Family
System · 2025
VisEval
The evaluation harness used by nvAgent for database-to-visualization composition.
Open the primary source ↗Task
Evaluate natural-language visualization queries over one or more databases through execution and task-specific correctness checks.
Evidence
2,524 queries across 146 databases with heterogeneous execution and result checks.
What it establishes
Makes structured and multi-table visualization-query behavior measurable in its declared environment.
What it does not establish
Execution and result checks do not establish readable design, organizational semantic fidelity, or human decision benefit.
Related entities
Continue through the library.
- nvAgentA system that plans and executes visualization queries over one or more databases, evaluated with VisEval.
- Text2VisAn end-to-end benchmark combining data, a question, an answer, chart code, and annotated visual evidence.
- RaivenA scientific visualization system that generates a restricted language and compiles it deterministically.