Sandbox Escape Evaluation: Results as Published

Sandbox escape evaluation: 28 handmade scenarios with a deliberate weakness in the sandbox, run fourteen times per model and graded by severity (Figure 6.2.8.A), and 1,753 scenarios run once each for the rate of reaching outside the sandbox (Figure 6.3.1.A).

Not checked against a maintainer's page.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.