AMD Ryzen Threadripper PRO 9965WX vs Intel Xeon 6740P Comparison

Head-to-Head Benchmarks

The recorded data presents a split decision between the Intel Xeon 6740P and the AMD Ryzen Threadripper PRO 9965WX, with each processor taking eight wins across the benchmark suite. The nature of those wins, however, tells a clear story about workload suitability.

The AMD Ryzen Threadripper PRO 9965WX dominates the Cinebench rendering tests. In Cinebench R15 multicore, it scores 8162 against the Intel's 7544, a 7.6% advantage. That same 7.6% delta appears across Cinebench R15 singlecore, R20 multicore, R20 singlecore, and R23 multicore, where the AMD reaches 80976 versus 74851. This consistent margin points to a fundamental efficiency advantage in threaded and single-threaded rendering workloads.

The single-thread gap is far more pronounced in PassMark's single-thread test. The AMD scores 4551, which is 34.6% ahead of the Intel's 2975. This is the largest delta in either direction across the entire benchmark set. The Ryzen Threadripper's higher clock speeds clearly translate into decisive single-core performance in this specific measurement.

The Intel Xeon 6740P counters with significant wins in several PassMark compute workloads. Its most substantial victory comes in floating point math, where it scores 296102 versus 229685, a 28.9% lead. The Xeon achieves the same 28.9% margin in the physics test, scoring 9705 against the AMD's 7529. Data encryption shows a 24% advantage for Intel, with scores of 82028 and 66155 respectively.

The remaining Intel wins are narrower but consistent. Random string sorting goes to Intel by 17% (175015 versus 149617), data compression by 14.3% (1537129 versus 1345230), and integer math by 11.3% (388500 versus 349195). Extended instructions favor Intel by 7.6% (116992 versus 108753), while prime number finding shows a 9.3% edge (822 versus 752).

The PassMark multithread test is the one aggregate metric where AMD wins outside the Cinebench family, scoring 92604 against 88061, a 4.9% margin. This suggests the AMD processor handles broad thread-level parallelism well despite having fewer cores, while the Intel part excels in specific math-heavy and compression workloads.

Architecture Differences

The two processors take fundamentally different design approaches. The Intel Xeon 6740P is built on Granite Rapids architecture using a 5 nm process from Intel's own foundry, while the AMD Ryzen Threadripper PRO 9965WX uses Zen 5 architecture (codenamed Shimada Peak) fabricated by TSMC on a 4 nm process. The Intel part belongs to the Xeon 6 generation, and the AMD chip is part of the Ryzen Threadripper 9000 series with the Shimada Peak codename.

Core counts differ dramatically. The Xeon 6740P provides 48 cores and 96 threads, exactly double the 24 cores and 48 threads of the Ryzen Threadripper PRO 9965WX. This core advantage helps explain the Intel's strong showing in parallel compute tasks like floating point math and physics simulations.

Clock speeds show the opposite pattern. The AMD processor runs at 4.20 GHz base and boosts to 5.40 GHz, while the Intel part operates at 2.10 GHz base and 3.80 GHz boost. The AMD's higher clocks account for its commanding single-thread performance and its Cinebench victories.

Cache hierarchies also differ substantially. The Xeon 6740P features 112 KB of L1 cache per core, 2 MB of L2 per core, and a massive 288 MB of shared L3 cache. The Ryzen Threadripper PRO 9965WX offers 64 KB L1 per core, 1 MB L2 per core, and 128 MB of L3. The Intel chip's larger caches, particularly the 288 MB shared L3, likely contribute to its data-heavy workload wins.

Physical design separates the two further. The Intel processor has a die size of 2x 598 mm², uses Intel Socket 4710, and carries a 270 W TDP. The AMD chip uses 4x 70.6 mm² dies, fits AMD Socket sTR5, and has a 350 W TDP with 33,260 million transistors. The AMD processor has an unlocked multiplier, while the Intel part does not.

Memory support is similar on paper. Both use DDR5 with eight-channel memory buses and identical 409.6 GB/s memory bandwidth. Both support ECC memory. PCIe connectivity differs, with the Xeon 6740P offering Gen 5 with 88 lanes from the CPU, while the Ryzen Threadripper PRO 9965WX provides Gen 5 with 128 lanes.

Neither processor includes integrated graphics. The Intel part was released on 2025-02-23, while the AMD processor launched on 2025-07-22. Both are listed as Active in production status.

The Verdict

The data supports a clear workload-based recommendation. The AMD Ryzen Threadripper PRO 9965WX is the stronger choice for rendering and single-thread-sensitive applications. Its 7.6% lead across all five Cinebench tests, combined with a 34.6% advantage in PassMark single-thread, makes it the better option for interactive 3D work, simulation previews, and any software that relies heavily on per-core performance.

The Intel Xeon 6740P is the better fit for data-centric server and workstation tasks. Its 28.9% wins in floating point math and physics, 24% lead in encryption, and 14.3% advantage in data compression all point to strong suitability for scientific computing, financial modeling, and data processing pipelines. The 48-core count provides substantial parallelism for heavily threaded enterprise workloads.

The average benchmark scores place the Intel part at 176227 versus 147009 for the AMD chip, but this aggregate figure masks the workload-specific nature of the results. The Intel processor sits at the 98th percentile among all CPUs, as does the AMD part, indicating both are top-tier performers in their respective domains.

FAQ

Q: Which processor is faster in Cinebench R23 multicore?

A: The AMD Ryzen Threadripper PRO 9965WX scores 80976 in Cinebench R23 multicore, which is 7.6% ahead of the Intel Xeon 6740P's score of 74851.

Q: How much faster is the Intel Xeon 6740P in floating point math?

A: The Intel Xeon 6740P scores 296102 in PassMark floating point math, a 28.9% advantage over the AMD Ryzen Threadripper PRO 9965WX's 229685.

Q: What is the single-thread performance difference?

A: In PassMark single-thread testing, the AMD Ryzen Threadripper PRO 9965WX scores 4551, which is 34.6% higher than the Intel Xeon 6740P's 2975.

Q: How do the core counts compare?

A: The Intel Xeon 6740P has 48 cores and 96 threads, while the AMD Ryzen Threadripper PRO 9965WX has 24 cores and 48 threads.

Q: Do both processors support ECC memory?

A: Yes, both the Intel Xeon 6740P and the AMD Ryzen Threadripper PRO 9965WX support ECC memory and use DDR5 with eight-channel memory buses.

Q: Which processor has more PCIe lanes?

A: The AMD Ryzen Threadripper PRO 9965WX provides Gen 5 with 128 lanes from the CPU, while the Intel Xeon 6740P offers Gen 5 with 88 lanes.

Where Each One Wins

The AMD Ryzen Threadripper PRO 9965WX wins in rendering and single-threaded scenarios. All Cinebench tests, from R15 through R23, in both singlecore and multicore variants, favor the AMD chip by 7.6%. The PassMark multithread test also goes to AMD by 4.9%, and the single-thread test shows a massive 34.6% advantage. This combination suits creative professionals running 3D rendering, video editing timelines, and applications with heavy per-core dependencies.

The Intel Xeon 6740P wins in computational and data-processing domains. The 28.9% margins in floating point math and physics indicate strong performance for scientific simulations and engineering analysis. The 24% encryption advantage suits security-focused workloads such as secure communications and database encryption. Data compression at 14.3% ahead, random string sorting at 17% ahead, and integer math at 11.3% ahead all point to robust database and file-handling capabilities. The 7.6% edge in extended instructions and 9.3% lead in prime number finding round out a profile well suited to server-side compute tasks.