Intel Core Ultra 5 245K vs Intel Core Ultra 9 285 Comparison

Head-to-Head Benchmarks

The benchmark data is unambiguous: the Intel Core Ultra 9 285 wins every single recorded test against the Intel Core Ultra 5 245K, 17 wins to 0. The most dramatic margin appears in Cinebench R23 multi-core, where the Ultra 9 285 scores 48,945 versus 25,066 for the Ultra 5 245K, a 48.8% advantage. That is nearly double the multi-threaded rendering performance, a decisive gap for workloads that scale across cores.

Single-core performance tells a similar story, though with a different shape. In Cinebench R23 single-core, the Ultra 9 285 records 6,909 against 2,132, a 69.1% lead. This is the largest relative difference in the entire benchmark set, indicating that the Ultra 9 285 does not merely add cores, it delivers substantially higher performance per thread. The Cinebench R15 single-core result reinforces this: 696 versus 322, a 53.7% deficit for the Ultra 5 245K.

The Cinebench R20 results show consistent margins. Multi-core scores are 20,556 for the Ultra 9 285 versus 15,368 for the Ultra 5 245K, a 25.2% difference. Single-core scores are 2,901 versus 2,169, also a 25.2% difference. The symmetry of these two deltas suggests a uniform architectural efficiency advantage, not just a core-count effect.

PassMark results follow the same pattern. The largest PassMark margin is in integer math: 164,869 versus 98,524, a 40.2% lead for the Ultra 9 285. Floating-point math shows a 33% gap (194,988 versus 130,678). Data compression favors the Ultra 9 285 by 23.8% (602,121 versus 458,817), while data encryption shows a 29.1% advantage (46,949 versus 33,286). Extended instructions, a proxy for SIMD and vectorized workloads, show a 17.1% lead (45,357 versus 37,617).

The smallest recorded margin is in PassMark single-thread: 4,881 versus 4,714, a 3.4% difference. This is the only test where the two processors are close, suggesting that lightly threaded, single-core tasks see only a modest advantage for the Ultra 9 285. The physics test shows a 14.4% gap (3,598 versus 3,081), while prime number finding shows a 9.8% difference (459 versus 414). Random string sorting is 25.2% apart (73,651 versus 55,098), matching the Cinebench R20 margins.

Multithreaded PassMark performance is 56,602 versus 43,047, a 23.9% lead. The overall average benchmark score in the database is 75,488 for the Ultra 9 285 versus 54,053 for the Ultra 5 245K, placing the Ultra 9 285 at the 95th percentile of all CPUs versus the 91st percentile for the Ultra 5 245K. The nearest rivals for the Ultra 9 285 include AMD EPYC 8224P (0.1% lower), AMD EPYC 4545P (0.2% higher), and AMD Ryzen 7 PRO 9755X3D (0.3% lower). The Ultra 5 245K sits near Intel Xeon 6505P (0.7% higher), Intel Core i7-14700F (0.8% higher), and AMD Ryzen 9 9900X3D (1.3% lower).

Architecture Differences

Both processors share the same fundamental design. They belong to the Core Ultra Series 2, use the Arrow Lake architecture with the Arrow Lake-S codename, and are fabricated on a 3 nm process node at TSMC. Both use the Intel Socket 1851, support dual-channel DDR5 memory with 102.4 GB/s bandwidth, and include ECC memory support. The integrated graphics are identical: Arc Xe-LPG Graphics with 64 execution units.

The core counts differ substantially. The Ultra 5 245K has 14 cores and 14 threads, while the Ultra 9 285 has 24 cores and 24 threads. Neither processor supports hyperthreading, so thread count equals core count in both cases. The cache hierarchy also diverges. L1 cache is 192 KB per core for both, and L2 is 3 MB per core for both, but the shared L3 cache is 24 MB on the Ultra 5 245K versus 36 MB on the Ultra 9 285, a 50% increase in last-level cache capacity.

Clock speeds show an interesting inversion. The Ultra 5 245K has a base clock of 4.20 GHz, significantly higher than the 2.50 GHz base clock of the Ultra 9 285. However, the boost clock favors the Ultra 9 285 at 5.60 GHz versus 5.20 GHz. This means the Ultra 5 245K starts at a higher frequency but has a lower ceiling, while the Ultra 9 285 relies on a wider frequency range and more cores. The thermal design power also differs: the Ultra 5 245K is rated at 125 W, while the Ultra 9 285 is rated at 65 W, a notable inversion given the latter has more cores and higher boost clocks.

The multiplier is unlocked on the Ultra 5 245K but locked on the Ultra 9 285, giving the lower-tier chip manual overclocking flexibility that the flagship lacks. Both use the same PCIe configuration: Gen 5 with 20 lanes from the CPU. Both have a transistor count of 17,800 million and a die size of 243 mm², confirming they are the same physical silicon with different binning and configurations. The release dates differ, with the Ultra 5 245K launching on 2024-10-23 and the Ultra 9 285 launching later on 2024-12-31.

FAQ

Q: Which processor has more cores?

A: The Intel Core Ultra 9 285 has 24 cores and 24 threads, while the Intel Core Ultra 5 245K has 14 cores and 14 threads. Neither supports hyperthreading, so thread counts equal core counts.

Q: Is the single-core performance gap as large as the multi-core gap?

A: In some tests, the single-core gap is actually larger. Cinebench R23 single-core shows a 69.1% lead for the Ultra 9 285, while multi-core shows a 48.8% lead. However, PassMark single-thread shows only a 3.4% difference, indicating that the margin varies heavily by workload.

Q: Do both processors use the same manufacturing process?

A: Yes, both use a 3 nm process node at TSMC, with 17,800 million transistors and a 243 mm² die size. They share the same Arrow Lake-S silicon.

Q: What is the L3 cache difference?

A: The Ultra 9 285 has 36 MB of shared L3 cache, while the Ultra 5 245K has 24 MB. L1 and L2 caches are identical at 192 KB per core and 3 MB per core, respectively.

Q: Which processor has a higher base clock?

A: The Ultra 5 245K has a higher base clock of 4.20 GHz, compared to 2.50 GHz for the Ultra 9 285. However, the Ultra 9 285 has a higher boost clock of 5.60 GHz versus 5.20 GHz.

Q: Can either processor be overclocked?

A: The Ultra 5 245K has an unlocked multiplier, while the Ultra 9 285 does not. Both support the Intel Socket 1851 and use the same DDR5 dual-channel memory interface.

Specification Differences

The two processors differ in the following recorded specifications:

• Cores: 14 (Ultra 5 245K) versus 24 (Ultra 9 285)
• Threads: 14 versus 24
• Base clock: 4.20 GHz versus 2.50 GHz
• Boost clock: 5.20 GHz versus 5.60 GHz
• TDP: 125 W versus 65 W
• L3 cache: 24 MB shared versus 36 MB shared
• Multiplier: Unlocked versus locked
• Part number: SRQCT versus SRQD4
• Release date: 2024-10-23 versus 2024-12-31
• Launch MSRP: $319 versus $579
• Percentile vs all CPUs: 91 versus 95
• Average benchmark score: 54,053 versus 75,488

Identical specifications include the 3 nm process node, TSMC foundry, transistor count (17,800 million), die size (243 mm²), L1 cache (192 KB per core), L2 cache (3 MB per core), memory support (DDR5 dual-channel), memory bandwidth (102.4 GB/s), ECC support, PCIe configuration (Gen 5, 20 lanes), integrated graphics (Arc Xe-LPG 64EU), socket (Intel Socket 1851), architecture (Arrow Lake), and market segment (Desktop).

The Verdict

The recorded data shows a clear hierarchy. The Intel Core Ultra 9 285 outperforms the Intel Core Ultra 5 245K in every one of the 17 head-to-head benchmarks, with no exceptions. The average benchmark score is 75,488 versus 54,053, a 39.7% overall advantage. The Ultra 9 285 reaches the 95th percentile of all CPUs, while the Ultra 5 245K sits at the 91st percentile.

For workloads that stress multi-core rendering, the choice is obvious. The Cinebench R23 multi-core score of 48,945 versus 25,066 represents a 48.8% advantage, and the R15 multi-core result (4,933 versus 3,850) confirms the pattern. For integer-heavy tasks, the 40.2% lead in PassMark integer math (164,869 versus 98,524) makes the Ultra 9 285 the stronger option. Data compression, encryption, and floating-point math all favor the Ultra 9 285 by margins between 17.1% and 33%.

The only area where the gap narrows is single-threaded PassMark performance, where the Ultra 9 285 leads by just 3.4% (4,881 versus 4,714). This suggests that for strictly single-threaded, low-complexity tasks, the two processors are nearly equivalent. However, even in that test, the Ultra 9 285 wins.

The Ultra 5 245K does offer a higher base clock (4.20 GHz versus 2.50 GHz) and an unlocked multiplier, which may matter for users who prioritize manual overclocking. Its 125 W TDP rating is higher than the 65 W rating of the Ultra 9 285, which is counterintuitive given the latter has more cores. But the benchmark results do not show any workload category where the Ultra 5 245K takes a lead.

Where Each One Wins

The Intel Core Ultra 9 285 wins in every measured category. There is no benchmark in the database where the Ultra 5 245K records a higher score. The closest contest is PassMark single-thread, where the Ultra 9 285 leads by only 3.4%, making that the least decisive victory. The largest victory is Cinebench R23 single-core, with a 69.1% margin.

For users who prioritize single-core responsiveness in lightly threaded applications, the Ultra 9 285 still holds the edge, though the margin is modest in PassMark terms. For multi-core rendering, video encoding, data compression, encryption, and scientific computing, the Ultra 9 285 delivers substantially higher throughput, with most margins falling between 20% and 50%.

The Ultra 5 245K may appeal to users who require the unlocked multiplier for overclocking headroom, as the Ultra 9 285 lacks that feature. The higher base clock of the Ultra 5 245K (4.20 GHz) could also provide consistent performance at lower loads without relying on boost behavior. However, based strictly on the benchmark scores, the Ultra 9 285 is the superior processor in every recorded test, with an average score advantage of 39.7% and a higher percentile ranking among all CPUs.