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=arc-pro-b60-24gb-x2.
Full machine surface: /llms.txt · REST API: api.bestmodel.run

  rig                               | model                                  | basis    | value          | n
  arc-pro-b60-24gb-x2                | meta-llama-llama-3-2-1b-instruct       | reported | 189.3 tok/s    | n=2
  arc-pro-b60-24gb-x2                | ornith-ai-ornith-1-0-35b-gguf          | reported | 62.6 tok/s     | n=2
  arc-pro-b60-24gb-x2                | meta-llama-meta-llama-3-8b-instruct    | measured | 46.7 tok/s     | n=13
  arc-pro-b60-24gb-x2                | openai-gpt-oss-20b                     | reported | 40.1 tok/s     | n=2
  arc-pro-b60-24gb-x2                | meta-llama-llama-2-7b-hf               | reported | 34.8 tok/s     | n=2
  arc-pro-b60-24gb-x2                | qwen-qwen3-5-9b                        | reported | 30.4 tok/s     | n=2
  arc-pro-b60-24gb-x2                | qwen-qwen3-6-27b                       | reported | 9.5 tok/s      | n=2

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