Loading activity…
@oscar_yinn
phd @uwnlp @waiorg
AI
TMax-v1.1-9B reportedly scored 33.0% on Terminal-Bench 2.0, up from 27.2% for its v1.0 counterpart.
XAI
A post about the project claims a 65% score gain with the same compute on a 24-hour multi-repository agent-swarm task.
