Wild Bench

Multilingual: no

WildBench is an automated evaluation framework that benchmarks large language models using 1,024 challenging, real-world tasks selected from over one million human-chatbot conversation logs. It introduces two evaluation metrics (WB-Reward and WB-Score) that achieve high correlation with human preferences and uses task-specific checklists for systematic evaluation.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: communication, general, reasoning. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 5 of 5 results

Mistral Large 3 self-reported llm-stats

68.5%
Mistral Small 3.2 24B Instruct self-reported llm-stats

65.3%
Mistral Small 3 24B Instruct self-reported llm-stats

52.2%
Jamba 1.5 Large self-reported llm-stats

48.5%
Jamba 1.5 Mini self-reported llm-stats

42.4%