AMD Ryzen Threadripper PRO 9985WX vs Intel Xeon 6980P Comparison

The Verdict

The benchmark data presents an unusually one-sided comparison. Across all 17 recorded head-to-head tests, the AMD Ryzen Threadripper PRO 9985WX records a win over the Intel Xeon 6980P. The database shows no benchmark where the Intel part takes the lead. The AMD processor's average benchmark score of 320,749 places it in the 99th percentile of all CPUs, while the Intel Xeon 6980P's average of 251,516 also sits in the 99th percentile but with a substantial gap between them.

For workloads dominated by single-threaded performance, the choice is clear. The AMD part leads by 110.5% in Cinebench R15 single-core and by 166.6% in PassMark single-thread tests. Users running lightly threaded applications, legacy code, or tasks that depend on high clock speeds should select the Ryzen Threadripper PRO 9985WX without hesitation.

For heavily threaded workloads, the picture is more nuanced but still favors AMD. In Cinebench R23 multi-core, the AMD processor scores 132,859 against the Intel's 63,175, a 110.3% advantage. The PassMark multithread score shows a 101.9% delta in AMD's favor. The Intel Xeon 6980P does offer double the core count at 128 cores versus 64, but the recorded data indicates that the AMD architecture extracts more usable throughput per core across every tested application.

The AMD processor's nearest rivals in the database include the Ryzen Threadripper 9980X at 0.3% behind, the Xeon 6781P at 1.7% ahead of AMD, and the EPYC 9575F at 2.9% ahead. The Intel Xeon 6980P's nearest rivals include the EPYC 9634 at 3% ahead of Intel, the Xeon 6747P at 5.6% ahead, while the EPYC 9684X sits 5.8% behind Intel and the Ryzen Threadripper 9970X sits 10.1% behind. This positioning suggests the Intel part competes in a lower performance tier despite its higher core count.

The verdict for system integrators and workstation buyers: the AMD Ryzen Threadripper PRO 9985WX is the stronger processor in every measured category within this database. The Intel Xeon 6980P remains a viable server platform for specific scale-out deployments where its 128 cores and twelve-channel memory bus serve particular infrastructure needs, but for raw application performance as recorded here, the AMD part dominates.

Architecture Differences

The two processors diverge fundamentally in their design approach. The AMD Ryzen Threadripper PRO 9985WX uses the Zen 5 architecture under the codename Shimada Peak, fabricated on a 4 nm process at TSMC. It integrates 66,520 million transistors across eight dies, each measuring 70.6 mm². The Intel Xeon 6980P uses Granite Rapids architecture, fabricated on Intel's 5 nm process with three dies of 598 mm² each. The database does not record a transistor count for the Intel part.

Core configurations differ significantly. The AMD processor provides 64 cores and 128 threads, while the Intel part doubles that with 128 cores and 256 threads. Clock speeds favor AMD dramatically: a 3.20 GHz base clock and 5.40 GHz boost clock versus Intel's 2.00 GHz base and 3.90 GHz boost. Both processors support DDR5 memory, but the memory channels differ: AMD uses eight-channel memory with 409.6 GB/s bandwidth, while Intel uses twelve-channel memory with 614.4 GB/s bandwidth. Both support ECC memory.

Cache hierarchies show distinct design philosophies. The AMD part allocates 64 KB of L1 per core, 1 MB of L2 per core, and a 256 MB L3 cache. The Intel part allocates 112 KB of L1 per core, 2 MB of L2 per core, and a 504 MB shared L3 cache. The larger L3 on Intel reflects its higher core count and shared cache topology, while AMD's per-core L2 allocation matches its lower core count.

PCIe capabilities also differ. The AMD processor offers Gen 5 with 128 lanes from the CPU, while the Intel processor provides Gen 5 with 96 lanes from the CPU. Neither includes integrated graphics. The AMD processor has an unlocked multiplier, whereas the Intel processor is locked. The AMD part's launch MSRP is $7999; the Intel part's launch MSRP is $12460.

Power envelopes differ substantially, with AMD rated at 350 W TDP and Intel at 500 W TDP. Socket compatibility separates the platforms entirely: AMD uses Socket sTR5, Intel uses Socket 7529. The AMD processor was released in July 2025, while the Intel processor launched in September 2024. Both are currently in active production.

FAQ

Q: Which processor has more cores?

A: The Intel Xeon 6980P has 128 cores and 256 threads, double the AMD Ryzen Threadripper PRO 9985WX's 64 cores and 128 threads.

Q: Does the AMD processor win in all benchmark categories?

A: Yes, the database records 17 wins for the AMD Ryzen Threadripper PRO 9985WX and 0 wins for the Intel Xeon 6980P across all head-to-head tests.

Q: Which processor has a higher boost clock?

A: The AMD Ryzen Threadripper PRO 9985WX boosts to 5.40 GHz, while the Intel Xeon 6980P boosts to 3.90 GHz.

Q: How does memory bandwidth compare?

A: The Intel Xeon 6980P provides 614.4 GB/s over twelve channels, while the AMD Ryzen Threadripper PRO 9985WX provides 409.6 GB/s over eight channels.

Q: What is the single-thread performance gap?

A: In PassMark single-thread tests, the AMD processor scores 4,482 against Intel's 1,681, a 166.6% advantage. In Cinebench R23 single-core, AMD scores 18,756 versus Intel's 8,918, a 110.3% delta.

Q: Which processor has more PCIe lanes?

A: The AMD Ryzen Threadripper PRO 9985WX offers 128 Gen 5 lanes, while the Intel Xeon 6980P offers 96 Gen 5 lanes.

Specification Differences

The two processors differ across nearly every specification field in the database. Core count: AMD 64, Intel 128. Thread count: AMD 128, Intel 256. Base clock: AMD 3.20 GHz, Intel 2.00 GHz. Boost clock: AMD 5.40 GHz, Intel 3.90 GHz. TDP: AMD 350 W, Intel 500 W.

Process node: AMD 4 nm from TSMC, Intel 5 nm from Intel's foundry. Die configuration: AMD uses eight dies of 70.6 mm² each, Intel uses three dies of 598 mm² each. The AMD part records 66,520 million transistors; no transistor count is listed for the Intel part.

Cache layout: AMD provides 64 KB L1 per core, 1 MB L2 per core, and 256 MB L3. Intel provides 112 KB L1 per core, 2 MB L2 per core, and 504 MB shared L3. Memory channels: AMD eight, Intel twelve. Memory bandwidth: AMD 409.6 GB/s, Intel 614.4 GB/s.

PCIe: AMD Gen 5 with 128 lanes, Intel Gen 5 with 96 lanes. Socket: AMD sTR5, Intel 7529. Multiplier: AMD unlocked, Intel locked. Release date: AMD July 2025, Intel September 2024. Launch MSRP: AMD $7999, Intel $12460.

The architecture and codename fields also differ completely: AMD uses Zen 5 with Shimada Peak, Intel uses Granite Rapids. The generation identifiers are "Ryzen Threadripper (Zen 5 (Shimada Peak))" for AMD and "Xeon 6 (Granite Rapids-AP)" for Intel.

Head-to-Head Benchmarks

The Cinebench suite shows consistent dominance for the AMD processor. In Cinebench R15 multi-core, AMD scores 13,392 against Intel's 6,367, a 110.3% advantage. The single-core R15 test shows AMD at 1,890 versus Intel's 898, a 110.5% delta. Cinebench R20 multi-core continues the pattern: AMD 55,800, Intel 26,533, again a 110.3% gap. The R20 single-core result shows AMD 7,877 versus Intel 3,745, a 110.3% delta. Cinebench R23 multi-core records AMD 132,859 and Intel 63,175, with the same 110.3% margin. R23 single-core shows AMD 18,756 against Intel 8,918, a 110.3% advantage.

The PassMark suite reveals the largest deltas. The most extreme result appears in PassMark physics: AMD scores 13,783 while Intel manages only 3,350, a 311.4% difference. This suggests the AMD architecture delivers far more effective physics computation per clock. PassMark single-thread tests show AMD at 4,482 versus Intel's 1,681, a 166.6% margin. PassMark find prime numbers records AMD 1,138 against Intel 555, a 105% delta.

Integer math shows a notable gap: AMD scores 872,710 versus Intel's 637,476, a 36.9% advantage. Random string sorting follows at 36.6% in AMD's favor with scores of 329,014 and 240,792. Data compression shows AMD 2,912,972 against Intel 2,364,519, a 23.2% delta. Data encryption records AMD 154,824 versus Intel 125,246, a 23.6% advantage.

The smallest margins appear in floating-point math and extended instructions. PassMark floating-point math shows AMD 553,348 against Intel 501,720, a 10.3% delta. PassMark extended instructions records AMD 225,340 versus Intel 214,794, a 4.9% advantage. PassMark multithread shows AMD 150,071 against Intel 74,324, a 101.9% delta.

The data indicates that AMD's advantage grows in tests that depend on high clock speeds and per-core efficiency, while the gap narrows in workloads that may benefit from Intel's larger cache and higher core count. Despite the Intel processor's 128 cores and 504 MB L3 cache, the recorded benchmarks show no test where it overcomes the AMD processor's clock and architecture advantages. The 500 W TDP of the Intel part does not translate into superior measured performance in this database, while the AMD part achieves its results within a 350 W envelope.