智源研究院“百模”评测结果：字节跳动多项第一，大厂AI整体领先

新浪财经2024-12-23

新浪科技讯 12月23日午间消息，近日，智源研究院发布国内外100余个开/闭源语言、视觉语言、文生图、文生视频大模型综合及专项评测结果。评测发现，2024年下半年，大模型发展更聚焦综合能力提升与实际应用。多项评测结果中，字节跳动多项AI能力领先，阿里巴巴、百度等大厂派AI均取得优异表现。　　据评测结果，针对一般中文场景的开放式问答或生成任务，语言模型能力已趋于饱和稳定，但是复杂场景任务的表现，...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2493202626?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2024-12-23 12:30","share_image_url":"https://static.laohu8.com/b0d1b7e8843deea78cc308b15114de44","id":"2493202626","market":"other","top_or_hot":-1,"title":"智源研究院“百模”评测结果：字节跳动多项第一，大厂AI整体领先","media":"新浪财经","content":"<div>\n<p>新浪科技讯 12月23日午间消息，近日，智源研究院发布国内外100余个开/闭源语言、视觉语言、文生图、文生视频大模型综合及专项评测结果。评测发现，2024年下半年，大模型发展更聚焦综合能力提升与实际应用。多项评测结果中，字节跳动多项AI能力领先，阿里巴巴、百度等大厂派AI均取得优异表现。\n\n　　据评测结果，针对一般中文场景的开放式问答或生成任务，语言模型能力已趋于饱和稳定，但是复杂场景任务的表现，...</p>\n\n<a href=\"https://finance.sina.com.cn/tech/2024-12-23/doc-ineamnxt2674412.shtml\">网页链接</a>\n\n</div>\n","source":"sina","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>智源研究院“百模”评测结果：字节跳动多项第一，大厂AI整体领先</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n智源研究院“百模”评测结果：字节跳动多项第一，大厂AI整体领先\n</h2>\n\n<h4 class=\"meta\">\n\n\n2024-12-23 12:30 北京时间&nbsp;&nbsp;&nbsp;<a href=https://finance.sina.com.cn/tech/2024-12-23/doc-ineamnxt2674412.shtml><strong>新浪财经</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>新浪科技讯 12月23日午间消息，近日，智源研究院发布国内外100余个开/闭源语言、视觉语言、文生图、文生视频大模型综合及专项评测结果。评测发现，2024年下半年，大模型发展更聚焦综合能力提升与实际应用。多项评测结果中，字节跳动多项AI能力领先，阿里巴巴、百度等大厂派AI均取得优异表现。\n\n　　据评测结果，针对一般中文场景的开放式问答或生成任务，语言模型能力已趋于饱和稳定，但是复杂场景任务的表现，...</p>\n\n<a href=\"https://finance.sina.com.cn/tech/2024-12-23/doc-ineamnxt2674412.shtml\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"BK4581","symbol_name":"高盛持仓","start_time":0,"source_url":"https://finance.sina.com.cn/tech/2024-12-23/doc-ineamnxt2674412.shtml","article_id":"2493202626","we_media_id":null,"thumbnails":[],"rights":null,"url":"https://stock-news.laohu8.com/highlight/detail?id=2493202626","pubTimestamp":1734928200,"columns":[],"sourceInfo":{"source_id":"sina","name":"sina"},"weMediaInfo":null,"summary":"新浪科技讯 12月23日午间消息，近日，智源研究院发布国内外100余个开/闭源语言、视觉语言、文生图、文生视频大模型综合及专项评测结果。评测发现，2024年下半年，大模型发展更聚焦综合能力提升与实际应用。多项评测结果中，字节跳动多项AI能力领先，阿里巴巴、百度等大厂派AI均取得优异表现。","collect":0,"end_time":0,"defaultTopTitle":"sina.com.cn","property":[],"viewcount":null,"language":"zh","relate_stocks":{"BK4581":"高盛持仓","LU1051768304.USD":"贝莱德新兴市场股票收益A6","BK4505":"高瓴资本持仓","IE00BFMHRM44.USD":"NEUBERGER BERMAN GLOBAL EQUITY MEGATRENDS \"A\" (USD) ACC","LU0348816934.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT\" (USD)","LU0251143458.SGD":"Fidelity Emerging Markets A-SGD","BK4504":"桥水持仓","BK4122":"互联网与直销零售","LU1046421795.USD":"富达环球科技A-ACC","LU0880133367.SGD":"UBS (LUX) EQUITY FUND CHINA OPPORTUNITY USD \"P\" (SGD) ACC","BK4548":"巴美列捷福持仓","LU0501845795.SGD":"瑞银大中华区股票基金P Acc SGD","IE00B0JY6N72.USD":"PINEBRIDGE GLOBAL EMERGING MARKETS FOCUS EQUITY \"A\" (USD) ACC","BK4565":"NFT概念","LU0052756011.USD":"TEMPLETON GLOBAL BALANCED \"A\" (USD) INC","BK4554":"元宇宙及AR概念","LU1267930227.SGD":"TEMPLETON GLOBAL BALANCED \"AS\" (SGD) ACC A","LU1823568750.SGD":"Fidelity Global Technology A-ACC SGD","LU0072913022.USD":"UBS (LUX) EQUITY FUND -  GREATER CHINA \"P\" (USD) ACC","BK4531":"中概回港概念","09988":"阿里巴巴-W","LU0128525689.USD":"TEMPLETON GLOBAL BALANCED \"A\"(USD) ACC","BK4585":"ETF&股票定投概念","BK4534":"瑞士信贷持仓","LU0067412154.USD":"UBS (LUX) EQUITY FUND -  CHINA OPPORTUNITY \"P\" (USD) ACC","BABA":"阿里巴巴","LU1105468828.SGD":"Allianz Total Return Asian Equity AM DIS H2-SGD","LU0310800965.SGD":"FTIF - Templeton Global Balanced A Acc SGD","BK4587":"ChatGPT概念","BK4558":"双十一","LU1152091754.HKD":"UBS (LUX) EQUITY FUND - CHINA OPPORTUNITY (USD) \"PM\" (HKD) INC","LU1048596156.SGD":"Blackrock Asian Growth Leaders A2 SGD-H","LU0918141705.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AM\" (HKD) INC","LU0348814723.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"A\" (USD) INC  NC","BK4524":"宅经济概念","LU1282648689.USD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AMG\" (USD) INC","LU1688375341.USD":"贝莱德中国灵活股票基金","BK4220":"综合零售","LU1008478684.HKD":"UBS (LUX) EQUITY FUND -  CHINA OPPORTUNITY \"P\" (HKD) ACC","BK4535":"淡马锡持仓","LU0821914370.USD":"贝莱德亚洲成长领袖A2","LU1152091168.USD":"UBS (LUX) EQUITY FUND - CHINA OPPORTUNITY (USD) \"PM\" INC","BK4527":"明星科技股","BK4538":"云计算","LU0797268264.HKD":"ALLIANZ TOTAL RETURN ASIAN EQUITY \"AT\" (HKD) ACC","BK4588":"碎股","LU1046422090.SGD":"Fidelity Pacific A-SGD","BK4503":"景林资产持仓","LU0918141887.USD":"安联亚洲实际收益股票基金","BK4502":"阿里概念"},"translate_title":"Zhiyuan Research Institute's \"100 Models\" evaluation results: ByteDance ranks first in many places, and major manufacturers lead the overall AI","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"BABA":0.73,"09988":0.6},"content_text":"新浪科技讯 12月23日午间消息，近日，智源研究院发布国内外100余个开/闭源语言、视觉语言、文生图、文生视频大模型综合及专项评测结果。评测发现，2024年下半年，大模型发展更聚焦综合能力提升与实际应用。多项评测结果中，字节跳动多项AI能力领先，阿里巴巴、百度等大厂派AI均取得优异表现。\n\n　　据评测结果，针对一般中文场景的开放式问答或生成任务，语言模型能力已趋于饱和稳定，但是复杂场景任务的表现，国内头部语言模型仍然与国际一流水平存在显著差距。在中文能力理解上，字节跳动Doubao-pro-32k-preview、百度ERNIE 4.0 Turbo位居第一、第二，OpenAI o1-preview-2024-09-12、Anthropic Claude-3-5-sonnet-20241022位列第三、第四，阿里巴巴Qwen-Max-0919排名第五。\n\n　　在视觉语言多模态模型能力评测结果中，一些较好的开源模型在图文理解任务上正在缩小与头部闭源模型的能力差距，而长尾视觉知识与文字识别以及复杂图文数据分析能力仍有提升空间。评测显示，OpenAI GPT-4o-2024-11-20与字节跳动Doubao-Pro-Vision-32k-241028先后领先于Anthropic Claude-3-5-sonnet-20241022，阿里巴巴Qwen2-VL-72B-Instruct和Google Gemini-1.5-Pro紧随其后。\n　　此外，文生图多模态模型今年上半年参评模型普遍无法生成正确的中文文字，但此次参评的头部模型已经具备中文文字生成能力，但整体普遍存在复杂场景人物变形的情况，针对常识或知识性推理任务，小于3的数量关系任务表现有所提升，大于3的数量关系依然无法处理。评测结果显示，腾讯Hunyuan Image位列第一，字节跳动Doubao image v2.1、Ideogram 2.0分居第二、第三，OpenAI DALL·E 3、快手可图次之。\n　　在文生视频多模态模型，画质进一步提升，动态性更强，镜头语言更丰富，专场更流畅，但普遍存在大幅度动作变形，无法理解物理规律，物体消失、闪现、穿模的情况。评测结果显示，快手可灵1.5（高品质）、字节跳动即梦P2.0 pro、爱诗科技PixVerse V3、MiniMax海螺AI、Pika 1.5位列前五。\n　　据介绍，本次评测依托智源研究院自2023年6月上线的大模型评测平台FlagEval，经过数次迭代，目前已覆盖全球800多个开闭源模型，包含20多种任务，90多个评测数据集，超200万条评测题目。（文猛）\n\n\n海量资讯、精准解读，尽在新浪财经APP\n\n责任编辑：石秀珍 SF183","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"symbols":[],"gpt_button":0},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"deviceId":"web-server-community-laohu8-v3","version":"4.30.0","shortVersion":"4.30.0","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2493202626"}