Benchmark

LiveBench 20241125

math reasoning general text

LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

榜单来源

Top 10

榜单概览

1Qwen3-235B-A22B-Thinkin…78.42Qwen3-Next-80B-A3B-Thin…76.63Qwen3-Next-80B-A3B-Inst…75.8
数据说明

分数为 0-100 百分制综合成绩（Elo 榜为相对评分，仅供同榜内比较）。评测分数属事实数据，整理自公开评测体系与厂商公开资料，部分分数为厂商自报口径，不同榜单的评测方法与数据集可能存在差异，请结合多个榜单交叉参考。

Ranking

模型排名

名次 模型 机构 分数 来源
1 Qwen3-235B-A22B-Thinking-2507 Alibaba Cloud / Qwen Team 78.4 来源
2 Qwen3-Next-80B-A3B-Thinking Alibaba Cloud / Qwen Team 76.6 来源
3 Qwen3-Next-80B-A3B-Instruct Alibaba Cloud / Qwen Team 75.8 来源