AMD Ryzen Threadripper PRO 9965WX vs Intel Xeon 6741P Comparison

Head-to-Head Benchmarks

The recorded data paints a lopsided picture. The Intel Xeon 6741P wins 15 of the 17 head-to-head benchmark comparisons, with the AMD Ryzen Threadripper PRO 9965WX taking only the two single-thread PassMark tests. The margin of victory varies dramatically by workload type.

In the Cinebench suite, the Intel part holds a consistent edge across every rendering test. Cinebench R15 multicore shows the Xeon 6741P at 8624 against 8162 for the Threadripper, a 5.7% lead. The single-core R15 result is nearly identical in percentage terms, 1217 vs 1152, also a 5.7% win for Intel. Moving to R20, the multicore gap stays at 5.7% (35935 vs 34009), and the single-core test repeats that exact delta (5073 vs 4801). Cinebench R23 tells the same story: multicore 85561 vs 80976, single-core 12079 vs 11431, both again at 5.7%. The consistency of that 5.7% delta across all six Cinebench tests suggests a fundamental per-core efficiency advantage for the Intel architecture in this workload, not just a raw core-count effect.

The PassMark suite reveals where the Xeon 6741P truly separates itself. Data compression is a major win: 1816408 vs 1345230, a 35% advantage. Data encryption shows an even larger gap at 35.7% (89746 vs 66155). Extended instructions land at 31.2% (142682 vs 108753). Integer math also comes in at 31.2% (458058 vs 349195). The most extreme divergence appears in floating-point math, where Intel scores 358423 against 229685, a 56% margin. Prime number finding is even more one-sided: 1242 vs 752, a 65.2% lead. Physics simulation shows the biggest single delta of all, with Intel at 13890 versus AMD at 7529, an 84.5% blowout.

Random string sorting is closer, but Intel still wins by 18.5% (177322 vs 149617). The PassMark multithread score narrows the gap to 8.7% (100660 vs 92604), reflecting the Threadripper's respectable multi-core throughput despite its core deficit.

The only AMD victories come in PassMark single-thread and the duplicate PassMark singlethread entry, both recording 4551 for AMD against 3195 for Intel. That is a 29.8% advantage for the Ryzen part in single-threaded PassMark work. This result is striking because in Cinebench single-core tests, Intel actually wins by 5.7%. The PassMark single-thread test clearly stresses different aspects of the processor, favoring the AMD's higher clock speeds.

Looking at the broader database context, the Xeon 6741P sits at the 99th percentile of all CPUs with an average benchmark score of 194901. Its nearest rivals are the AMD EPYC 9335 (194228, only 0.3% behind), the Intel Xeon 678X (193477, 0.7% behind), the Intel Xeon 6740E (187718, 3.8% behind), and the AMD EPYC 8534P (185092, 5.3% behind). The Threadripper PRO 9965WX ranks at the 98th percentile with an average score of 147009. Its nearest rivals are the AMD EPYC 8434P (146881, 0.1% behind), the AMD Ryzen 9 PRO 9965 (145728, 0.9% behind), the AMD EPYC 7643P (144824, 1.5% behind), and the Intel Xeon w9-3575X (144323, 1.9% behind). The average score gap between the two processors in this comparison is substantial: 194901 vs 147009, meaning the Xeon holds roughly a 32.6% higher average benchmark score across all recorded tests.

The Verdict

The data directs a clear conclusion: the Intel Xeon 6741P is the superior processor in nearly every measured dimension. It wins 15 of 17 head-to-head tests, and its victories are not marginal. In floating-point math and physics simulation, the Intel part is 56% and 84.5% ahead respectively. For data compression, encryption, and extended instructions, the lead sits between 31.2% and 35.7%. Even in Cinebench workloads, where the Threadripper was expected to compete closely given its much higher boost clock, the Xeon wins every single test by 5.7%.

The AMD Ryzen Threadripper PRO 9965WX has exactly one meaningful strength in this dataset: PassMark single-thread performance, where it leads by 29.8%. If that specific workload is the primary use case, the AMD part is the pick. Otherwise, the Xeon 6741P dominates.

The core count difference explains much of the multicore performance gap. The Xeon offers 48 cores and 96 threads against 24 cores and 48 threads for the Threadripper. Doubling the core count while maintaining a per-core advantage in Cinebench results in that consistent 5.7% delta. The Threadripper's clock advantage, 5.40 GHz boost versus 3.80 GHz, helps it in PassMark single-thread but cannot overcome the core deficit elsewhere.

The average benchmark score gap, 194901 vs 147009, places the Xeon in a different performance tier entirely. The Threadripper's nearest rivals include the EPYC 8434P and Ryzen 9 PRO 9965, both in the 145000 range. The Xeon's rivals start at 185092 and go up to 194228. These are not adjacent performance classes.

Where Each One Wins

The Intel Xeon 6741P wins in all compute-heavy parallel workloads. Physics simulation is its strongest category with an 84.5% advantage, making it the clear choice for scientific computing, fluid dynamics, and any simulation workload. Floating-point math at 56% ahead covers financial modeling, signal processing, and scientific computation. Prime number finding at 65.2% suggests strength in number-theoretic algorithms and cryptography-adjacent workloads. Data compression at 35% and encryption at 35.7% point to database, storage, and security applications. The Cinebench wins across all versions indicate rendering and 3D animation workloads favor the Xeon. Integer math at 31.2% and extended instructions at 31.2% cover general-purpose computing and SIMD-heavy code.

The AMD Ryzen Threadripper PRO 9965WX wins only in PassMark single-thread testing. With a 29.8% lead over the Xeon in that specific metric, it is the better option for lightly threaded applications that depend on raw per-thread speed. Legacy software, single-threaded scripts, or interactive workloads that cannot parallelize would benefit from the Threadripper's higher clock speeds. However, this advantage does not carry over to Cinebench single-core tests, where Intel wins by 5.7%, so the AMD advantage appears specific to the PassMark measurement methodology.

For systems running mixed workloads, the Xeon's all-around dominance makes it the safer choice. The Threadripper's single-thread win is real but narrow in scope, confined to one benchmark family.

FAQ

Q: Which processor has more cores and threads?

A: The Intel Xeon 6741P has 48 cores and 96 threads. The AMD Ryzen Threadripper PRO 9965WX has 24 cores and 48 threads. Intel has exactly double the core and thread count.

Q: What is the biggest performance gap between these two processors?

A: The largest delta is in PassMark physics simulation, where the Intel Xeon 6741P scores 13890 against the AMD's 7529, an 84.5% advantage for Intel. The second largest is prime number finding at 65.2% in Intel's favor.

Q: Does the AMD processor win any benchmark tests?

A: Yes, the AMD Ryzen Threadripper PRO 9965WX wins the PassMark single-thread test with a score of 4551 versus Intel's 3195, a 29.8% advantage. This appears twice in the data as both PassMark single-thread and PassMark singlethread record the same scores.

Q: How do their average benchmark scores compare?

A: The Intel Xeon 6741P has an average benchmark score of 194901, ranking at the 99th percentile of all CPUs. The AMD Ryzen Threadripper PRO 9965WX averages 147009, ranking at the 98th percentile. The Xeon's average score is approximately 32.6% higher.

Q: What are the clock speed specifications for each processor?

A: The Intel Xeon 6741P has a base clock of 2.50 GHz and a boost clock of 3.80 GHz. The AMD Ryzen Threadripper PRO 9965WX has a base clock of 4.20 GHz and a boost clock of 5.40 GHz.

Q: What memory configurations do these processors support?

A: Both processors support DDR5 memory with an eight-channel memory bus and 409.6 GB/s of memory bandwidth. Both also support ECC memory.

Architecture Differences

The two processors come from fundamentally different design philosophies. The Intel Xeon 6741P uses the Granite Rapids architecture on a 5 nm process node fabricated by Intel. The AMD Ryzen Threadripper PRO 9965WX uses the Zen 5 architecture, codenamed Shimada Peak, on a 4 nm process node fabricated by TSMC. The AMD chip packs 33,260 million transistors across four chiplets, each measuring 70.6 mm², for a total die area of 4x 70.6 mm². The Intel chip uses a dual-die design with each die measuring 598 mm², for a total of 2x 598 mm².

Cache hierarchies differ substantially. The Intel Xeon 6741P provides 112 KB of L1 cache per core, 2 MB of L2 cache per core, and a massive 288 MB of shared L3 cache. The AMD Ryzen Threadripper PRO 9965WX offers 64 KB of L1 per core, 1 MB of L2 per core, and 128 MB of L3 cache. The Intel part has more than double the L3 cache, which helps explain its dominance in cache-sensitive workloads like data compression and encryption.

Memory support is identical: both use DDR5 with an eight-channel bus and 409.6 GB/s of bandwidth, and both support ECC memory. PCIe connectivity is close but not equal. The Intel Xeon 6741P offers Gen 5 with 136 lanes from the CPU, while the AMD part offers Gen 5 with 128 lanes. Neither has integrated graphics.

The socket and platform differ completely. Intel uses Socket 4710, while AMD uses Socket sTR5. The Intel part is a server/workstation segment processor with a locked multiplier, part number SRVEY. The AMD part is also server/workstation segment but has an unlocked multiplier, part number 100-000000724, making it more flexible for overclocking. The Intel launch MSRP is $4421, and the AMD launch MSRP is $2899.

The Intel Xeon 6741P is from the Xeon 6 generation (Granite Rapids-SP) and was released on 2025-02-23. The AMD Ryzen Threadripper PRO 9965WX belongs to the 9000 series, is from the Ryzen Threadripper generation (Zen 5 Shimada Peak), and was released on 2025-07-22. Both are listed as active production parts.

The thermal design power differs, with Intel rated at 300 W and AMD at 350 W, though the AMD part's higher TDP does not translate into higher multicore performance in the recorded benchmarks. The base clocks are also very different: 2.50 GHz for Intel versus 4.20 GHz for AMD, while boost clocks are 3.80 GHz versus 5.40 GHz respectively. Despite the AMD's significantly higher clock speeds, the Intel part wins on every Cinebench test and nearly every PassMark test, underscoring the importance of core count, cache size, and architecture efficiency over raw clock frequency.