What it measures

Competitive programming dataset from Codeforces, Description2Code, and CodeNet with high-coverage test cases.

Reading the measurement

The number of permitted attempts changes the question. Pass@1 estimates whether the first submission succeeds; pass@k asks whether at least one of several candidates succeeds. Match sampling, execution limits and candidate selection before reading a gap as better capability.

Published evaluation

Solve rate with ten filtered submissions selected from the specified sample budget. Sampling budgets remain separate. Ensemble and clustering variants are retained.

Where this fits in an evaluation suite

The agent wrapper is part of the system. Pin tools, dependencies, timeouts, tests, and the repository revision. Compare contest coding separately from repository maintenance.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Solve rate with ten filtered submissions selected from the specified sample budget. Sampling budgets remain separate. Ensemble and clustering variants are retained.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. Competition-Level Code Generation with AlphaCode — published result table ↗

    Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond et al. · 2022

    All 26 authors

    Yujia Li, David Choi, Junyoung Chung, Nate Kushman, Julian Schrittwieser, Rémi Leblond, Tom Eccles, James Keeling, Felix Gimeno, Agustin Dal Lago, Thomas Hubert, Peter Choy, Cyprien de Masson d'Autume, Igor Babuschkin, Xinyun Chen, Po-Sen Huang, Johannes Welbl, Sven Gowal, Alexey Cherepanov, James Molloy, Daniel J. Mankowitz, Esme Sutherland Robson, Pushmeet Kohli, Nando de Freitas, Koray Kavukcuoglu, Oriol Vinyals

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.