jiang_2026_openeval_ifeval

66,152 responses from 124 respondents to 541 items.

About this table

DescriptionAI models as respondents: 124 large language models (id = model name, verbatim, aliases not merged) scored on the 541 prompts of IFEval, an instruction-following benchmark whose prompts each carry 1-3 programmatically verifiable instructions (e.g. no commas, at least 300 words). resp is the number of the prompt's instructions the model's response satisfied under IFEval's strict check (0 to itemcov_n_instructions); resp == itemcov_n_instructions is prompt-level strict accuracy. From the OpenEval archive (Hugging Face Open-Eval-Commons/OpenEval, revision 23a1ded9), one run, scores only. Respondents are not independent: many models share base weights, decoding temperature varies across models (cov_temperature), and items may appear in training data.
ReferenceJiang, H., Zhang, S., Zhu, D., Bai, Y., Truong, S. T., Yi, X., Koyejo, S., Xie, X., & Xiao, Z. (2026). AI Evaluation Should Require Standardized Item-Level Data Releases. arXiv:2604.03244 (v2). Benchmark: Zhou, J., et al. (2023). Instruction-Following Evaluation for Large Language Models. arXiv:2311.07911.
DOI10.48550/arXiv.2604.03244
LicenceCC BY-NC 4.0
Source datahttps://huggingface.co/datasets/Open-Eval-Commons/OpenEval/tree/23a1ded985b3c2cdaaddb27581a35bfabe0ad7e7

Size and shape

Responses66,152
Respondents124
Items541
Response categories4
Responses per respondent533.484
Responses per item122.277
Density0.986
LongitudinalFALSE

Classification

age rangeNot applicable (non-person)
sampleAI/model
construct typeCognitive/educational
measurement toolTest
item formatConstructed Response
primary language(s)eng
construct nameIFEval instruction following (verifiable instructions, strict check)

Columns

cov_model_sizecov_temperatureiditemitemcov_n_instructionsresp

Get the data

Licence: CC BY-NC 4.0 — non-commercial use only.

Download CSVno account neededBrowse on Redivisexplore and queryCroissant metadataHugging Face, Kaggle, OpenML

Or load it directly in R or Python:

# R
install.packages("remotes")
remotes::install_github("itemresponsewarehouse/Rpkg")
library(irw)
df <- irw_fetch("jiang_2026_openeval_ifeval")
# Python
pip install irw

import irw
df = irw.fetch("jiang_2026_openeval_ifeval")

How to cite

@misc{https://doi.org/10.48550/arxiv.2604.03244,
  doi = {10.48550/ARXIV.2604.03244},
  url = {https://arxiv.org/abs/2604.03244},
  author = {Jiang, Han and Zhang, Susu and Zhu, Dongyao and Bai, Yuzhuo and Truong, Sang T. and Yi, Xiaoyuan and Koyejo, Sanmi and Xie, Xing and Xiao, Ziang},
  keywords = {Artificial Intelligence (cs.AI), Computers and Society (cs.CY), Databases (cs.DB), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {AI Evaluation Should Require Standardized Item-Level Data Releases},
  publisher = {arXiv},
  year = {2026},
  copyright = {Creative Commons Attribution 4.0 International}
}

Version and provenance

IRW versionv407
Redivis datasetitem_response_warehouse_6 v3.2
Redivis dataset DOI10.57761/yvkw-nj32
Manifest pin for this IRW versionv3.2
Metadata sourceirw_meta v24.0