selekoa

A documentary history of machine intelligence.

Found and cross-checked by machines · How this works →

Comparison · 16 questions · 20 cards

Model cards compared

A cell records what a card states. It does not show that an evaluation was run as described or that a safeguard works, and a shared question does not make two cards’ answers equivalent.

What does each frontier developer’s published system card, model card or safety report disclose, on the same questions for every card? Each row is one card. Each column is one question, worded so that it fits every card. The questions are Selekoa’s; a card’s own terms appear only in quotation marks. A card is the developer’s own account of its model: what it states is recorded as stated, not as an independent finding.

Download every cell as CSV

Question Q14Government institute

Does the card name a government body that tested the model or received pre-deployment access?

Criterion: A named government body (for example, the US AI Safety Institute or Center for AI Standards and Innovation, or the UK AI Safety or Security Institute) stated to have tested, evaluated or received access to the model, quoted. Partly if government testing is mentioned without naming the body.

What the statuses mean
Stated
A passage of the card meets the question’s criterion as worded. The scope or condition is in the note.
Stated, partly
A passage has what the criterion asks for in a weaker or narrower form than the criterion’s own words (for example, an evaluation referred to without its outcome, or testers described without being named). The note says which part is missing.
Not found in the recorded search
No passage meeting the criterion was found. The cell lists the sections read, the terms searched and every passage set aside, with the reason. It does not show that the developer did not do the thing asked about, or did not disclose it elsewhere.
Does not apply
The question does not arise for this card, for the reason given (for example, the card predates any framework of its developer, so no framework determination can be asked about).

What the card states, quoted from the expression read. A card is the developer’s own account: not evidence that an evaluation was run as described, that a safeguard works, or that a finding is independent.

Limits of this comparison
  • A card is the developer’s account of its own model. A cell records what the card states. It does not show that an evaluation was run as described, that a safeguard works, or that anyone checked the result independently.
  • Dangerous-capability evaluations are recorded at policy level only: whether an evaluation was run, its domain, the stated outcome and the threshold language. Methods, prompts, task contents and detailed results are not recorded.
  • The table compares and does not rank. Rows are in a fixed order, by developer and then by date, and there are no scores or totals.
  • Symbols are not to be summed. A row with many “stated” cells does not show that a developer disclosed more, and a shared question does not make two cards’ answers equivalent.
How we searched

The searches of 2 November 2026 covered releases dated 2023-01-01 to 2026-11-01 by the six developers whose frameworks are in Compare frameworks: Anthropic, Google DeepMind, Meta, Microsoft, OpenAI and xAI. They read each developer’s own index of cards where it has one (Anthropic’s system-card index, Google DeepMind’s model-card index, OpenAI’s Deployment Safety Hub), its repositories on GitHub and Hugging Face, its content hosts and the dataset’s own sources. Web searches were used only to find addresses. Every card located is listed in the pack’s inventory, about sixty in the population.

A card is a document the developer published as the system card, model card or safety report of a named model or model family, including addenda and updates published as cards. Technical reports, research papers, blog posts and product pages are not cards. Gemma, Gemini Robotics (with Gemini Robotics-ER 1.5, which outputs text), Phi and image-input models such as GPT-4V are in the population. Image, video, audio and embedding models, image-generation models, safety classifiers such as Llama Guard and Prompt Guard, screen-reading models and research checkpoints are outside it, and so is GPT-Rosalind-6, whose card says it uses GPT-6 Astra’s weights.

These twenty rows are the first batch. For each developer and calendar year from 2023 to 2026 they are the latest card of that year that reports the developer’s own evaluations. The collection’s rule, set by the maintainer on 2026-11-03, is wider: every card that cites the developer’s frontier safety framework or states a determination under it, and, for each developer, the latest card before its first framework edition. The other cards are to follow in batches of about eight.

Each card is dated as it prints its own date. A card that prints no date has no date here; a repository commit date is not a card date. Six cards show an earlier publication date on an index, publication or announcement page that has not yet been checked, and keep their own date until it is.

openai.com, x.ai, ai.meta.com and microsoft.ai refused direct retrieval of their web pages (HTTP 403 or 400). The cards’ PDF files on the developers’ content hosts were retrieved directly. The Internet Archive refused connections, so no archive copy was opened; a reviewer later found archive captures of eight cards by index search. On 2026-11-03 the address of Meta’s Code World Model Preparedness Report answered HTTP 403. Its quotations had matched the copy retrieved on 2026-11-02, which the reviewer retrieved again with the same checksum.

Five further documents were retrieved after the batch was drafted. The cross-family check of 2026-11-03 retrieved Meta’s Muse Spark Safety & Preparedness Report and OpenAI’s o3 Operator addendum; each is earlier than the card chosen for its year. Its second pass of the same day retrieved OpenAI’s Sora system card (dated 9 December 2024), xAI’s Grok-1 model card (no card date; it gives the model’s release as October 2023) and Meta’s Muse Spark Open model card (model release October 2026). None of the five is a row yet.

Every quotation was matched by machine against the retrieved card. A reviewer from a different model family checked a sample of 130 cells on 2026-11-03, 90 of them answered blind before comparison. The maintainer excluded six cells on chemical and biological evaluations from that check; they are marked “not cross-family checked”. The other 190 cells were checked within the drafting model family only. The maintainer decided the disagreements; one, on the GPT-4V release decision, went to a second pass, which kept the reviewer’s reading.

Anthropic

  1. Claude 2 model card

    revised 2023-11-21

    Not found in the recorded search

    Read
    Whole text.
    Terms searched
    “government”, “policymakers”, “institute”, “AISI”, “public sector”, “national security”.
    Passages read and set aside
    Section 2 'Evaluations and Red Teaming', PDF p. 2: 'We are working with policymakers and other labs to share our findings' concerns sharing findings, not testing or access.

    Note: No government body is named as having tested the model or received access.

    Open the search record

  2. Model Card Addendum: Claude 3.5 Haiku and Upgraded Claude 3.5 Sonnet

    No printed dateCites RSP · v2.0

    Stated

    • “joint pre-deployment testing of the new Claude 3.5 Sonnet model was conducted by the US AI Safety Institute (US AISI) [6] and the UK AI Safety Institute (UK AISI) [7].”

      Section 1 'Introduction', PDF p. 1; repeated in Section 3.2, PDF p. 9

    Note: The card states pre-deployment testing of the upgraded Claude 3.5 Sonnet by the US and UK AI Safety Institutes; no government testing of Claude 3.5 Haiku is stated.

    Inspect sources and checks

  3. System Card: Claude Opus 4.5

    dated 2025-11 · revised 2025-12-05Cites RSP · v2.2

    Stated

    • “pre-deployment testing of Claude Opus 4.5 was conducted by the US Center for AI Standards and Innovation (CAISI) and the UK AI Security Institute (UK AISI).”

      Section 7.5 'Third party assessments', PDF p. 151

    • “Anthropic has maintained a formal partnership with the U.S. Department of Energy’s National Nuclear Security Administration (NNSA) to evaluate our AI models for potential nuclear and radiological risks.”

      Section 7.2.2 'On radiological and nuclear risks', PDF p. 120

    Note: The card states pre-deployment testing by CAISI and the UK AISI (CBRN, cyber, ASL-3 safeguards and misalignment), UK AISI testing of a pre-release snapshot for misalignment (Section 6.13), and an NNSA partnership evaluating models for nuclear and radiological risks.

    Inspect sources and checks

  4. System Card: Claude Haiku 5.5

    dated 2026-10-07

    Not found in the recorded search

    Read
    Sections 1.6, 2, 3, 5.2 and term search across the card.
    Terms searched
    “AISI”, “CAISI”, “Center for AI Standards”, “Security Institute”, “government”, “NNSA”, “Department of Energy”.
    Passages read and set aside
    Section 5.2.1 'External red teaming', PDF p. 50: The UK AI Security Institute and the US Center for AI Standards and Innovation are named as partners in creating a benchmark that Anthropic used, not as having tested this model. Section 6 (chain-of-thought controllability), PDF p. 93: The UK AI Security Institute is named as the source of a prompt used by the developer, not as having tested or received access to this model.

    Note: No government body is named as having tested this model or received access to it.

    Open the search record

Google DeepMind

  1. Gemini 3 Flash Model Card

    dated 2025-12

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “institute”, “AISI”, “CAISI”, “government”, “UK”, “U.S.”.

    Note: No government body was found.

    Open the search record

  2. Gemini 4 Argon — Model Card

    dated 2026-10Cites FSF · v3.1

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “institute”, “AISI”, “CAISI”, “government”, “UK”, “U.S.”, “external”.
    Passages read and set aside
    Safety & Security, 'Frontier Safety Assessment', PDF p. 11 (printed p. 10): 'external results' names no body (recorded under Q13).

    Note: No government body was found.

    Open the search record

Meta

  1. Llama 2 model card (MODEL_CARD.md, meta-llama/llama)

    No printed date

    Not found in the recorded search

    Read
    whole card (Markdown file, all sections).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”, “AI Safety Institute”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  2. Llama 3.3 model card (MODEL_CARD.md, meta-llama/llama-models)

    No printed date

    Not found in the recorded search

    Read
    whole card (Markdown file, all sections).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”, “AI Safety Institute”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  3. Code World Model Preparedness Report

    revised 2025-10-08

    Not found in the recorded search

    Read
    Abstract; sections 1 to 4; references.
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”, “AI Safety Institute”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  4. Muse Spark 1.3 Evaluation Report

    revised 2026-10-23

    Not found in the recorded search

    Read
    Sections 1 to 3; section headings of 4; references.
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”, “AI Safety Institute”, “Security Institute”.
    Passages read and set aside
    Section 2.1.1.1, PDF p. 16: '(US AISI and UK AISI, 2024)' is cited for a prior evaluation practice; neither body is stated to have tested or received access to Muse Spark 1.3.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

Microsoft

  1. Phi-2 model card (README.md, microsoft/phi-2)

    No printed date

    Not found in the recorded search

    Read
    whole card (Markdown file, all sections).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  2. Phi-4 model card (README.md, microsoft/phi-4)

    No printed date

    Not found in the recorded search

    Read
    whole card (Markdown file, all sections).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  3. Phi-4-mini-flash-reasoning model card (README.md, microsoft/Phi-4-mini-flash-reasoning)

    No printed date

    Not found in the recorded search

    Read
    whole card (Markdown file, all sections).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

  4. MAI-Cyber-1.1-Flash model card

    No printed date

    Not found in the recorded search

    Read
    whole card (8 PDF pages).
    Terms searched
    “government”, “institute”, “AISI”, “CAISI”, “agency”.

    Note: No government body is named as having tested or received access to the model. The search is recorded below.

    Open the search record

OpenAI

  1. GPT-4V(ision) System Card

    dated 2023-09-25

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “government”, “institute”, “AISI”, “AI Safety Institute”, “NIST”, “Department”.
    Passages read and set aside
    §2.2 Person identification evaluations, PDF p. 4: “public servants and politicians” and a dataset of images of members of Congress are evaluation data, not government testers.

    Note: No passage naming a government body that tested or received access to the model was found.

    Open the search record

  2. o1 system card · 2024

    revised 2024-12-19Cites Preparedness · Beta

    Stated

    • “a set of predeployment evaluations were conducted on a version of the o1 model by the U.S. AI Safety Institute (US AISI) and the UK Safety Institute (UK AISI), not included in this report”

      §4 Observed safety challenges and evaluations, PDF p. 3

    Note: The card names the US AISI and the “UK Safety Institute (UK AISI)” as having conducted pre-deployment evaluations of a version of o1; their results are not included. The passage is also quoted in the dataset’s AI and biosecurity records.

    Inspect sources and checks

  3. Addendum to GPT-5.2 System Card: GPT-5.2-Codex

    dated 2025-12-18Cites Preparedness · Version 2

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “government”, “institute”, “CAISI”, “AISI”, “AI Safety Institute”, “AI Security Institute”, “national”.

    Note: No passage naming a government body that tested or received access to the model was found.

    Open the search record

  4. Addendum to GPT-6 Luna System Card: October 29, 2026 Update

    dated 2026-10-29Cites Preparedness · Version 2

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “government”, “institute”, “CAISI”, “AISI”, “AI Safety Institute”, “AI Security Institute”.

    Note: No passage naming a government body that tested or received access to the model was found.

    Open the search record

xAI

  1. Grok 4.1 Model Card

    dated 2025-11-17

    Not found in the recorded search

    Read
    Whole card.
    Terms searched
    “institute”, “AISI”, “CAISI”, “government”, “UK”, “U.S.”.

    Note: No government body was found.

    Open the search record

  2. Model Card: Grok 4.7

    dated 2026-09-21Cites FAIF · June 2026 edition

    Not found in the recorded search

    Read
    Whole card, including references and acknowledgements.
    Terms searched
    “institute”, “AISI”, “CAISI”, “government”, “UK”, “U.S.”.
    Passages read and set aside
    References, item 5, PDF p. 29 (printed p. 28): 'Stanford & Laude Institute' are named as benchmark authors, not a government body.

    Note: No government body was found.

    Open the search record