Skip to content
masterclass Buddy
Start learning

AI & ML · Concept

BLEU

Graders measure model outputs against references or grading prompts. Text similarity graders use fixed metrics; score model graders ask another model for a numeric score.

Last updated

Syntax

{"type":"text_similarity","name":string,"input":string,"reference":string,"pass_threshold":number,"evaluation_metric":"fuzzy_match"|"bleu"|"gleu"|"meteor"|"cosine"|"rouge_1"|"rouge_2"|"rouge_3"|"rouge_4"|"rouge_5"|"rouge_l"}

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

Subscribe
  • Evals
  • Reinforcement fine-tuning
  • text-embedding-3-large
  • fuzzy_match
  • BLEU
  • GLEU
  • METEOR
  • ROUGE

Source: Graders | OpenAI API. Checked 2026-11-03.