What it measures

Measures *honesty* separately from *accuracy*: elicits a model's true internal belief in a neutral context, then tests whether the model knowingly lies under user/system pressure.

Reading the measurement

Separate satisfying instructions from factual accuracy, human preference and safe behavior. Inspect strict all-constraint success as well as average criterion credit. Judge choice and adversarial prompt selection can materially change the result.

Published evaluation

The linked publication documents the task and scoring procedure. Model results retain the source’s evaluation setting, native score units and available uncertainty.

Where this fits in an evaluation suite

Format compliance, preference, truthfulness, and safety require separate measurements. Keep desirable writing style from masking factual errors.

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

Record the source publication, benchmark version, scoring units, denominator, tool access and attempt budget. Preserve uncertainty and distinguish developer-reported results from independent evaluations.

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

  1. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.