AMD Ryzen 7 8745HX vs Intel Core 9 273PE Comparison

Head-to-Head Benchmarks

The head-to-head data records 11 benchmark comparisons between the AMD Ryzen 7 8745HX and the Intel Core 9 273PE. Intel takes 8 of those wins, while AMD claims 3. The margins, however, tell a more nuanced story than the raw win count.

Intel’s largest victory comes in the PassMark physics test, where it scores 3120 against AMD’s 1681, a delta of -46.1% from AMD’s perspective. That is nearly double the performance in a workload that typically stresses scheduling and core throughput. Floating point math shows a similar pattern: Intel scores 107884 versus AMD’s 61972, a 42.6% deficit for the Ryzen part. Integer math follows with Intel at 139410 and AMD at 100328, a 28% gap. These three workloads alone establish Intel’s dominance in raw computational throughput.

The multithread test gives Intel another clear win, 36810 versus 31517, a 14.4% margin. Find prime numbers also favors Intel, 203 versus 159, a 21.7% difference. Data compression goes to Intel at 405885 against 363759, a 10.4% edge. Data encryption is closer, with Intel at 22719 and AMD at 21840, a 3.9% gap. Random string sorting is nearly a tie: Intel scores 45098, AMD scores 44494, a 1.3% difference.

AMD’s wins are concentrated in single-thread performance and extended instruction throughput. The single-thread test shows AMD at 3879 against Intel’s 3650, a 6.3% advantage. The extended instructions test gives AMD 27638 versus Intel’s 24630, a 12.2% lead. These two results indicate that AMD’s core design retains an edge in latency-sensitive, lightly threaded work even though it trails in heavily parallel tasks.

The average benchmark score in the database places AMD at 60104 and Intel at 49845. That discrepancy is notable because the head-to-head tests mostly favor Intel, yet the broader average favors AMD. This suggests that the recorded benchmark set for AMD includes workloads beyond the 11 shared tests, and those additional results lift its average considerably. The percentile rankings reinforce this: AMD sits at the 92nd percentile of all CPUs, while Intel sits at the 90th.

Architecture Differences

The two processors come from different design philosophies. AMD uses the Zen 4 architecture on a 5 nm TSMC process, with a Dragon Range codename. Intel uses the Bartlett Lake codename on a 10 nm Intel process. The node difference is significant: 5 nm versus 10 nm, which typically affects power efficiency and transistor density, though the recorded data does not include direct efficiency measurements.

Core counts differ substantially. AMD provides 8 cores and 16 threads. Intel provides 12 cores and 24 threads. That 50% core advantage and 50% thread advantage explains much of Intel’s lead in multithreaded and physics workloads. The cache hierarchies also differ. AMD uses 64 KB of L1 per core, 1 MB of L2 per core, and 32 MB of shared L3. Intel uses 80 KB of L1 per core, 2 MB of L2 per core, and 36 MB of shared L3. Intel’s larger per-core L2 and larger shared L3 give it more on-die data capacity.

Clock behavior differs in both directions. AMD starts at 3.60 GHz base and boosts to 5.10 GHz. Intel starts lower at 2.30 GHz base but boosts higher to 5.70 GHz. The higher Intel boost clock helps explain its strong single-core Cinebench results, while the lower base clock reflects a different power management strategy. AMD’s TDP is 55 watts; Intel’s is 65 watts. Both are mobile or desktop parts with different market positioning: AMD is listed as a mobile segment processor on AMD Socket FL1, while Intel is listed as a desktop processor on Intel Socket 1700.

Memory support diverges. AMD supports DDR5 only, dual-channel, with a recorded bandwidth of 83.2 GB/s. Intel supports both DDR4 and DDR5, dual-channel, with a recorded bandwidth of 89.6 GB/s. Intel also supports ECC memory, while AMD does not. PCIe connectivity favors AMD: Gen 5 with 28 lanes (CPU only) versus Intel’s Gen 5 with 16 lanes (CPU only). Integrated graphics differ as well, with AMD using Radeon 610M and Intel using UHD Graphics 730. The database does not include iGPU benchmark scores, so no performance comparison is possible.

The process and transistor data are incomplete for Intel: the database lists 6,570 million transistors and a 71 mm² die size for AMD, but no transistor count or die size for Intel. Production status is Active for both. AMD’s multiplier is unlocked; Intel’s is not. AMD’s release date is recorded as 2025-04-22, while Intel’s is 2026-03-08. Intel’s launch MSRP is listed as $549; AMD has no recorded launch MSRP.

Where Each One Wins

The data supports a clear workload split. Intel wins where core count and aggregate throughput dominate. Physics simulation, floating point math, integer math, multithread rendering, prime number finding, and data compression all favor Intel, with margins ranging from 10.4% to 46.1%. These are workloads that scale with additional cores and threads, and Intel’s 12-core, 24-thread configuration provides the necessary parallelism.

AMD wins in single-thread responsiveness and extended instruction efficiency. The 6.3% single-thread lead and the 12.2% extended instructions lead indicate that AMD’s Zen 4 cores are more efficient when the workload is latency-bound or uses specialized instruction paths. For applications that depend on per-core speed rather than parallel scaling, AMD holds the advantage.

The encryption test is nearly neutral, with Intel ahead by only 3.9%. Random string sorting is also close, with Intel ahead by 1.3%. These near-ties suggest that memory access patterns and sorting algorithms are not strongly differentiated between the two designs, despite Intel’s larger cache and higher bandwidth.

The Cinebench results for Intel, which are not mirrored in AMD’s recorded benchmark set, show a strong multicore showing: Cinebench R23 multicore at 31288, R20 multicore at 13140, and R15 multicore at 3153. The single-core Cinebench numbers are 4417 (R23), 1855 (R20), and 445 (R15). These results are consistent with Intel’s high boost clock and high thread count, but they cannot be directly compared to AMD since the database does not list Cinebench scores for the Ryzen part.

FAQ

Q: Which processor has the higher single-thread score?

A: The AMD Ryzen 7 8745HX scores 3879 in the PassMark single-thread test, while the Intel Core 9 273PE scores 3650. AMD leads by 6.3%.

Q: How large is Intel’s lead in multithread performance?

A: Intel scores 36810 in the PassMark multithread test against AMD’s 31517, a 14.4% advantage.

Q: What explains Intel’s big win in the physics test?

A: Intel scores 3120 in PassMark physics versus AMD’s 1681, a 46.1% margin. The physics workload scales strongly with thread count, and Intel has 12 cores and 24 threads compared to AMD’s 8 cores and 16 threads.

Q: Does AMD have any workload where it wins by double digits?

A: Yes. AMD leads the extended instructions test by 12.2%, scoring 27638 against Intel’s 24630.

Q: Which processor has the higher average benchmark score?

A: AMD has an average benchmark score of 60104, while Intel has 49845. AMD also ranks at the 92nd percentile of all CPUs, versus Intel’s 90th.

Q: What are the cache differences?

A: AMD uses 64 KB L1 and 1 MB L2 per core with 32 MB shared L3. Intel uses 80 KB L1 and 2 MB L2 per core with 36 MB shared L3.

The Verdict

The database presents two different performance profiles. The AMD Ryzen 7 8745HX delivers superior single-thread performance, a 6.3% edge in PassMark single-thread, and a 12.2% edge in extended instructions. Its average benchmark score of 60104 is higher than Intel’s 49845, and it holds the 92nd percentile rank.

The Intel Core 9 273PE dominates in parallel workloads. Its 12-core, 24-thread configuration produces wins in physics, floating point, integer, multithread, prime finding, and compression tests, with the largest margin reaching 46.1%. Intel also offers ECC memory support, dual DDR4/DDR5 compatibility, and a higher boost clock of 5.70 GHz.

For users whose workloads are heavily multithreaded, the Intel part is the stronger choice according to the recorded data. For users who prioritize single-thread responsiveness or specialized instruction throughput, the AMD part holds the advantage. The choice depends on the workload mix, not on a single aggregate score.