Unlike most real-world games, 3DMark does award higher scores to platforms with higher-end processors in them, favoring higher core counts, in particular.
Conversely, the benchmark does reflect a shift from CPU to GPU dependence as resolution and detail levels increase. In fact, the baseline $1000 PC manages to beat the $2000 build at stock settings in 3DMark's Extreme preset, despite the fact that both builds include GeForce GTX 670s.
A combination of a weak dual-core CPU and less powerful graphics card put the $500 build more than 50% below Don's $1000 PC.
The $2000 PC’s SSD isn’t just bigger; it's also a faster model. Drive performance is the largest contributor to our PCMark results, though CPU architecture and clock rate play a significant role, too.
Here’s how my PC's advantage compares in a few synthesized real-world benchmarks (as opposed to pure synthetics, like SiSoftware's Sandra). CPU overclocking doesn’t help here, so the difference you see between the $2000 PC’s stock and overclocked settings is due to a reversion back to Windows 7's native AHCI driver in the overclocked configuration.
The performance of Paul's $500 PC isn't horrible. It's simply a byproduct of his mechanical disk.
- Chasing Down Diminishing Returns
- Test System Configurations, With Overclocks
- Benchmark Results: 3DMark And PCMark
- Benchmark Results: SiSoftware Sandra
- Benchmark Results: Battlefield 3
- Benchmark Results: DiRT 3
- Benchmark Results: The Elder Scrolls V: Skyrim
- Benchmark Results: StarCraft II
- Benchmark Results: Audio And Video Encoding
- Benchmark Results: Productivity
- Power And Efficiency
- Breaking Down The Value Chart