Know a great AI tool or AI news source? Submit it to AiByts
LIBERO6 min read

pi0.5 LIBERO Results, Reproduced On Manifold

We ran the public pi0.5 LIBERO checkpoint for 1,999 episodes across all four suites and averaged 96.7%, against 96.85% reported by openpi. Per-suite results and rerun spread.

By BifrostBifrost Blog

Read the full story

Originally published by Bifrost Blog on Oct 6, 2026.

Read on Bifrost Blog(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.