Update benchmark_report.json with new model names and performance metrics; enhance about.py with updated dataset size, subcategories, and author details for the Polish Cultural Vision Benchmark (PCVB) v2.

Update README to reflect the new title and emoji for the Polish Cultural Vision Benchmark (PCVB).

Update benchmark_report.json

Update benchmark_report.json

Update benchmark_report.json

Comment out CSV file input in app.py to streamline data handling following recent refactor to JSON. This change enhances clarity and aligns with the updated data structure.

Refactor app.py to use JSON for benchmark data, removing CSV and metadata dependencies. Update performance plotting to reflect new data structure and enhance visualization with cultural context. Introduce benchmark report JSON file for structured model evaluation results.

Update metadata.json

Update benchmark_results.csv

Update benchmark_results.csv

Update benchmark_results.csv

Update benchmark_results.csv

Update app.py

metadata

new models

Fix GPU precision label in performance plot

update

update gradio

update

generate static page leaderboard

Update metadata.json

beilik v2.3

asd

update eq-bench

Change the way the parsable questions are expressed from numerical to percentage (#1)

Update README.md

Update README.md

Update README.md

Update README.md

eq bench

eq bench

eq bench

eq bench

eq bench

eq bench

eq bench

eq bench

eq bench

Update README.md

initial commit

Duplicate from demo-leaderboard-backend/leaderboard