Nanochataquarat RL Env (Community)
Fresh
AQuA-RAT multiple-choice reasoning environment aligned with the nanochat RL pipeline
Cite
Notes
Only stored in your browser.
Public scores on this env
33 vf-eval reports across 3 models
AQuA-RAT multiple-choice reasoning environment aligned with the nanochat RL pipeline
Cite
Notes
Only stored in your browser.
3 vf-eval reports across 3 models