Reported in recent model launches
These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.
What it measures
Security-oriented software evaluation appears in recent model capability reports.
How to read the result
Read it as a specialist engineering result, with the original scoring definition and evaluation configuration retained.
Limits and comparison traps
The launch table supplies less detail than a full task release. Avoid extrapolating from the headline to unrestricted security workflows.
Benchmark reference notes
Real-world CVE reproduction, vulnerability localization, and security patching benchmark.
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
Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.
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.