What it measures
Multi-file repository-level code completion and cross-file dependency retrieval benchmarks.
Reading the measurement
Look beyond a plausible code sample to the executable artifact. Tests, repository context, language coverage and time limits shape the result. Separate first-attempt correctness from success after debugging, retries or agent assistance.
Published evaluation
Exact match for the complete language subset, including cross-file and in-file examples. The adjacent edit-similarity column is a separate measure.
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
Exact match for the complete language subset, including cross-file and in-file examples. The adjacent edit-similarity column is a separate measure.
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 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.