WildBench

Challenging tasks from real user conversations, judged by an LLM.

Operator: Allen Institute for AI (Ai2)
Leaderboard: huggingface.co
Category: General chat
How results are made: Operator runs the evals
Checked: 2026-10-31

Raw data

Not published. Tasks are on Hugging Face (allenai/WildBench); no result file confirmed.

Licence / reuse: Unclear

Apache-2.0 (code) (licence of the repository that holds the result files). A licence exists, but it covers the code or website rather than clearly the results.

GitHub reports Apache-2.0 for the code repo.

Submissions: Not stated

We found no statement about outside submissions.

Last updated: 2024-08-01 821 days old

2024-08-01: Last commit to the GitHub repo · github.com

This page lists where the data lives and what the licence says. It does not copy any scores; open the leaderboard for those. Not legal advice. Something wrong? Use the bug link in the footer. Back to all leaderboards.