Skip to main content
We are deprecating the following templates: content_moderation, factual_accuracy, content_safety_violation, is_factually_consistent, is_compliant, and recall_score.For new integrations, please use:
  • toxicity instead of content_moderation and content_safety_violation
  • groundedness instead of factual_accuracy and is_factually_consistent
  • data_privacy_compliance instead of is_compliant
  • recall_at_k, precision_at_k, ndcg_at_k, mrr, hit_rate instead of recall_score

Answer Refusal

Audio Quality

Audio Transcription

Bias Detection

BLEU

Caption Hallucination

Chunk Attribution

Chunk Utilization

Clinically Inappropriate Tone

Completeness

Content Moderation

Content Safety Violation

Context Adherence

Context Relevance

Conversation Coherence

Conversation Resolution

Cultural Sensitivity

Data Privacy

Detect Hallucination

Embedding Similarity

Eval Ranking

Factual Accuracy

Fuzzy Match

Groundedness

Instruction Adherence

Is Compliant

Is Concise

Is Email

Is Factually Consistent

Is Good Summary

Is Harmful Advice

Is Helpful

Is Informal Tone

Is JSON

Is Polite

Lavenshtein Similarity

Length Evals

LLM Function Calling

No Age Bias

No Apologies

No Gender Bias

No Harmful Therapeutic Guidance

No OpenAI Reference

No Racial Bias

Numeric Similarity

PII

Prompt Injection

Hit Rate

MRR

NDCG@K

Precision@K

Recall@K

Recall Score (Deprecated)

Rouge

Semantic List Contains

Sexist

Summary Quality

Synthetic Image Evaluator

Task Completion

Text-to-SQL

Tone

Toxicity

Translation Accuracy

Valid Links