Benchmark Almanac

Institute of Computer Science

We track 3 benchmarks that Institute of Computer Science made or helped make.

0 in use 3 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
FeatEng Models write Python functions to transform 103 tabular datasets. The score measures how much those changes reduce prediction error for an XGBoost model. Data science and SQL Oct 2024 11.1% Not in cards
PolEval 2025 Gender-inclusive Proofreading Models rewrite Polish passages that use generic masculine forms while preserving their meaning. Reading in many languages May 2025 Not in cards
PolEval 2025 Gender-sensitive Translation Models translate inclusive Polish passages into English and English passages into gender-inclusive Polish. Translation May 2025 Not in cards