← 回總覽

LMSYS Arena 排行榜新增价格和上下文数据

📅 2026-03-14 06:08 Arena.ai 人工智能 2 分鐘 1492 字 評分: 84
大型语言模型基准测试 LMSYS Arena 模型定价 上下文窗口 AI 基础设施
📌 一句话摘要 Arena 排行榜现已加入模型定价（每 100 万 token）和最大上下文窗口大小，以帮助用户比较大型语言模型（LLM）。 📝 详细摘要 lmarena.ai（前身为 LMSYS）已更新其基准测试排行榜，纳入了关键的经济和技术指标：每百万 token 的输入/输出成本以及最大上下文窗口。此次更新使开发者和研究人员不仅能根据性能分数评估模型，还能根据与特定用例相关的成本效益和技术限制进行评估。这是对业界最受信任的众包 LLM 基准测试平台的一项重大增强。 📊 文章信息 AI 评分：84 来源：lmarena.ai(@lmarena_ai) 作者：Arena.ai 分类：人
![Image 1: Arena.ai](https://www.bestblogs.dev/en/tweets?sourceId=SOURCE_39a65f)

Arena leaderboards now include Price and Context.

  • Price is shown as input / output cost per 1M tokens, and context shows the maximum context window.
Compare Arena scores based on what matters for your use case.

!Image 2: 视频缩略图

00:16

4 Replies

12 Retweets

68 Likes

5,058 Views ![Image 3: Arena.ai](https://www.bestblogs.dev/en/tweets?sourceid=39a65f)

One Sentence Summary

The Arena leaderboards now feature model pricing (per 1M tokens) and maximum context window sizes to help users compare LLMs.

Summary

lmarena.ai (formerly LMSYS) has updated its benchmark leaderboards to include critical economic and technical metrics: input/output costs per million tokens and the maximum context window. This update allows developers and researchers to evaluate models not just on performance scores, but also on cost-efficiency and technical constraints relevant to specific use cases. This is a significant enhancement for the industry's most trusted crowdsourced LLM benchmark.

AI Score

84

Influence Score 14

Published At Yesterday

Language

English

Tags

LLM Benchmarking

LMSYS Arena

Model Pricing

Context Window

AI Infrastructure

查看原文 → 發佈: 2026-03-14 06:08:15 收錄: 2026-03-14 10:00:25

🤖 問 AI

針對這篇文章提問，AI 會根據文章內容回答。按 Ctrl+Enter 送出。