Anthropic Evals

Using Anthropic with Phoenix Evals#

Info

Requires anthropic

pip install "arize-phoenix-evals>=3" anthropic

Create an LLM instance with the Anthropic provider:

from phoenix.evals import LLMllm = LLM(provider="anthropic", model="claude-sonnet-4-20250514")

The LLM wrapper reads your API key from the ANTHROPIC_API_KEY environment variable, or you can pass it directly:

llm = LLM(provider="anthropic", model="claude-sonnet-4-20250514", api_key="sk-ant-...")

Using with evaluators#

from phoenix.evals import LLM, evaluate_dataframefrom phoenix.evals.metrics import FaithfulnessEvaluatorllm = LLM(provider="anthropic", model="claude-sonnet-4-20250514")evaluator = FaithfulnessEvaluator(llm=llm)results_df = evaluate_dataframe(dataframe=df, evaluators=[evaluator])