bestmodel.run / pool — agent view

Honesty ladder: measured > reported > extrapolated > formula > no data yet.
Top 60 cells, default sort: fastest decode. Columns: rig | model | basis | value | n.
Filter: rig=rtx-pro-6000-blackwell-workstation-edition-96gb.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  rtx-pro-6000-blackwell-workstation-edition-96gb | openai-gpt-oss-120b                    | measured | 197.3 tok/s    | n=4
  rtx-pro-6000-blackwell-workstation-edition-96gb | orcarouter-qwen3-8-27b-uncensored-fp8  | reported | 166.6 tok/s    | n=2
  rtx-pro-6000-blackwell-workstation-edition-96gb | qwen-qwen3-6-35b-a3b                   | reported | 164.1 tok/s    | n=2
  rtx-pro-6000-blackwell-workstation-edition-96gb | 0xsero-qwen3-5-122b-a10b-reap-20       | measured | 126.5 tok/s    | n=5
  rtx-pro-6000-blackwell-workstation-edition-96gb | hauhaucs-qwen3-5-122b-a10b-uncensored-hauhaucs-aggressive | reported | 86.9 tok/s     | n=2
  rtx-pro-6000-blackwell-workstation-edition-96gb | inclusionai-ling-2-6-flash             | measured | 86.2 tok/s     | n=8
  rtx-pro-6000-blackwell-workstation-edition-96gb | google-gemma-4-31b-it                  | reported | 58.6 tok/s     | n=1
  rtx-pro-6000-blackwell-workstation-edition-96gb | google-gemma-4-31b-it                  | measured | 47.4 tok/s     | n=4
  rtx-pro-6000-blackwell-workstation-edition-96gb | nvidia-gemma-4-26b-a4b-nvfp4           | reported | 36.9 tok/s     | n=1
  rtx-pro-6000-blackwell-workstation-edition-96gb | qwen-qwen3-6-27b-fp8                   | reported | 24.8 tok/s     | n=2

Capture or correct a number: /console (signed, Ed25519).