Factual Grounding Evaluation on PubmedQA
0.84ROC-AUCDeepchecks Grounded in Context
Evaluation results
| Method | Links | |
|---|---|---|
| Deepchecks Grounded in ContextEvaluator=Proprietary SLM2026.05 | 0.84 | |
| RAGAS FaithfulnessEvaluator LLM=GPT-4o2026.05 | 0.8 | |
| Langsmith Answer FaithfulnessEvaluator LLM=GPT-4o2026.05 | 0.78 |