Skip to content

Measure the reasoning, then fix what the measurement found: 55% to 91% - #9

Merged
punnerud merged 5 commits into
mainfrom
eval/quality-baseline
Aug 11, 2026
Merged

Measure the reasoning, then fix what the measurement found: 55% to 91%#9
punnerud merged 5 commits into
mainfrom
eval/quality-baseline

Plan the angles first: 84 % at six steps, against 80 % at four

18d9ce0
Select commit
Loading
Failed to load commit list.

Select a check to view from the sidebar