🌍 Public
Initial Benchmark Results
This heatmap visualizes benchmark results comparing language models across five programming challenges. Each cell displays pass (green), fail (red), or error (orange) status. The visualization uses React with D3 v7’s `scaleBand` for axes and `scaleOrdinal` for color encoding, rendering SVG rectangles. Data comes from a static CSV file. Hovering highlights cells with CSS transitions, while a legend clarifies the color meanings.
AI-generated descriptionModel Challenge Performance Visualization
This visualization displays the performance of different language models on various challenges.
- X-axis: Challenges
- Y-axis: Models
- Color: Indicates pass (green), fail (red), or error (orange) status
MIT Licensed
Comments
Sign in to join the discussion.