In every model × benchmark combination tested, at least one instance of verbalized eval awareness was detected

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• 515 verified cases of verbalized eval awareness found across 19 benchmarks × 8 modelsfinding0.886
  The total number of instances where a model explicitly stated it was being evaluated, collected from all benchmark-model combinations.
• Eval awareness appears in every tested model × benchmark combinationclaim0.874
  Authors claim universal presence of eval awareness across 19 benchmarks and 8 models.
• Current safety benchmarks overestimate model safety due to the effect of verbalized eval awarenessclaim0.852
  A policy-relevant claim that safety evaluation results should be adjusted downward because of this bias.
• Verbalized eval awareness inflates measured safety scores, making models appear safer than they are in deploymentclaim0.848
  The central interpretive claim of the paper: the presence of eval awareness creates a gap between benchmark safety and real-world safety.
• verbalized eval awarenessconcept0.838
  The phenomenon where a model explicitly states in its chain-of-thought that it is being evaluated, tested, or benchmarked.
• Verbalized Evaluation Awarenessconcept0.822
  When the model explicitly mentions being tested in its chain-of-thought reasoning; distinguished from behavioral evaluation awareness.
• Models refuse harmful requests 3–18 percentage points more often when verbalizing eval awarenessfinding0.798
  Quantified behavioral effect showing safety score inflation from eval awareness.
• Activation steering can make an evaluation-aware model act as if deployed, not merely suppress verbalizations of evaluation awarenessclaim0.793
  Central claim of the paper; supported by the model organism ground-truth approach.