📁 Metrics¶
- 📁 Bert Score
- 📁 Granite Guardian
- 📁 Key Value Extraction
- 📁 Llm As Judge
- 📁 Perplexity
- 📁 Perplexity A
- 📁 Perplexity Chat
- 📁 Perplexity Nli
- 📁 Perplexity Q
- 📁 Qa
- 📁 Rag
- 📁 Reward
- 📁 Robustness
- 📁 Sentence Bert
- 📁 Text2Sql
- 📄 Accuracy
- 📄 Accuracy Binary
- 📄 Anls
- 📄 Bleu
- 📄 Char Edit Dist Accuracy
- 📄 Char Edit Distance
- 📄 Exact Match Mm
- 📄 F1 Binary
- 📄 F1 Macro
- 📄 F1 Macro Multi Label
- 📄 F1 Micro
- 📄 F1 Micro Multi Label
- 📄 F1 Strings
- 📄 F1 Weighted
- 📄 Fin Qa Metric
- 📄 Fuzzyner
- 📄 Is Code Mixed
- 📄 Jaccard Index
- 📄 Kendalltau B
- 📄 Kpa
- 📄 Map
- 📄 Matthews Correlation
- 📄 Max Accuracy Binary
- 📄 Max F1 Binary
- 📄 Meteor
- 📄 Meteor Hf
- 📄 Mrr
- 📄 Ndcg
- 📄 Ner
- 📄 Normalized Sacrebleu
- 📄 Precision Binary
- 📄 Precision Macro Multi Label
- 📄 Precision Micro Multi Label
- 📄 Prediction Length
- 📄 Recall Binary
- 📄 Recall Macro Multi Label
- 📄 Recall Micro Multi Label
- 📄 Regard Metric
- 📄 Relaxed Correctness
- 📄 Rerank Recall
- 📄 Retrieval At K
- 📄 Roc Auc
- 📄 Rouge
- 📄 Rouge With Confidence Intervals [deprecated]
- 📄 Sacrebleu
- 📄 Safety Metric
- 📄 Spearman
- 📄 Squad
- 📄 String Containment
- 📄 String Containment Ratio
- 📄 Token Overlap
- 📄 Token Overlap With Context
- 📄 Unsorted List Exact Match
- 📄 Vectara Groundedness Hhem 2 1
- 📄 Websrc Squad F1
- 📄 Weighted Win Rate Correlation
- 📄 Wer
Read more about catalog usage here.