AI Potluck
Model components / Benchmark / eval datasets

IFEval

Google

Instruction-Following Eval: 541 prompts carrying about 25 types of verifiable instruction - word-count limits, keyword inclusion, format requirements - so that compliance can be scored programmatically rather than by a judge model. It is a core component of the Hugging Face Open LLM Leaderboard.

Verified 2026-08-13 via the google/IFEval dataset card on Hugging Face.

Openness

5 high confidence
5.0
license
Apache-2.0(OSI/open,redistributable)
access
public(not gated)
datasheet
present(card+structure+citation)
splits
public(single train split, no held-out)

Fully open: Apache-2.0, ungated, redistributable, with a complete dataset card.

  • https://huggingface.co/datasets/google/IFEval recorded 2026-08-13

    `license:apache-2.0` in the repo tags; the embedded repo state reads `"gated":false`; the dataset card still renders over the single public train split; 121,664 downloads in the trailing 30 days

Adoption

4 high confidence
4.0

116,029 Hugging Face downloads in the trailing 30 days for google/IFEval, which puts it in the 100K-1M band, level 4 on the dataset adoption scale. That scale tops out at >1M, an order of magnitude below the ones used for software and models, because no dataset in this corpus has ever passed 10M downloads. IFEval is a core benchmark on the Hugging Face Open LLM Leaderboard and the standard instruction-following evaluation.

Capability

not assessed

A dataset is not 'capable', so this axis is left unscored; openness and adoption carry this category.

Verified 2026-08-12