Evaluator Bench
evaluator; distance from a lab: 1

Andon Labs

Scorecard

Long-horizon agent evaluations (Vending-Bench) and autonomous deployments; Anthropic Project Vend partner.

VC-backed, Stockholm, SE / San Francisco, US. Vendor / red-team co.; listed with commercial and first-party. Confidence low. Domains: autonomy, benchmarks.

Conditional floor 8/8 evidenced · Retrieved & confirmed Scores by preset: Lab procurement –; Regulator or auditor –; Public trust –; Equal weights –. Weakest evidenced dimension: governance 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. Funding disclosure and a COI policy would move this from low to medium confidence quickly.

Dissent, lower. Role incompatibility (X) at 1 could be 0. Andon sells Pion, a platform for running businesses autonomously, and deploys agents inside Anthropic and xAI offices while grading those labs' models on Vending-Bench; its own site says "Safety from humans in the loop is a mirage" and pitches the deployments as the safety layer. If a lab buys that layer, it is a monitoring product sold to an evaluated lab, which is anchor 0.

Dissent, higher. Role incompatibility (X) at 1 could be 2. No payment from any lab is documented: Anthropic describes Project Vend as a research partnership, the ledger records no fee, and Pion has no named customer. Absent a priced engagement, the record supports research collaboration with labs rather than services sold to them, which is closer to the anchor-2 consulting picture than to a vendor relationship.

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 2/4
Anchor 2: Labs pay per engagement; otherwise diversified.
evidence: tier 3 (self)
Capped at 2 by andon.03 (F.10): Commercial platform (Pion) and lab partnerships; funding and client mix not disclosed..
Governance 1/4
Anchor 1: Private for-profit with no published COI policy.
evidence: tier 3 (self)
Capped at 1 by andon.04 (G.1): No published COI policy found..
Personnel 2/4
Anchor 2: Frequent two-way hiring; recusal on request.
evidence: tier 3 (self)
Capped at 2 by andon.07 (P.6): Undisclosed..
Access depth (lab-granted) 1/4
Anchor 1: Pre-release API with safeguards on.
evidence: tier 4 (press)
mechanism: lab-controlled
Capped at 1 by andon.05 (A.1): Access through partnerships (Anthropic Project Vend); not routine pre-release..
Scope control 3/4
Anchor 3: Evaluator sets scope and can add questions.
evidence: tier 3 (self)
Floored at 3 by andon.06 (S.5): Designs its own long-horizon tasks.. No admissible signal caps it.
Publication rights 2/4
Anchor 2: Publishes; lab reviews with broad redaction.
evidence: tier 3 (self)
mechanism: self-imposed
Floored at 2 by andon.01 (R.7): Publishes candid results, including misalignment findings on the best-scoring models.. No admissible signal caps it.
Method transparency 2/4
Anchor 2: Methods described in prose.
evidence: tier 3 (self)
Floored at 2 by andon.11 (M.2): Vending-Bench is described in a public paper (arXiv 2502.15840); the simulated environment is run by Andon as a service and its code is not published.. No admissible signal caps it.
Role incompatibility 2/4
Anchor 2: Consults for labs.
evidence: tier 3 (self)
Capped at 2 by andon.08 (X.1): Sells a commercial agent platform..

Values under each evidence policy

DimensionLeads includedRetrieved & confirmedAgainst interestVerified spansPrimary only
Funding2222–
Governance1111–
Personnel2222–
Access depth (lab-granted)1111–
Scope control33–3–
Publication rights22–2–
Method transparency22–2–
Role incompatibility2222–
Score, Lab procurement– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 5/8– Conditional floor, 8/8– Unevidenced, 0/8
Score, Regulator or auditor– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 5/8– Conditional floor, 8/8– Unevidenced, 0/8
Score, Public trust– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 5/8– Conditional floor, 8/8– Unevidenced, 0/8
Score, Equal weights– Conditional floor, 8/8– Conditional floor, 8/8– Conditional floor, 5/8– Conditional floor, 8/8– Unevidenced, 0/8

Traced money and ties

hop 0: 1 row. Confirmed rows: 1 of 1 (1 excluded after a re-fetch disagreed or could not be verified: T55) Dollar sums: confirmed + unaudited USD rows only; imported figures are not re-derived and never summed. Second hop traced for 1 of 1 sources. Ties: none within two steps recorded. Checked and not found: 0.

Ledger

Money in

Roles hosted

One hop away

Anthropic, Y Combinator

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 Andon Labs 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)