AIDA64 Cache & Memory
The AIDA64 memory benchmark measures how quickly data moves between system memory and the CPU's cache hierarchy. It provides a closer look at memory bandwidth, latency, and cache behavior.
The 32 GB DDR5-5600 configuration reached 84.74 GB/s reads, 77.48 GB/s writes, and 78.45 GB/s copies, with latency measuring 89.6 ns. Those bandwidth figures give the Core i9-13900F healthy dual-channel memory throughput for CPU-heavy workstation work, while the replaceable SO-DIMMs also leave room for a future capacity upgrade.
Cinebench
Cinebench uses Maxon's Cinema 4D engine to measure processor rendering performance across both single-threaded and multithreaded workloads. Comparing both scores shows how well the processor handles lightly threaded tasks and heavier rendering jobs.
The Core i9-13900F scored 1,237 points in the multicore test and 87 points in single-core, producing a very uneven split between sustained rendering and lightly threaded performance. The multicore score places the G3A close to several Ryzen AI 9 HX 370 systems despite their 65 W desktop processor configuration. The 87-point single-core score is unusually low for this CPU, so I went back and verified it against the original result before including it here.
7-Zip
7-Zip's built-in benchmark measures processor performance during both data compression and decompression across a range of dictionary sizes. It's a useful indicator of how a system handles file-heavy workloads such as packing archives, installing software, or building projects.
The G3A produced 134,089 MIPS while compressing, 140,014 MIPS while decompressing, and 137,051 MIPS overall, putting the Core i9-13900F near the front of this comparison group. File compression uses many threads effectively, and this result is a much better reflection of the processor's heavy multithread throughput than the unusually low Cinebench single-core score.
PCMark
PCMark runs a collection of common desktop activities, including web browsing, video conferencing, office applications, and media workflows. It gives a broad look at day-to-day desktop performance.
The G3A scored 6,962 overall, with 9,794 in Essentials, 8,154 in Productivity, and 11,466 in Digital Content Creation. Everyday desktop performance falls closer to the middle of my comparison group, while the stronger content score better suits the workstation positioning and mixed CPU/GPU hardware inside this system.
Y-Cruncher
Y-Cruncher calculates digits of Pi with extreme precision, placing an extreme load on both CPU and memory. It's useful for gauging raw compute ability and stability under heavy math workloads.
Calculating 2.5 billion digits of Pi took 84.705 seconds of computation time and 87.733 seconds from start to finish. That puts the G3A in the same general range as several newer high-end Mini-PCs, giving the 24-core desktop processor good sustained math performance without matching the fastest Ryzen AI Max+ 395 systems.
Geekbench
Geekbench tests a wide variety of workloads, from encryption and AI to office productivity and photo editing. It also includes a GPU compute test, which provides a useful look at graphics performance outside of games.
Geekbench produced 2,085 points in single-core, 15,559 points in multicore, and 92,278 points in the OpenCL graphics compute test. The multicore score is among the stronger results in this group, while the RTX 2000 Ada nearly matches the 92,803-point Radeon 8060S result from the Tank M1A+ Pro in OpenCL; the low single-core score again contrasts sharply with the processor's multithread performance.