Claude Opus 5.5 beats Opus 5 in 14 of 16 comparisons, leads physical agent Elo 1313-1289
qinzytech · x · 2026-10-28
Embodi Analysis compared Claude Opus 5.5 vs Opus 5 in an October annotation batch: Opus 5.5 was preferred in 14 of 16 comparisons, and leads its Physical Agent Capability Index 1313 to 1289 Elo.
However, in the shown physical stacking task (place the yellow block on the red block), neither model succeeded: Opus 5.5's yellow block ended beside the gripper, and Opus 5 also failed to rest it on the red block. The assessor concluded both attempts were incomplete — gripper proximity doesn't satisfy the instruction; the block must rest on the target after release.
More from Models
- Anthropic models burn 2-3x tokens and cost 10-50x more on FrontierCode 2.0 — teortaxesTex · 2026-10-28
- Last full day on grandfathered 20x OpenAI plans before 10x usage switch — nptacek · 2026-10-28
- Dev: Claude lags far behind OpenAI models on memory and computer use — iruletheworldmo · 2026-10-28
- FrontierCode 2: Anthropic models burn 2-3x tokens, cost 10-50x more than open rivals — bookwormengr · 2026-10-28
- Tweak one neuron and Qwen3.5-4B turns into a screaming oracle: PEFT activation steering demos — LysandreJik · 2026-10-28
- Surge AI at Kaggle Bench Summit: why frontier models still struggle with work-like benchmarks — echen · 2026-10-28