Family
Benchmark · 2026
DashArena
A benchmark, browser executor, and human-calibrated judge for open-ended interactive dashboard generation.
Open the primary source ↗Task
Generate a single-file dashboard and a two-turn intended-use trajectory for 234 open-ended tasks.
Evidence
Browser render and replay, schema and execution receipts, and human-calibrated pairwise judging.
What it establishes
Adds task-grounded interaction evidence and shows that current systems can attempt analytical dashboards while remaining unreliable in render, replay, and semantics.
What it does not establish
Model-authored trajectories and Tableau-derived tasks do not represent every audience, device, decision, or production environment.
Related entities
Continue through the library.
- Dashboard2CodeA benchmark for reconstructing interactive Plotly Dash applications from screenshots, optional DOM, and interaction.
- RealChart2CodeA chart-to-code benchmark built from real source data, multi-panel tasks, and iterative refinement.
- ChartographyA deliberately difficult set of practitioner-authored professional chart-reading tasks.