Geekbench Page

Understanding Geekebench Scores:

Geekbench 4 scores are calibrated against a baseline score of 4,000 (which is the score of an Intel Core i7-6600U @ 2.60 GHz). Higher scores are better, with double the score indicating double the performance.

Geekbench 5 scores are calibrated against a baseline score of 1,000 (which is the score of an Intel Core i3-8100). Higher scores are better, with double the score indicating double the performance.

Geekbench 6 scores are calibrated against a baseline score of 2,500 (which is the score of an Intel Core i7-12700). Higher scores are better, with double the score indicating double the performance.
  Geekbench 6 now only works on x86_64-v2 CPUs or higher. with a avx2 versions with x86_64-v3 base.

Geekbench ML/AI 0.6.0 scores are calibrated against a baseline score of 1,500 (which is the score of an Intel Core i7-10700). Higher scores are better, with double the score indicating double the performance.

Sources:
https://web.archive.org/web/20170711024339/https://www.geekbench.com/download/linux/
https://web.archive.org/web/20191212010251/https://www.geekbench.com/download/linux/
https://web.archive.org/web/20230214211225/https://www.geekbench.com/download/linux/
https://www.geekbench.com/ml/download/windows/ (March 2nd 2024)

Date: February 19th 2023

Run Geekbench Compute (GPU) on Linux:

Find supported GPUs using this command:
./geekbench_x86_64 --compute-list
Run Compute Benchmark on wanted GPU by (an example):
./geekbench_avx2 --compute vulkan --compute-platform-id 0 --compute-device-id 1

Source: http://support.primatelabs.com/kb/geekbench/geekbench-5-pro-command-line-tool
Date: March 3rd 2023

Run Geekbench AI on Linux:

./banff is the exactable name for Geekbench AI. With ./banff_x86_64 targeting x86-64-v2 or higher CPU's and ./banff_avx2 targeting x86-64-v3 or higher CPU's
To find what framework (TensorFlow/ONNX/etc), backend (CPU,GPU,NNAPI) and device (you're physical hardware), run this command:
./banff_avx2 --ai-list
Run AI benchmark on wanted framework, backend, and device after you finded them:
./banff_avx2 --ai-framework [ID] --ai-backend [ID] --ai-device [ID]
I tend to ignore / not add -ai-backend [ID] --ai-device [ID] if there is only CPU backend available and one CPU in my machine.

My Devices Benchmarks:

These are benchmarks by me or others for devices in my household. Past and present.

Other Device Benchmarks:

These are for Items I don't Have, but want

Other peoples profiles:

These are for people I follow on Geek Bench, and elsewhere like YouTube

Back