The Intel Core i9-13905H is a high-end mobile CPU for laptops based on the Raptor Lake-H series (Alder Lake architecture). It was announced in early 2023 and offers 6 performance cores (P-cores, Golden Cove architecture) and 8 efficient cores (E-cores, Gracemont architecture). The P-cores support Hyper-Threading leading to 20 supported threads when combined with the E-cores. The clock rate ranges from 2.6 to 5.4 GHz (single core turbo, all-core 4.9 GHz) on the performance cluster and 1.9 to 4.1 GHz on the efficiency cluster. The performance of the E-cores should be similar to old Skylake cores (compare with the Core i7-6920HQ). All cores can use up to 24 MB L3 cache. Similar to the i9-13900H but without vPro support and the 13905H uses a different package and socket.
Performance
Thanks to the high core count and high clock speed, the Core i9-13905H is (together with the 13900HK) the fastest 45W CPU for laptops and only bested by Raptor Lake-HX based models with more cores and improved P-cores (e.g., the i9-13980HX). Still, the CPU is very well suited for all demanding use cases like gaming, content creation, and scientific calculations.
Features
The integrated memory controller supports various memory types up to DDR5-5200 (up from 4800 MHz for the 12th gen). The Thread Director (in hardware) can support the operating system to decide which thread to use on the performance or efficient cores for the best performance. For AI tasks, the CPU also integrates GNA 3.0 and DL Boost (via AVX2). Quick Sync in version 8 is the same as in the Rocket Lake CPUs and supports MPEG-2, AVC, VC-1 decode, JPEG, VP8 decode, VP9, HEVC, and AV1 decode in hardware. The CPU now supports PCIe 5.0 x8 for a GPU and two PCIe 4.0 x4 for SSDs.
The integrated graphics card is based on the Xe-architecture and offers 96 EUs (Execution Units) .
The CPU is rated at 45 W base power (115 W PL2) but most laptops will use a PL1 of around 60 Watt. The SoC is manufactured in a 10nm process at Intel, which is known as Intel 7 (improved over the 12th Gen).
The AMD Ryzen 9 5950X is a high-end 16-core, hyperthreaded (SMT) Vermeer Series desktop processor. With 32 threads, the new flagship offers as many threads as the AMD Ryzen 9 3950X. Introduced on October 8, 2020, the Ryzen 9 5950X is the fastest 16-core processor and is specified at 105 watts TDP.
The Ryzen 9 5950X runs at 3.4 GHz to 4.9 GHz (single core). Wen all 16 cores are loaded, up to 4.5 GHz are still possible.
The internal structure of the processor has not changed fundamentally at first glance. The CCX structure has changed a bit compared to Zen 2, because now a CCX consists of up to 8 CPU cores. So each individual core can access the complete L3 cache (32 MByte). Furthermore the CCX modules are connected to each other via the same I/O die, which we already know from Zen2. According to AMD, the Infinity fabric should now reach clock rates of up to 2 Ghz, which in turn allows a RAM clock of 4,000 MHz without performance loss.
Performance
The average 5950X in our database matches the Core i9-12900K, the Core i9-12900HX and also the Ryzen Threadripper 2970WX in multi-thread performance, making this Ryzen a great processor for pretty much any task imaginable as of mid 2022.
Power consumption
This Ryzen 9 series chip has a default TDP (also known as the long-term power limit) of 105 W. It will, however, happily consume much more than that as long as the cooling solution is able to handle the heat - even before one starts considering the possibility of overclocking the thing.
The Ryzen 9 5950X is built with TSMC's 7 nm process for average, as of mid 2023, energy efficiency.
The AMD Ryzen 7 5700X is a desktop processor with 8 cores and simultaneous multithreading (SMT), which means it can process 16 threads simultaneously. In April 2022, AMD presented the Ryzen 7 5700X, a new 8-core processor that is very similar to the AMD Ryzen 7 5800X. However, due to the lower TDP, there are no restrictions on the clock frequency. Nevertheless, the AMD Ryzen 7 5700X reaches up to 4.6 GHz in boost, which is only 100 MHz less than the AMD Ryzen 7 5800X. However, the base clock drops significantly to 3.4 GHz.
The performance of the AMD Ryzen 7 5700X is consistently excellent in all applications. The native 8-core can really show off its strengths, especially in multi-threaded applications, although the single-core performance has also been significantly improved compared to the older Zen 2 architecture.
The internal structure of the processor is similar to the AMD Ryzen 7 5800X. The CCX modules are also connected to each other via the I/O die, which we already know from Zen2. However, according to AMD, the Infinity Fabric should now achieve clock rates of up to 2 GHz, which in turn enables a RAM clock rate of 4,000 MHz without any loss of performance.
In terms of manufacturing processes, AMD also relies on TSCM for the 7nm production of the CPU cores in the Vermeer processors, although the I/O die is still supplied in 12 nm by Globalfoundries.
The AMD Ryzen 7 5700X is impressive in gaming thanks to the significantly improved IPC compared to Zen2. In terms of power consumption, the AMD Ryzen 7 5700X impresses with its low TDP of just 65 watts. This means that the processor can also be operated with a compact air cooler without any problems. The AMD Ryzen 7 5800X is operated with a TDP of 105 watts.
Average Benchmarks Intel Core i9-13905H → 100%n=24
Average Benchmarks AMD Ryzen 9 5950X → 113%n=24
Average Benchmarks AMD Ryzen 7 5700X → 86%n=24
- Range of benchmark values for this graphics card - Average benchmark values for this graphics card * Smaller numbers mean a higher performance 1 This benchmark is not used for the average calculation
v1.33
log 01. 03:38:27
#0 ran 0s before starting gpusingle class +0s ... 0s
#1 checking url part for id 14983 +0s ... 0s
#2 checking url part for id 12787 +0s ... 0s
#3 checking url part for id 15075 +0s ... 0s
#4 redirected to Ajax server, took 1759282707s time from redirect:0 +0s ... 0s
#5 did not recreate cache, as it is less than 5 days old! Created at Mon, 29 Sep 2025 12:06:34 +0200 +0s ... 0s
#6 composed specs +0.006s ... 0.006s
#7 did output specs +0s ... 0.006s
#8 getting avg benchmarks for device 14983 +0.004s ... 0.01s
#9 got single benchmarks 14983 +0.008s ... 0.018s
#10 getting avg benchmarks for device 12787 +0.005s ... 0.023s
#11 got single benchmarks 12787 +0.009s ... 0.032s
#12 getting avg benchmarks for device 15075 +0.004s ... 0.037s
#13 got single benchmarks 15075 +0.005s ... 0.042s
#14 got avg benchmarks for devices +0s ... 0.042s
#15 min, max, avg, median took s +0.076s ... 0.117s
- Average benchmark values for this graphics card
