InnerVault

confabulations

Stale GitHub, lechmazur

Hallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.

Open the source (opens github.com) https://github.com/lechmazur/confabulations

What it is

Datasets & benchmarks from lechmazur.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

How to get it

Get the code

git clone https://github.com/lechmazur/confabulations.git

Standard git access to a public repository

Setup steps: not provided by the source. Follow the instructions on the source.

Related

  1. Simreal-MLBench

    Datasets & benchmarks

    [Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

    Stale GitHub, Simreal-AI 301 ★Apache-2.0Updated 53 days ago

    git clone https://github.com/Simreal-AI/Simreal-MLBench.git
  2. nyt-connections

    Datasets & benchmarks

    Benchmark that evaluates LLMs using 759 NYT Connections puzzles extended with extra trick words

    Indexed GitHub, lechmazur 250 ★Updated 5 days ago

    git clone https://github.com/lechmazur/nyt-connections.git
  3. geobench

    Datasets & benchmarks

    GeoGuessr benchmark for language models

    Indexed GitHub, ccmdi 65 ★MITUpdated 3 days ago

    git clone https://github.com/ccmdi/geobench.git
  4. claude-protein-binder-design

    Datasets & benchmarks

    Hugging Face dataset by Anthropic

    Indexed Hugging Face Hub, Anthropic 244 ♥cc-by-4.0Updated 3 months ago

    Anthropic/claude-protein-binder-design
  5. nautilus-compass

    Datasets & benchmarks

    Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

    Indexed GitHub, chunxiaoxx 1,258 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/chunxiaoxx/nautilus-compass.git
  6. seo-skill-bench

    Datasets & benchmarks

    Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic scoring, pre-registered rubric.

    Stale GitHub, aleclindz 51 ★MITUpdated 32 days ago

    git clone https://github.com/aleclindz/seo-skill-bench.git