BWhat changed
Continuously collected timestamped programming-contest problems and evaluated generation, repair, execution and test-output prediction to assess coding models beyond a static generation-only test.
Scientific scope
Continuously collected timestamped programming-contest problems and evaluated generation, repair, execution and test-output prediction to assess coding models beyond a static generation-only test. Contamination-free is a design goal relative to chosen release/training cutoffs, not independently guaranteed knowledge of every provider's training data. Original March2024 snapshot is distinct from later question totals and live rankings.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Contamination-free is a design goal relative to chosen release/training cutoffs, not independently guaranteed knowledge of every provider's training data. Original March2024 snapshot is distinct from later question totals and live rankings.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Jain et al.: time-windowed live code-generation and execution evaluation — original project
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction