In the battle, if side A finishes before side B we allow the user to vote for A before B finishes. (This is contrary to Arena.ai methodology, but I think it's the right thing for agents when sides can take a dramatically different amount of time.) This is why DeepSeek 4.1 Flash is doing so well in our leaderboard, it's super fast and often sufficient.
> and a "developer vote"
This is confusing, sorry. Inspecting our data it's almost entirely people doing software developments with agents. It's just a vote.
> (Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)
This is a pivot from Bottomless (YC W19). That business is doing okay and funding our runway, in addition to fundraising back in 2021.
(Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)