Simulated robotics eval: Claude Opus 5.5 preferred over Opus 5 in 14 of 16 comparisons
qinzytech · x · 2026-10-17
embodianalysis published direct head-to-head comparisons of Claude Opus 5.5 vs Opus 5 in simulated robotics tasks, with Opus 5.5 preferred in 14 of 16 pairs. Two examples illustrate behavior differences: in a croissant-and-jam task, Opus 5.5 moved the croissant to the cutting board and proceeded to the cabinet while Opus 5 left it on the plate (neither placed the jam); in a microwave task Opus 5 was preferred, reaching toward the lower Start button while Opus 5.5 worked near the upper controls, with clips not clearly confirming the microwave started. The authors stress a methodology point: completion-only scoring would rate both croissant runs identically (unfinished) and miss progress through the instruction — the 14/2 preference result is a relative judgment, not a task success rate.
More from Embodied
- Contact-UAN: MIT's residual world model fixes humanoid sim-to-real with 6.5 minutes of data — kevin_zakka · 2026-10-17
- ROS 2 LiDAR localization runs 390 m outdoors on handheld Livox MID-360 — rsasaki0109 · 2026-10-17
- Embodied Astra tops RoboMME at 92.1% — beating humans by just keeping full visual history in context — hankyang94 · 2026-10-17
- 100% blind developer built AccessSlice with Claude to make 3D printing accessible — Mrblindguardian · 2026-10-17
- ROS weekly: ROSCon China kicks off in Shanghai, ROS By-The-Bay set for Oct 22 at Intrinsic — kscottz · 2026-10-17
- FoundationVIO fuses IMU with foundation-model predictions to fix metric scale in feed-forward SLAM — zhenjun_zhao · 2026-10-17