OpenCompass司南
评测榜单旨在为大语言模型和多模态模型提供全面、客观且中立的得分与排名，同时提供多能力维度的评分参考，以便用户能够更全面地了解大模型的能力水平。
MMLU 全称 Massive MultitaskLanguage Understanding，是一种针对大模型的语言理解能力的测评，是目前最著名的大模型语义理解测评之一，由UCBerkeley大学的研究人员在2020年9月推出。该测试涵盖57项任务，包括初等数学、美国历史、计算机科学、法律等。任务涵盖的知识很广泛，语言是英文,用以评测大模型基本的知识覆盖范围和理解能力。
数据统计
相关导航
Chatbot Arena
Attention Required! | Cloudflare
Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
OSS Insight
The comprehensive Open Source Software insight tool by analyzing massive events from GitHub, powered by TiDB, the best insight building database of data agility.
AI Model & API Providers Analysis
Comparison and analysis of AI models and API hosting providers. Independent benchmarks across key performance metrics including quality, price, output speed & latency.
All Large Language Models Directory
Discover the Large Language Models at AllLLMs, your biggest LLM directory. Curated by John Rush list of LLMs for AI enthusiasts and experts.
暂无评论...
