Evaluator Bench
SecureBio, 2026; retrieved 2026-09-15 tier 3 self (securebio)confirmed

Conflicts of Interest Policy

https://securebio.org/ai/conflicts-of-interest/

Mandatory COI disclosure at hiring and every 6 months; recusal for financial interests, recent employment and close relationships with the assessed entity; no results-contingent funding; services revenue from AI companies held under 25% of annual revenue; free API credits from AI firms including those assessed. Fetched 2026-09-15; spans present.

Signals citing this source

  • SecureBio, F (against): Labs typically pay for evaluations of their own models; OpenAI covered the cost of the GPT-5.5 assessment.
  • SecureBio, X (against): SecureBio reports licensing its evaluations to multiple frontier labs as a revenue model and delivering pretraining data-filtering datasets and topic lists used in the design of several frontier models.
  • SecureBio, G (for): SecureBio publishes a conflicts-of-interest policy requiring recusal for financial interests or recent employment at the assessed entity and barring results-contingent funding.“Staff will be required to recuse themselves from engagements where an actual or perceived conflict of interest exists”
  • SecureBio, P (for): SecureBio's COI policy makes disclosure of conflicts mandatory for all AI-team staff at hiring and every six months, requires recusal, and its reports disclose conflicts relevant to each assessment.“All staff and contractors on our AI team must disclose potential conflicts of interest”
  • SecureBio, F (against): SecureBio's COI policy states that AI firms, including those whose models it assesses, provide it with free API credits, in undisclosed amounts.“AI firms, including those whose models we assess, provide us with free API credits”

Ledger rows citing this URL

  • none