Claude 3.5 Haiku, Upgraded Claude 3.5 Sonnet
Anthropic
partial detail 16 method fields published
Evaluation
Internal agentic coding evaluation (upgraded Claude 3.5 Sonnet / 3.5 Haiku)
agentic coding: implement a pull request in an open-source codebase
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.