Comment by thereitgoes456

15 hours ago

It’s so annoying that everyone just points to the Artificial Analysis index (or even worse, Epoch AI, where part of the score is how good the AI is at chess) as a proxy for “how good” the model is.

Its 200-300 TPS. GPT is at 50-60. And its like 5% worse? Yeah that is a good tradeoff.

  • Are you watching/waiting on your agents? I care zero about t/sec, quality is far more important that quantity or latency, but they run in the background and I check in from time to time