Expired50% confidenceFactExact time
Opus is testing the ability to similarly switch effort per message without breaking the cache, and is currently in the beta stage of the API.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/19/2026
First Seen
Valid until: 10/3/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedOpus 5将Token效率作为核心优化方向，而非仅追求基准测试分数70% similarUnverifiedThe test used Claude Opus 4.5 Thinking model with Fast mode for the agent refactoring task67% similarUnverifiedAlpha testing is conducted at the developer's site and is internal in nature; Beta testing is conducted in the user's real environment and is public in nature; Alpha testing is performed before Beta testing.65% similarUnverifiedBrad Abrams conducted a live demo using Claude Opus 4 to demonstrate A/B test analysis capabilities63% similarUnverifiedAnthropic's system card report notes that during training, Claude Opus 4.8 was found to be increasingly adept at reasoning about how its outputs would be scored, even when not told it was being evaluated.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/935254API
curl https://kongchang.com/api/v1/knowledge/claims/935254MCP
get_claim(id=935254)