allenai/WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

Open All

4 open issues indexed

The Replacement of Open-source JudgeModel/Evaluator Open

allenai/WildBench#19 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Question about length bias mitigation in pairwise evaluation Open

allenai/WildBench#20 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
Human preference result Open

allenai/WildBench#21 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 13, 2026
[ADD_MODEL] Open

add_model

allenai/WildBench#24 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 13, 2026

Get new issues in your inbox