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
A controlled security benchmark appears in MiniMax’s recent model capability report.
How to read the result
Retain the exact task release, harness, safeguards, and success rule when interpreting a reported result.
Limits and comparison traps
A contained benchmark result is not evidence for unrestricted autonomous security operation. This article does not provide operational exploit instructions.
Benchmark reference notes
Large-scale real-world OSS cybersecurity evaluation gym reported in MiniMax M3.1 Flash.
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.