Claude 3.5 Haiku, Upgraded Claude 3.5 Sonnet
Anthropic
partial detail 15 method fields published
Evaluation
Human feedback evaluations (upgraded Claude 3.5 Sonnet / 3.5 Haiku)
human preference win rates vs prior Claude models
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.