Data · dataset · 2025
RExBench
Listed in Hugging Face Datasets
Dataset
Description
Summary
RExBench is a benchmark to test the ability of coding agents to autonomously implement realistic research hypothesis extensions which have not previously been implemented. The benchmark consists of 12 research experiment implementation tasks, where each task is set up as an extension to an existing research paper and codebase, accompanied by domain expert-written instructions. The original RExBench dataset was released… See the full description on the dataset page: huggingface.co/datasets/tin-lab/RExBench.
Links
Get the data
- Hugging Face dataset page huggingface.co/datasets/tin-lab/RExBench ↗
Gated (auto) - request access on the dataset page
landing page · request access · from Hugging Face
Documentation and papers
- arXiv:2506.22598 arxiv.org/abs/2506.22598 ↗
publication · from Hugging Face
Catalogue records · 1
- Hub API huggingface.co/api/datasets/tin-lab/RExBench ↗
metadata API · from Hugging Face
Topics
- From keywords
- Computer Science & AI
Provenance · 1 source records, 8 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| Hugging Face Datasets | tin-lab/RExBench | 15 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| access_level | source · Hugging Face | connector:huggingface@1.0.0 | /gated |
| concepts[field].local:field:computer-science-ai | mapping · Hugging Face | connector:huggingface@1.0.0 | |
| created_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| description | source · Hugging Face | connector:huggingface@1.0.0 | /description |
| license | source · Hugging Face | connector:huggingface@1.0.0 | /tags[license:*] |
| publication_date | source · Hugging Face | connector:huggingface@1.0.0 | |
| title | source · Hugging Face | connector:huggingface@1.0.0 | /id |
| updated_date | source · Hugging Face | connector:huggingface@1.0.0 |