth is 50 percent higher, and its TDP is far lower. For a mobile system where power efficiency and a modern integrated GPU matter, the Panther Lake part has clear appeal. The Arc B390 graphics are a newer generation than the Arc Xe-LPG 32EU on the desktop chip.

But the benchmark database does not record any scenario where the Core Ultra X9 378H overtakes the Core Ultra 7 265 in overall average score. The desktop chip's 64,640 average versus 47,468 is decisive. Buyers building a desktop system with a 65 W power budget should choose the Core Ultra 7 265. Buyers constrained to a mobile platform with 25 W TDP and needing the newer integrated GPU should choose the Core Ultra X9 378H, accepting lower performance in most recorded tests but gaining the R20 and physics wins.