kostis-init/CP-Bench-Leaderboard
Mark leaderboard as deprecated
Mark leaderboard as deprecated
Mark leaderboard as deprecated
Disable Gradio share tunnel on Space
update dockerfile
update dockerfile
update dockerfile
update dockerfile
update dockerfile
update dockerfile
update dockerfile
update dockerfile
update citation
handle different version names in dataset and in storage
update text
remove v2
update text
add default tab v2 in leaderboard
update eval logging
update eval logging
clean up model counting
fix when counting subm models
minor fix in desc
minor fix in desc
Add dataset versioning support and update leaderboard configuration
Add report file link to leaderboard and update column definitions
Sort leaderboard entries by "Final Solution Accuracy" in hf_utils.py
Fix indexing for leaderboard columns in hf_utils.py
Add base LLM and modelling framework to submission metadata; update leaderboard columns
Fix error percentage calculation in user_eval.py
Update README.md
Update README.md
Update README.md with project structure and development instructions; fix error percentage calculation in user_eval.py
Refactor evaluation logic: streamline user_eval.py, update evaluation script references, and clean up eval.py
Update README.md
Update README.md
update leaderboard entry parsing, enhance LLM client configuration, and correct submission file link
update leaderboard columns and enhance evaluation summary reporting
add dataset citation
update template.py
add template doc
add template script for generating constraint models using LLMs
update submission guidelines in UI text and add template script link
update Dockerfile to set QT_PLUGIN_PATH environment variable
update Dockerfile to use python:3.12-slim and add necessary dependencies
simplify Dockerfile by switching to full python:3.12 image and removing unused dependencies
update Dockerfile to include libegl1-mesa
remove unused constants and redundant imports; update Dockerfile dependencies
update Dockerfile to expose Gradio port and set library path
fix missing dirs
