Comment by qnleigh

5 hours ago

As far as I understand, this is exactly how ELO scores work. If a more capable show up and starts beating all the other models, it literally takes ELO points from everyone else.

https://en.wikipedia.org/wiki/Elo_rating_system

2 comments

qnleigh

Reply
TekMol  3 hours ago 

    If a more capable show up and starts
    beating all the other models

There is an instance of this in the chart. In 2025-06-24 when Gemini-2.5-pro shows up. As you can see, the ELO of the others do not drop.

harperlee  4 hours ago

Depends on the test design; is an agent competing against other agent in a given match, or against a test? Plus! Does the test's ELO fluctuate?