Cinebench R23: CPU results with AMD and Intel

tl; dr: How fast is the processor in the brand new Cinebench R23 CPU benchmark? The community is called upon to test models from AMD and Intel, as well as Apple Silicon in the future. The goal: a comparative comparison with old and new CPUs and APUs from AMD and Intel and with Systems-on-a-Chip from Apple.

This is new in Cinebench R23

Cinebench R23 (download), like Cinebench R20 (community benchmark) and earlier versions, is based on the technology of the well-known Cinema 4D rendering tool, but now based on Release 23. This means that a heavily used rendering engine is again used. revised, among other things also the AVX instruction set and for the first time also the Apple M1 processor supported. The minimum requirement, however, is still the SSE3 instruction set.

New features and still up to 256 threads

There is again a test for single-threaded and multi-threaded performance, which can now be selected individually. Maxon focuses on scaling with many threads in Cinebench R23 – in addition, up to 256 threads are supported.

Furthermore, the benchmark feature set has been expanded and both the code and the compiler have been adapted, which is why, according to the manufacturer, the previous results should not be used for comparison.

• The new Cinebench is based on the code of the current Cinema 4D R23 and uses updated compilers. In this version, a minimum run time is enabled by default (previously hidden in the settings).
• According to Maxon, Cinebench R23 delivers more reliable and accurate results for high-performance systems and allows users to check whether their hardware is capable of delivering consistent performance without bottlenecks due to thermal issues.
• Users now have the ability to test single-core performance directly without manually enabling the Advanced Benchmarking option. The extended benchmarking mode also allows any runtime to be set up to test hardware for even longer periods of time.
• Due to code and compiler changes, the Cinebench result values ​​will be converted to a new range of values, so they should not be compared with the results from previous versions of Cinebench.

How fast are the processors in Cinebench R23? At the moment, the editorial team simply doesn’t have the free ability to create a broad overview, so Cinebench R20 (community benchmark) allows the community to show what they can do this time and diligently deliver their results. Multi-core and single-core tests must be performed separately.

Note: The “Advanced Benchmark” option should be activated under “File”, the “Minimum Test Duration” option, which can be used for the new Cinebench R23 stability test, should be set to “off”.

The results are presented using the form below and, after having been verified by the editorial staff, are inserted in the schemes. When submitting the results, additional information is also important, such as the processor used and whether it has been factory tested or overclocked (specifying the multi-core turbo) or, for example, in eco mode. The correct spelling of “Core i9-10900K” or “Ryzen 5 5600X” must be ensured – this makes it much easier to adopt valid results.

Note: With mobile CPUs and APUs, the selected TDP level should also be transmitted.

Examples:

• Ryzen 5 5600X @ Stock (The CPU works in the factory state)
• Ryzen 5 5600X @ 4.7 GHz (CPU runs on 4.7GHz all-core turbo)
• Ryzen 5 5600X @ Eco (CPU runs in eco mode with low TDP)
• Ryzen 7 4800H 45 Watt (APU works with a 45 watt TDP rating)
• Core i7-10700K @ Stock (The CPU works in the factory state)
• Core i7-10700K @ 5.0 GHz (CPU runs on 5.0 GHz all-core turbo)
• 28 Watt Core i7-1185G7 (The APU works with a TDP rating of 28 watts)

You don’t need to specify other parameters such as RAM, it has never been important in Cinebench.

The results

The following diagrams contain the editorial team’s initial benchmarks (blue and red) and will later be expanded to include community benchmarks (orange).

What has already been proven: the new engine can handle more cores even better. A Ryzen 9 5950X with 16 cores, for example, increases by 31 percent over the Ryzen 9 5900X with 12 cores, in Cinebench R20 it is 22 percent, and the gaps in multi-core execution are greater among other CPUs as well.

Was the article interesting, helpful or both? Publishers appreciate any support from ComputerBase Pro and disabled ad blockers. Learn more about announcements on ComputerBase.