What it measures
307 USA Computing Olympiad problems across Bronze, Silver, Gold, and Platinum divisions.
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
Pass@1 over the source 307-problem USACO benchmark. The method is part of the agent identity; this is distinct from contest submission budgets.
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
Pass@1 over the source 307-problem USACO benchmark. The method is part of the agent identity; this is distinct from contest submission budgets.
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
Reviewed 2026-10-27. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.