Data Agent Training Comparison
Visualize training and evaluation metrics for your project
RL Environments at Scale
Visualize training and evaluation metrics for your project
Run OpenCode data analysis tasks in a sandbox
Run a coding agent on a chosen data task via your model endpoint
Score multilingual OCR and document QA answers
Explore data tasks, run commands, and submit answers
Cross-model RL training, evaluation, and run history
Transcribe math images to LaTeX and receive a score
From an idea to a trained 4B, with the dead ends left in
Show live I/O tracking dashboard
Display your tracked metrics in a dashboard
Every painting of every run, with the sketch that made it
Show a live tracking dashboard
Interact with a GeoGuessrβlike environment
Show interactive tracking visualizations
Show interactive tracking visualizations
Display track information and visualizations