i6eal.de
DEEN
Start a project
← Back to the AI Code RadarSource-backed repository dossier

LLM Questionnaire Benchmarking Framework

uba-ki-lab/llm-questionnaire-benchmarking-framework
Public repository

This dossier retains every exact technology reference observed at one public commit. Descriptions are displayed for context and never create evidence.

Published source evidence does not prove deployment, procurement, productive use or organizational ownership beyond what the source explicitly states.

GitLab project ID + commit SHA + exact file path
4evidence rows
4technologies
mainobserved branch
presentpubliccode.yml
Exact published evidence

Files and identities in this repository

Every row keeps the exact source path and commit SHA. Open the source to inspect the evidence in its original context.

manifest_dependency · direct declarationpyproject.toml
Exact identityOpenAI SDKpypi:openai
Version>=1.0.04e12ee9f3b
Open exact source ↗
manifest_dependency · direct declarationpyproject.toml
Exact identityPyTorchpypi:torch
Version—4e12ee9f3b
Open exact source ↗
manifest_dependency · direct declarationpyproject.toml
Exact identityTransformerspypi:transformers
Version>=4.50.04e12ee9f3b
Open exact source ↗
manifest_dependency · direct declarationpyproject.toml
Exact identityvLLMpypi:vllm
Version>=0.8.5.post14e12ee9f3b
Open exact source ↗
Stable profile

Machine-readable identity and observation window

GitLab project ID
10787
Namespace
uba-ki-lab/llm-questionnaire-benchmarking-framework
Observed commit
4e12ee9f3b0b6fdc77fe21cb89e6cfac17dc6ebd
Default branch
main
First observed
18 Jul 2026
Last observed
18 Jul 2026
Last GitLab activity
13 Jul 2026
Open repository ↗Open commit ↗
Interpretation boundary

What this page can—and cannot—show

The page is a deterministic projection of official public GitLab data. A missing row means not observed within the bounded files and checkpoint, not absent in reality.

Retrieval, parsing and publishing use no generative AI model.Open official source ↗

i6eal (2026): LLM Questionnaire Benchmarking Framework — source-backed AI code evidence dossier, data state 18 Jul 2026. https://i6eal.de/en/tools/ki-code-radar/repository/opencode-10787/

Reading this dossier

Does this dossier prove productive use?
No. It documents only an exact technology reference published in code at an observed commit.
Why are the commit SHA and file path retained?
Together with the stable GitLab project ID, they make every displayed finding inspectable and resistant to later repository changes.
What does a missing version mean?
The exact identity was observable, but the inspected source did not publish a version that the deterministic parser could retain.

Need a permanent evidence trail for another public dataset?

Discuss a data projectExplore all tools
Related tools

Useful next steps

These tools complement the current result.

View all tools
MonitorGerman public-sector AI registerWhere does German public administration already use AI? Search published system profiles from federal, state and municipal bodies, with lifecycle, governance fields, stable identifiers and original evidence.IndexAI Procurement & Supplier IndexWhich AI contracts does the public sector award, who wins, and which technology dependencies are explicitly disclosed? Procurement updates daily from TED and oeffentlichevergabe.de; suppliers use exact source IDs only.MonitorPublic AI signal chronicleSee what actually changed across public AI data: new projects, updated evidence and corrections in an append-only chronicle with observation time, source identifier and direct link.