AutoGPT 是面向自主智能体的开源平台,支持用自然语言或可视化流程创建、运行和管理能够持续执行任务的智能体。
关于 Artificial Analysis AI基准测试平台
AI Model & API Providers Analysis | Artificial Analysis Artificial Analysis K Artificial Analysis Models Coding Agents Image, Speech, Video Inference Leaderboards About AI Trends K Independent analysis of AI Understand the AI landscape to choose the best model and provider for your use case Update API Performance Benchmarking v3 Time per task is now our headline performance metric, with agentic workloads added Update Decision Index v2.1 New private benchmarks and scoring that rewards calibrated confidence Language Models Image Video Speech Effort Highest API Default Intelligence Artificial Analysis Intelligence Index · Higher is better No publicly available API Time per Task Inference time (minutes) per Intelligence Index task · Lower is better No publicly available API Cost per Task Weighted average cost (USD) per Intelligence Index task · Lower is better No publicly available API Optima by Artificial Analysis New Build your own custom benchmark Model Recommender Get personalized model recommendations that optimize for your priorities across intelligence, speed, and cost Changelog New language model evaluation · 15 Nov Qwen4 Max New language model evaluation · 13 Nov Gemini 4 Argon (Medium) New language model evaluation · 13 Nov DeepSeek V4 Pro 0813 (High) New language model evaluation · 12 Nov Gemini 4 Hydrogen (Low) New language model evaluation · 12 Nov Gemini 4 Hydrogen (Medium) New language model evaluation · 12 Nov Gemini 4 Hydrogen (High) New language model evaluation · 12 Nov Gemini 4 Hydrogen (Xhigh) New language model evaluation · 11 Nov JT-4.1 Flash 236B A21B New article published · 10 Nov Multimodal Knowledge Agent (MKA) benchmark: testing knowledge work capabilities with complex visual files New article published · 9 Nov Endpoint Accuracy Index v1.1: Tighter long context intervals and expanded model coverage New article published · 9 Nov Meta's Muse Ember is the cheapest model scoring 36 on the Intelligence Index New language model evaluation · 9 Nov Claude Fable 5.2 (Max, Default Fallback) New language model evaluation · 9 Nov Claude Fable 5.2 (Low, Default Fallback) New language model evaluation · 9 Nov Claude Fable 5.2 (Medium, Default Fallback) New language model evaluation · 9 Nov Claude Fable 5.2 (High, Default Fallback) New language model evaluation · 9 Nov Claude Fable 5.2 (Xhigh, Default Fallback) New language model evaluation · 9 Nov Muse Ember (Xhigh) New language model evaluation · 9 Nov Muse Ember (Max) New article published
访问提示
本站仅提供官网信息与访问导航,不代表对该网站的产品、服务或交易作出担保。访问外部网站时,请核对网址,注意账号和财产安全。
同类型网站
查看分类百川智能发布的金融大模型,金融场景能力领先GPT-4o近20%
Build a Large Language Model (From Scratch) 是一款AI 大模型方向的 AI 工具,适合主流大语言模型与开源模型。
支持多 AI Agent 框架的可视化管理面板,支持 OpenClaw 和 Hermes Agent 双引擎,内置智能助手一键安装诊断