🧠 Reasoning Trace Explorer

📊

Select a dataset and model to explore reasoning traces

📈

Select a dataset to view model performance comparison

🔄

Select a dataset to view redundancy analysis

↩️

Select a dataset to view backtracking analysis

🎓

Select a dataset to view Transfer Utility (TU) analysis

🔗 Correlations

Render correlation heatmaps across metrics from the precomputed correlation results JSON.

Heatmap

🧩

Load correlation metadata to begin

If correlations aren’t available, ensure the correlation results JSON exists on the server.

📊 Model Leaderboard

Aggregated model rankings across all metrics (accuracy, efficiency, redundancy, backtracking, Transfer Utility)

📊

Loading leaderboard data...