mirror of
https://github.com/stablyai/orca.git
synced 2026-11-16 19:07:41 +00:00
The numeric reasoning_effort a model sees is not on a 0-100 scale (claude-opus-5-5: low=5, medium=10, high=15, xhigh=40). Workers launched with --effort high read 15 as low and misreported their effort.