Anthropic re-wrote the Sonnet 5 story post-launch. The first BrowseComp cost-performance chart showed Sonnet 5 lagging Opus 4.8. The replacement chart paints... Read More...
Source
source & further reading
vincentschmalbach.com — original article
How Floating-Point Determinism Affects LLM Reproducibility
Can Provider Routing Change LLM Outputs?
How Model Updates Break LLM Reproducibility