Intel Core 5 320 vs Intel Core Ultra 9 285 Comparison

Head-to-Head Benchmarks

The benchmark data shows a decisive sweep: the Intel Core Ultra 9 285 wins all 17 recorded head-to-head tests against the Intel Core 5 320. The largest margin appears in Cinebench R23 multi-core, where the Ultra 9 scores 48,945 against 6,197, a delta of -87.3% from the Core 5's perspective. That means the Core 5 320 delivers roughly one-eighth of the multi-threaded rendering throughput. The gap is similarly wide in PassMark integer math, with the Ultra 9 at 164,869 versus 32,323, a -80.4% delta, indicating the desktop part processes arithmetic workloads over five times faster.

Single-core performance tells a closer story, though the Ultra 9 still leads clearly. In PassMark single-thread, the Ultra 9 scores 4,881 against 4,045, a -17.1% delta, the smallest margin in the entire set. Cinebench R23 single-core shows a wider split: 6,909 versus 1,926, a -72.1% delta. This suggests the Core 5 320's low-power design limits its peak frequency-driven performance, while the Ultra 9's higher boost clock and desktop power envelope sustain much stronger per-thread output.

Intermediate multi-threaded workloads show consistent gaps. Cinebench R20 multi-core has the Ultra 9 at 20,556 versus 5,462, a -73.4% delta. PassMark multi-thread shows 56,602 versus 15,450, a -72.7% delta. PassMark physics, which often reflects real-world simulation tasks, shows 3,598 versus 1,221, a -66.1% delta. Data compression favors the Ultra 9 heavily: 602,121 versus 148,779, a -75.3% delta. Encryption follows at 46,949 versus 10,984, a -76.6% delta. Extended instructions, a measure of SIMD and specialized operations, shows 45,357 versus 13,262, a -70.8% delta.

The pattern is uniform: the Ultra 9 leads by roughly 3x to 5x in most workloads, with the single-thread PassMark test being the only exception at under 1.2x. The Core 5 320 posts no wins in any measured category, so the data offers no bright spot for the mobile chip in raw performance terms.

FAQ

Q: Which processor has the higher average benchmark score?

A: The Intel Core Ultra 9 285 records an average benchmark score of 75,488, while the Intel Core 5 320 averages 18,023. The Ultra 9 also sits at the 95th percentile among all CPUs, compared to the Core 5's 72nd percentile.

Q: How do the two compare in multi-threaded Cinebench R23?

A: The Ultra 9 scores 48,945, while the Core 5 320 scores 6,197. The delta is -87.3%, meaning the Core 5 delivers only about 12.7% of the Ultra 9's multi-core rendering score.

Q: Is the single-thread performance gap smaller than the multi-thread gap?

A: In PassMark single-thread, yes. The Ultra 9 scores 4,881 and the Core 5 scores 4,045, a -17.1% delta. However, in Cinebench R23 single-core, the gap is much larger at -72.1%, with scores of 6,909 and 1,926 respectively.

Q: What do the nearest rivals suggest about each chip's market position?

A: The Core 5 320 sits near the AMD Ryzen 5 1600 (0.2% delta), Intel Core 5 120U (0.7% delta), Intel Core i5-1334U (-0.7% delta), and AMD Ryzen 5 3600XT (0.7% delta). The Ultra 9 285 competes with server and high-end desktop parts: AMD EPYC 8224P (-0.1% delta), AMD EPYC 4545P (0.2% delta), AMD Ryzen 7 PRO 9755X3D (-0.3% delta), and AMD Ryzen 7 PRO 9755 (-0.3% delta).

Q: Which chip supports ECC memory?

A: The Intel Core Ultra 9 285 supports ECC memory. The Intel Core 5 320 does not.

Q: What are the socket requirements for each?

A: The Core 5 320 uses Intel BGA 1516, a soldered mobile socket. The Ultra 9 285 uses Intel Socket 1851, a desktop LGA socket.

Architecture Differences

The two processors represent fundamentally different design points. The Core 5 320, codenamed Wildcat Lake, is built on a 3 nm process at Intel's own foundry. The Ultra 9 285, codenamed Arrow Lake-S, also uses a 3 nm node but is fabricated by TSMC. The Ultra 9's die contains 17,800 million transistors on a 243 mm² die, while the Core 5's transistor count and die size are not recorded in the database.

Core counts diverge sharply. The Core 5 320 has 6 cores and 6 threads, meaning no hyper-threading. The Ultra 9 285 has 24 cores and 24 threads, also without hyper-threading, but with four times the physical cores. Cache hierarchies differ accordingly. The Core 5 has a 192 KB L1, 2.5 MB L2, and 6 MB shared L3. The Ultra 9 has 192 KB L1 per core, 3 MB L2 per core, and 36 MB shared L3. The Ultra 9's L3 is six times larger, which matters for workloads with large working sets.

Memory architecture is a major differentiator. The Core 5 320 supports DDR5 and LPDDR5X over a single-channel bus with 59.7 GB/s bandwidth. The Ultra 9 285 supports DDR5 over a dual-channel bus with 102.4 GB/s bandwidth, nearly double the memory throughput. The Ultra 9 also adds ECC memory support, which the Core 5 lacks.

PCIe connectivity differs by generation and lane count. The Core 5 provides Gen 4 with 6 lanes from the CPU. The Ultra 9 provides Gen 5 with 20 lanes from the CPU, which enables faster storage and expansion options. Integrated graphics also differ: the Core 5 uses Intel Xe3 Graphics with 2 Xe cores, while the Ultra 9 uses Arc Xe-LPG Graphics with 64EU. The Ultra 9's GPU is clearly more capable for display and compute tasks, though neither is a discrete-class solution.

Market positioning reinforces the architectural split. The Core 5 320 is a mobile part with a 15 W TDP, soldered to the board. The Ultra 9 285 is a desktop part with a 65 W TDP, seated in a socket. The release dates differ by over a year: the Ultra 9 launched at the end of 2024, while the Core 5 launched in April 2026.

Specification Differences

The recorded specifications show a clear separation between the two SKUs.

• Cores: 6 (Core 5 320) vs 24 (Ultra 9 285)
• Threads: 6 vs 24
• Base clock: 1.50 GHz vs 2.50 GHz
• Boost clock: 4.60 GHz vs 5.60 GHz
• TDP: 15 W vs 65 W
• Socket: Intel BGA 1516 vs Intel Socket 1851
• Process node: 3 nm (Intel foundry) vs 3 nm (TSMC foundry)
• L1 cache: 192 KB vs 192 KB per core
• L2 cache: 2.5 MB total vs 3 MB per core
• L3 cache: 6 MB shared vs 36 MB shared
• Memory support: DDR5, LPDDR5X vs DDR5 only
• Memory bus: Single-channel vs Dual-channel
• Memory bandwidth: 59.7 GB/s vs 102.4 GB/s
• ECC memory: No vs Yes
• PCIe: Gen 4, 6 lanes vs Gen 5, 20 lanes
• Integrated graphics: Intel Xe3 (2 Xe) vs Arc Xe-LPG (64EU)
• Market segment: Mobile vs Desktop
• Launch MSRP: $340 vs $579
• Release date: 2026-04-15 vs 2024-12-31

The Ultra 9 leads in every performance-relevant specification except power consumption, where the Core 5's 15 W TDP is a clear advantage for battery-driven systems. The Core 5's memory support includes LPDDR5X, which suits low-power mobile designs, but the single-channel bus limits bandwidth.

The Verdict

The data supports a straightforward conclusion: choose the Intel Core Ultra 9 285 for any workload where performance matters. It wins all 17 head-to-head tests, holds a 95th percentile ranking among all CPUs, and delivers a 75,488 average benchmark score. The Core 5 320, with a 72nd percentile and 18,023 average, is a capable low-power mobile part, but it cannot compete with the Ultra 9 in any measured category.

The Core 5 320's only advantage is its 15 W TDP and mobile form factor. It is designed for thin laptops where battery life and thermals take priority over raw throughput. Its nearest rivals include older desktop parts like the Ryzen 5 1600 and Ryzen 5 3600XT, which have similar average scores, indicating the Core 5 performs at the level of a mid-range previous-generation desktop chip despite being a modern mobile part.

The Ultra 9 285, by contrast, sits among server-class EPYC processors and high-end Ryzen PRO parts in its nearest rival list. It is a desktop workstation chip with ECC memory support, 20 Gen 5 PCIe lanes, and 36 MB of L3 cache. The launch MSRP gap, $340 versus $579, reflects the different market tiers, but the benchmark gap is far larger than the price gap suggests.

For a desktop builder or professional user, the Ultra 9 285 is the obvious pick. For a laptop buyer focused on portability and efficiency, the Core 5 320 serves a purpose, but the data shows no performance scenario where it wins.

Where Each One Wins

Intel Core Ultra 9 285:

The Ultra 9 wins every recorded benchmark. Its largest margins come in multi-threaded rendering and compute-heavy tasks. Cinebench R23 multi-core shows a -87.3% delta, the biggest gap of any test. PassMark integer math shows -80.4%, floating point math shows -78.2%, and data compression shows -75.3%. It also leads decisively in Cinebench R15 multi-core (-78.6%), R20 multi-core (-73.4%), and PassMark multi-thread (-72.7%). For encryption, extended instructions, prime number finding, random string sorting, and physics, the deltas range from -66.1% to -76.6%. Even in single-thread tests, it leads, with the smallest margin being -17.1% in PassMark single-thread.

Intel Core 5 320:

The Core 5 does not win a single recorded benchmark. Its relative strength appears only in PassMark single-thread, where the -17.1% delta is the closest margin. This indicates the mobile chip's boost clock of 4.60 GHz provides decent per-thread performance for light tasks. Its 15 W TDP and single-channel memory support make it suitable for battery-powered devices, but the database contains no performance test where it outperforms the Ultra 9.

The use-case split is clear: the Ultra 9 is for desktops and heavy workloads, the Core 5 is for mobile systems where the 15 W power draw and BGA socket are the deciding factors. In every measured metric, the Ultra 9 delivers more than three times the performance, and in many cases over five times. The Core 5 320 exists to fill a low-power niche, not to challenge desktop flagship parts.