Eval Studio

Eval Studio is a Python package for the introspection of machine learning models by enabling various facets of Responsible AI.

LLMs Evaluations

Evaluations with model explanations created by evaluators:

Evaluation 860a8508-67b0-4112-bc52-5ce11cea1fc4 (2026-01-22 17:11:16 T+0100)
- Dataset : <class 'h2o_sonar.lib.api.datasets._datasets_genai.LlmDataset'>
- Explainer(s) : 7
Evaluation 58eb5c72-1e1d-415a-a4ce-137fcef1670b (2026-01-22 17:09:41 T+0100)
- Dataset : <class 'h2o_sonar.lib.api.datasets._datasets_genai.LlmDataset'>
- Explainer(s) : 7

Eval Studio log

Eval Studio log with library runtime messages:

h2o-sonar.log

Please not that every evaluator has its own log and evaluator messages are not logged to the library log by default (check configuration documentation for more details).