Anthropic Evals

Using Anthropic with Phoenix Evals

Requires anthropic

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

Create an LLM instance with the Anthropic provider:

from phoenix.evals import LLM

llm = LLM(provider="anthropic", model="claude-sonnet-4-6")

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-4-6", api_key="sk-ant-...")

Using with evaluators

from phoenix.evals import LLM, evaluate_dataframe
from phoenix.evals.metrics import FaithfulnessEvaluator

llm = LLM(provider="anthropic", model="claude-sonnet-4-6")
evaluator = FaithfulnessEvaluator(llm=llm)

results_df = evaluate_dataframe(dataframe=df, evaluators=[evaluator])

Developer Tools

LLM Providers

TypeScript

Python

Java

.NET

Platform

Vector Databases

Sandboxes

Evaluation Integrations

Coding Agents

Anthropic Evals

Using Anthropic with Phoenix Evals

Using with evaluators

​Using Anthropic with Phoenix Evals

​Using with evaluators

Using Anthropic with Phoenix Evals

Using with evaluators