Running
221
🦁
WildBench
Note The leaderboard for visualizing the results and collecting human feedback.
allenai/WildBench
Viewer • Updated • 2.3k • 2.36k • 34Note Examples for evaluating LLMs.
allenai/WildBench-V2-Model-Outputs
Viewer • Updated • 62.5k • 1.48k • 2Note The model outputs for verified LLMs on the leaderboard.
-
WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
Paper • 2406.04770 • Published • 27