AMD Ryzen 5 PRO 6650U vs Intel Core Ultra 7 155U Comparison

Where Each One Wins

The recorded data splits these two mobile processors into distinct usage profiles. The AMD Ryzen 5 PRO 6650U takes 6 of the 15 head-to-head benchmark wins, while the Intel Core Ultra 7 155U takes 9. That raw count, however, hides a clear thematic separation.

The AMD part dominates in data and integer workloads. Its PassMark data compression score of 190180 beats the Intel chip's 177122, a 7.4% margin. Data encryption also goes to AMD, 12159 versus 11333, a 7.3% edge. The largest AMD victory in the entire comparison comes in extended instructions, where the Ryzen scores 12261 against Intel's 9903, a commanding 23.8% advantage. Integer math follows the same pattern, with AMD at 60045 and Intel at 57564, a 4.3% win. Random string sorting also favors AMD, 20299 versus 19767, a 2.7% margin. Even the multithread PassMark test, which is nearly a dead heat, goes to AMD at 16429 versus 16382, a razor-thin 0.3% difference.

The Intel Core Ultra 7 155U, by contrast, wins every Cinebench test and the more physics-oriented PassMark workloads. The largest Intel margins appear in PassMark physics, where Intel scores 1084 against AMD's 837, a 22.8% lead. Floating point math also favors Intel decisively, 40256 versus 32571, a 19.1% gap. In Cinebench R23 multicore, Intel posts 9674.5 against AMD's 8854, an 8.5% advantage. The single-core Cinebench R23 result shows an even larger relative gap, with Intel at 1666 and AMD at 1463, a 12.2% lead. Cinebench R15 multicore and singlecore both go to Intel as well, at 1585 versus 1459.5 (7.9%) and 238.5 versus 232.5 (2.5%), respectively. PassMark single-thread scores also favor Intel, 3372 versus 3149, a 6.6% margin. Prime number finding is the last Intel win, 65 versus 52, a 20% difference.

The practical interpretation is straightforward. For compression, encryption, and integer-heavy code, the AMD Ryzen 5 PRO 6650U is the stronger choice. For rendering, physics simulation, and any workload that scales with floating point throughput or single-core frequency, the Intel Core Ultra 7 155U pulls ahead. The overall average benchmark scores reflect this split: AMD's average is 21874, while Intel's is 21174, a difference that favors AMD by about 3.3% despite Intel winning more individual tests.

Architecture Differences

These two processors come from fundamentally different design philosophies. The AMD Ryzen 5 PRO 6650U uses the Zen 3+ architecture under the Rembrandt codename, built on a 6 nm process at TSMC. It has 6 cores and 12 threads. The Intel Core Ultra 7 155U uses the Meteor Lake architecture, built on a 7 nm process at Intel, with 12 cores and 14 threads. The core count difference is substantial, but the thread count difference is smaller because Intel's hybrid arrangement includes efficiency cores that do not all add threads in the same way.

Cache layouts diverge significantly. AMD provides 64 KB of L1 per core, 512 KB of L2 per core, and 16 MB of shared L3. Intel provides 112 KB of L1 per core, 2 MB of L2 per core, and 12 MB of shared L3. The Intel per-core L2 is four times larger, but AMD's shared L3 is 4 MB larger. The die size for AMD is recorded at 208 mm², while Intel's die size is not recorded in the database.

The integrated graphics differ as well. AMD pairs the CPU with a Radeon 660M. Intel pairs it with Arc Xe-LPG 64EU. Both are integrated solutions, but they belong to different architectural families. Memory support is DDR5 for both, with dual-channel buses. Memory bandwidth differs, with AMD at 76.8 GB/s and Intel at 89.6 GB/s, a 16.7% advantage for Intel. PCIe lane counts also differ: AMD provides Gen 4 with 20 lanes from the CPU, while Intel provides Gen 4 with 12 lanes from the CPU.

The sockets are incompatible. AMD uses Socket FP7, Intel uses BGA 2049. Both are mobile segments and remain in active production. Neither has an unlocked multiplier. AMD's release date is recorded as April 2022, while Intel's is December 2023. The Intel part has a recorded launch MSRP of $490, while AMD's is not recorded.

Process node and foundry choices reflect the different strategies. AMD outsources to TSMC at 6 nm, while Intel uses its own fabs at 7 nm. Neither is a leading-edge node by current standards, but the 6 nm process gives AMD a slight density advantage on paper, partially offset by Intel's larger per-core caches.

FAQ

Q: Which processor has a higher average benchmark score?

A: The AMD Ryzen 5 PRO 6650U has an average benchmark score of 21874, while the Intel Core Ultra 7 155U has 21174. Both sit at the 75th percentile among all CPUs in the database.

Q: Does the Intel chip win every benchmark?

A: No. Intel wins 9 of the 15 head-to-head tests, but AMD wins the remaining 6. AMD's wins include data compression, data encryption, extended instructions, integer math, multithread, and random string sorting.

Q: How do the core and thread counts compare?

A: The AMD part has 6 cores and 12 threads. The Intel part has 12 cores and 14 threads. Intel has twice the core count, but only 2 additional threads, reflecting its hybrid core arrangement.

Q: What is the single largest benchmark margin between the two?

A: The largest margin is in PassMark extended instructions, where AMD leads by 23.8%. Intel's largest margin is in PassMark physics, where it leads by 22.8%.

Q: Are both processors unlocked for overclocking?

A: No. Both have locked multipliers. The multiplier unlocked field is false for both the AMD Ryzen 5 PRO 6650U and the Intel Core Ultra 7 155U.

Q: Which processor has more PCIe lanes from the CPU?

A: The AMD Ryzen 5 PRO 6650U provides Gen 4 with 20 lanes from the CPU. The Intel Core Ultra 7 155U provides Gen 4 with 12 lanes from the CPU.

Specification Differences

The database records several fields where these two processors differ. The core count is 6 for AMD and 12 for Intel. Threads are 12 for AMD and 14 for Intel. Base clock differs dramatically, with AMD at 2.90 GHz and Intel at 1700.00 MHz, though this reflects different boost behavior and hybrid core frequencies. Boost clock is 4.50 GHz for AMD and 4.80 GHz for Intel.

The process node is 6 nm for AMD and 7 nm for Intel. The foundry is TSMC for AMD and Intel for Intel. Die size is 208 mm² for AMD, while no die size is recorded for Intel.

Cache differs at every level. L1 is 64 KB per core for AMD and 112 KB per core for Intel. L2 is 512 KB per core for AMD and 2 MB per core for Intel. L3 is 16 MB shared for AMD and 12 MB shared for Intel.

Memory bandwidth is 76.8 GB/s for AMD and 89.6 GB/s for Intel. PCIe lanes are 20 for AMD and 12 for Intel. Integrated graphics are Radeon 660M for AMD and Arc Xe-LPG 64EU for Intel.

The socket is AMD Socket FP7 for AMD and Intel BGA 2049 for Intel. The architecture is Zen 3+ for AMD and Meteor Lake for Intel. The codename is Rembrandt for AMD and Meteor Lake for Intel. The generation is listed as Ryzen 5 (Zen 3+ Rembrandt) for AMD and Ultra 7 (Meteor Lake) for Intel. The release date is April 2022 for AMD and December 2023 for Intel. The launch MSRP is not recorded for AMD and is $490 for Intel.

Both support DDR5 memory, both use dual-channel buses, neither supports ECC memory, both are mobile segments, both are active in production, and both have locked multipliers. The part numbers differ, with AMD at 100-000000539100-000000551 and Intel at SRN6B.

Head-to-Head Benchmarks

The Cinebench results all favor Intel, but the margins vary by test. In Cinebench R23 multicore, Intel scores 9674.5 against AMD's 8854, an 8.5% lead. This is a meaningful gap for a workload that scales with thread count and sustained power. The R23 singlecore result shows Intel at 1666 and AMD at 1463, a 12.2% lead, which is the largest single-core margin in the comparison. Cinebench R15 multicore goes to Intel at 1585 versus 1459.5, a 7.9% lead, and R15 singlecore goes to Intel at 238.5 versus 232.5, a smaller 2.5% margin.

The PassMark suite tells a more balanced story. AMD wins data compression by 7.4%, scoring 190180 versus 177122. Data encryption goes to AMD by 7.3%, 12159 versus 11333. The extended instructions test is AMD's standout, with a 23.8% lead, 12261 versus 9903. Integer math favors AMD by 4.3%, 60045 versus 57564. Random string sorting goes to AMD by 2.7%, 20299 versus 19767. The multithread test is the closest of all, with AMD at 16429 and Intel at 16382, a 0.3% edge for AMD.

Intel's PassMark wins are concentrated in floating point and physics. Floating point math goes to Intel by 19.1%, 40256 versus 32571. Physics goes to Intel by 22.8%, 1084 versus 837, which is Intel's largest margin in the entire comparison. Prime number finding goes to Intel by 20%, 65 versus 52. Single-thread performance goes to Intel by 6.6%, 3372 versus 3149.

The overall pattern in the head-to-head data is consistent. Intel wins every rendering and single-thread test, often by double-digit margins. AMD wins every integer and data-oriented test, with its largest wins coming in extended instructions and its narrowest in multithread. The average benchmark scores, 21874 for AMD and 21174 for Intel, show that AMD's wins tend to be in tests that carry more weight in the aggregate, despite Intel's higher count of individual victories. The percentile ranking is identical at 75 for both, placing them in the same performance tier overall, but the workload split is clear enough that buyers should match the chip to the task.