Nvidia RTX Pro 6000D squeaks ahead of RTX 5090D in Geekbench OpenCL—China-tailored AI card still performs well despite regulatory woes

Just as it did with the RTX 5090 and RTX 4090, Nvidia created a China-exclusive variant of the RTX Pro 6000, the RTX 6000D, only for the Cyberspace Administration of China to ban the product and encourage adoption of homegrown AI accelerators.

Despite those restrictions, someone has benchmarked the now contraband 6000D in Geekbench 6.5, GPU boasting an OpenCL score just ahead of the RTX 5090D V2 and just below the RTX Pro 6000.

The RTX 6000D scored 390,656 points in Geekbench 6.5’s OpenCL benchmark. The card’s performance is a mere 1% higher than Nvidia’s RTX 5090D V2, which boasts an OpenCL score of 386,710 points. The 6000D is also roughly 5% slower than its bigger brother, the RTX Pro 6000 server edition, which boasts a score of 410,605 points.

Best picks for you

• Export restrictions force Galax to build cutdown RTX 5090D V2 HoF

• China’s latest GPU arrives with claims of CUDA compatibility and RT support

• Upgraded Nvidia RTX 5090 gets 128GB VRAM and $13,000 price tag

Swipe to scroll horizontally

That’s not a big gap, especially considering the spec difference between the two RTX 6000 series GPUs. The RTX Pro 6000 comes with 96GB of GDDR7 operating on a 512-bit interface, spread over 32 chips with 3GB of capacity each. The GPU also comes with 24,064 CUDA cores split across 188 SMs.