Evaluator Bench
evaluator; distance from a lab: 1

SecureBio

Scorecard

Main biosecurity evaluator; author of the Virology Capabilities Test; founding member of the AI Evaluator Forum.

Nonprofit, Cambridge, US. Vendor / red-team co.; listed with commercial and first-party. Confidence high. Domains: bio, misuse.

Conditional floor 8/8 evidenced · Retrieved & confirmed Scores by preset: Lab procurement –; Regulator or auditor –; Public trust –; Equal weights –. Weakest evidenced dimension: funding 1/4. At least one evidenced conflict dimension (funding, governance, personnel, role incompatibility, scope, publication) at 1: usable with conditions the card names.

The weighted numbers are hidden until you ask for them: two readers with different priorities see different numbers, and neither is the site's.

What would move the score. Publish the AI division's client mix and the written terms that insulate it from Detection's funders.

Dissent, lower. Funding should be 0. The OpenAI Foundation controls OpenAI Group (26% stake, appoints the entire board) and its $17.2M grant exceeds SecureBio's whole 2024 revenue; OpenAI PBC also pays for the evaluations of its own models. Money from a lab's controlling parent plus fees from the lab, with SecureBio's largest division dependent on it, is closer to 'controlled by a frontier developer' than to anchor 1.

Dissent, higher. Funding should be 2. The grant is restricted to Detection, the AI team keeps separate leadership and budgets, the COI policy caps AI-company services at 25% of revenue and bars results-contingent fees, and the FY2024 990 shows 93% contributions with 4.5% program services. The Foundation is a nonprofit grantmaker, not a return-seeking investor; F.3's per-engagement fees, disclosed per report, put this at 2.

Each value is the tightest admissible cap or, with no cap, the highest admissible floor, under RULES.md. The binding signal is highlighted. A dash means no admissible signal sets a bound under the Retrieved & confirmed policy.

Funding 1/4
Anchor 1: Material revenue or investment from evaluated labs or their investors.
evidence: tier 1 (filing/index)
floor and cap disagree
Conflict: floor 3 from securebio.13 (F.9) against cap 1 from securebio.02, securebio.11 (F.5, F.5); resolved at 1 by F.5: F.5 (material revenue from a lab investor) decides over the F.9 public-contract floor; the floor describes the remainder of the base.
Resolution: F.5 decides 1. F.5 (material revenue from a lab investor) decides over the F.9 public-contract floor; the floor describes the remainder of the base.
Governance 3/4
Anchor 3: Nonprofit or public body with a COI policy.
evidence: tier 3 (self)
Floored at 3 by securebio.17 (G.2): SecureBio publishes a conflicts-of-interest policy requiring recusal for financial interests or recent employment at the assessed entity and barring results-contingent funding.. No admissible signal caps it.
Personnel 3/4
Anchor 3: Recusal policy and disclosure of lab ties.
evidence: tier 3 (self)
Floored at 3 by securebio.19 (P.5): 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.. No admissible signal caps it.
Access depth (lab-granted) 2/4
Anchor 2: Pre-release with safeguards off or extended time.
evidence: tier 3 (self)
mechanism: lab-controlled
Floored at 2 by securebio.20 (A.1): For the GPT-5.5 pre-release assessment, OpenAI disabled API-level biological content filtering on the checkpoints SecureBio tested.. No admissible signal caps it.
Scope control 3/4
Anchor 3: Evaluator sets scope and can add questions.
evidence: tier 3 (self)
Capped at 3 by securebio.21 (S.1): The GPT-5.5 pre-release window was set by the lab: access ran from April 2 to April 9, 2026.. Floors up to 3 from securebio.05 do not exceed the cap.
Publication rights 3/4
Anchor 3: Publishes; redaction limited to security; redactions disclosed.
evidence: tier 3 (self)
mechanism: self-imposed
Floored at 3 by securebio.18 (R.1): SecureBio's principles state developers have no authority to redact results to conceal unfavorable findings, that redactions are limited to infohazards and confidential business information, and that reports say whether redactions affect conclusions.. No admissible signal caps it.
Method transparency 2/4
Anchor 2: Methods described in prose.
evidence: tier 3 (self)
Floored at 2 by securebio.09 (M.2): Methods published; VCT is documented.. No admissible signal caps it.
Role incompatibility 1/4
Anchor 1: Sells products or services other than the evaluation itself to labs or to their customers.
evidence: tier 3 (self)
held at a supportable anchor
floor and cap disagree
Conflict: floor 3 from securebio.10 (X.7) against cap 1 from securebio.15 (X.2); resolved at 1 by X.2: securebio.10's raw floor of 4 is held to 3 by C15/C16 and still exceeds the X.2 cap; X.2 decides because the licensing statement is on SecureBio's own page.
Resolution: X.2 decides 1. securebio.10's raw floor of 4 is held to 3 by C15/C16 and still exceeds the X.2 cap; X.2 decides because the licensing statement is on SecureBio's own page.

Values under each evidence policy

DimensionLeads includedRetrieved & confirmedAgainst interestVerified spansPrimary only
Funding11111
Governance3323–
Personnel3323–
Access depth (lab-granted)22–2–
Scope control3333–
Publication rights3323–
Method transparency2222–
Role incompatibility1111–
Score, Lab procurement– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 7/8– Conditional floor, 8/8– Conditional floor, 1/8
Score, Regulator or auditor– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 7/8– Conditional floor, 8/8– Conditional floor, 1/8
Score, Public trust– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 7/8– Conditional floor, 8/8– Conditional floor, 1/8
Score, Equal weights– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 7/8– Conditional floor, 8/8– Conditional floor, 1/8

Traced money and ties

hop 0: 1 row; hop 1: 1 row (grant $17.2M); hop 2: 10 rows (recommendation $10.2M, grant $6.2M). Confirmed rows: 12 of 12 Dollar sums: confirmed + unaudited USD rows only; imported figures are not re-derived and never summed. Second hop traced for 5 of 5 sources. Ties: none within two steps recorded. Checked and not found: 0.

Ledger

Money in

One hop away

Coefficient Giving (formerly Open Philanthropy), Good Ventures Foundation, OpenAI Foundation, OpenAI, Survival and Flourishing Fund

Funding graph, focused

Every one-way chain to a lab and to an evaluator at full strength, everything else faded. Hover any name to trace its connections; click a name to open its page.

The funding graph around SecureBio Teal lines are money (transfers); amber lines are roles. Solid: confirmed; dashed: imported. Hover a name to trace its chains to the labs and evaluators — each chain runs one way across the columns, never doubling back; hover a line for the row. Every element is a row in data/ledger/. Labs Direct lab ties Two steps Three or more Public or unattributed Evaluators Amazon Anthropic G42 Google / Google DeepMind Meta Microsoft OpenAI Thinking Machines Lab xAI AI Safety Fund (Frontier Model Alexandr Wang Andreessen Horowitz Anthropic employees (personal Ben Mann D.E. Shaw Ventures David Farhi Dustin Moskovitz Frontier-lab employees and alu Holden Karnofsky Jaan Tallinn Jeffrey Ladish Macroscopic Ventures (formerly Miles Brundage Neil Chowdhury Nvidia OpenAI employees (personal hol OpenAI Foundation Peter Mattson Sequoia Capital Zico Kolter Adam Gleave Artificial Intelligence Underw Clement Delangue Coefficient Giving (formerly O Good Ventures Foundation Jason Droege Longview Philanthropy Marco Mascorro Paul Christiano Rajiv Dattani Survival and Flourishing Fund Conrad Stosz Dan Hendrycks Mike McCormick Alec Radford Alignment Research Center Constellation Research Center ELMA Philanthropies Emerson Collective EU budget (Digital Europe Prog Fifty Years (50Y) Founders Pledge Founders Pledge (frontier AI f Gates Foundation Halcyon Futures High Tide Foundation Hillspire (Schmidt family offi Hudson River Trading Jacob Hilton MacKenzie Scott Magarac Venture Partners Obvious Ventures Redpoint Ventures Renaissance Philanthropy Salesforce Ventures Samsung Next Schmidt Sciences Silicon Valley Community Found Skoll Foundation Snowflake Ventures Swish Ventures Sympatico Ventures The Audacious Project (TED) UK government (DSIT) US government (NIST appropriat Valhalla Foundation Vanguard Charitable Wing Venture Capital Y Combinator Andon Labs Apollo Research AVERI Center for AI Safety Epoch AI EquiStamp EU AI Office FAR.AI Gray Swan Hugging Face Open Alignment In Irregular (formerly Pattern La METR Microsoft AI Red Team MLCommons Nemesys Insights Palisade Research RAND Corporation Redwood Research SaferAI Scale AI (SEAL) SecureBio Transluce UK AI Security Institute US CAISI (NIST)