Skip to content
masterclass Buddy
Start learning

LangSmith · Type Alias

EvaluationResult

EvaluationResult is a Pydantic model for one evaluation outcome. It records a metric key, score or value, evaluator details, and optional run links or feedback settings.

Last updated

Since
v0.5

Syntax

EvaluationResult(key: str, score: SCORE_TYPE, value: VALUE_TYPE, evaluator_info: dict, metadata: Optional[dict] = None, comment: Optional[str] = None, correction: Optional[dict] = None, feedback_config: Optional[Union[FeedbackConfig, dict]] = None, source_run_id: Optional[Union[uuid.UUID, str]] = None, target_run_id: Optional[Union[uuid.UUID, str]] = None, extra: Optional[dict] = None)

In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.

Subscribe
  • EvaluationResults
  • FeedbackConfig
  • BaseModel

Source: EvaluationResult | langsmith | LangChain Reference. Checked 2026-11-03.