Code generation benchmarks
LiveCodeBench
Compare code-generation Pass@1 by problem release date and difficulty, with configurations and evaluation scope retained.
Source & report coverage
- Source type
- Code generation benchmarks
- Report snapshots
- 1 reports
- Data as of
- 2026-10-31
Sources and individual reports are listed separately. Each snapshot retains its subjects, tasks, metrics and conditions. External scores are not our own measurements and are not added across reports.
Reports & historical snapshots
- LiveCodeBench code generation · 2024-08-01 to 2025-05-01 →
Observed2026-10-19 · 28subject / run records ·4independent metrics