
{"id":11825,"date":"2026-09-03T00:14:49","date_gmt":"2026-09-02T16:14:49","guid":{"rendered":"https:\/\/infernews.com\/blog\/e-commercebench\/"},"modified":"2026-09-03T00:20:05","modified_gmt":"2026-09-02T16:20:05","slug":"e-commercebench","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/e-commercebench\/","title":{"rendered":"E-CommerceBench \u7d93\u71df 365 \u65e5\u7db2\u5e97\u7684 Agent \u8003\u8a66"},"content":{"rendered":"\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/09\/pasted-4ba671b9063d.jpg\" alt=\"Mean end-of-year total assets, eighteen models, five 365-day episodes each\"><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e00\u500b\u4ee3\u7406\u4eba\u7531 \u00a5100,000 \u8d77\u6b65\uff0c\u9023\u7e8c\u7d93\u71df\u6700\u591a\u56db\u9593\u7db2\u5e97 365 \u500b\u6a21\u64ec\u65e5\uff0c\u9084\u8981\u81ea\u884c\u8655\u7406\u63a1\u8cfc\u3001\u5b9a\u50f9\u3001\u88dc\u8ca8\u3001\u8a02\u55ae\u5c65\u884c\u53ca\u9000\u8ca8\u3002E-Commerce Bench \u5c6c\u65bc\u9577\u671f\u81ea\u4e3b\u5546\u696d\u904b\u4f5c\u7684 LLM agent benchmark\uff0c\u5be6\u969b\u8655\u7406\u7684\u662f\u4ee3\u7406\u4eba\u80fd\u5426\u5728\u73fe\u91d1\u6d41\u3001\u5eab\u5b58\u3001\u98a8\u96aa\u548c\u589e\u9577\u4e4b\u9593\u6301\u7e8c\u4f5c\u51fa\u6c7a\u7b56\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u74b0\u5883\u5305\u542b 6,886 \u500b\u7522\u54c1\u300160 \u500b\u985e\u5225\u53ca 576 \u5bb6\u4f9b\u61c9\u5546\uff0c\u5176\u4e2d 152 \u5bb6\u6d89\u53ca\u4e94\u7a2e\u8a50\u9a19\u985e\u578b\uff1b\u5168\u5e74\u4ea6\u6709\u516b\u6b21\u4fc3\u92b7\u548c\u5341\u9805\u5e02\u5834\u4e8b\u4ef6\u3002\u5ba2\u6236\u9700\u6c42\u7531\u56fa\u5b9a\u591a\u56e0\u7d20\u6a21\u578b\u6c7a\u5b9a\uff0c\u4f9b\u61c9\u5546\u50f9\u683c\u3001\u8b93\u6b65\u53ca\u63a5\u53d7\u8207\u5426\u5247\u7531 Deterministic Negotiation Kernel \u8a08\u7b97\uff0cLLM \u53ea\u8ca0\u8cac\u628a\u6c7a\u7b56\u5448\u73fe\u6210\u5c0d\u8a71\uff0c\u907f\u514d\u62bd\u6a23\u56de\u8986\u76f4\u63a5\u6539\u8b8a\u4ea4\u6613\u7d50\u679c\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6392\u884c\u699c\u4ee5\u4e94\u6b21\u7368\u7acb episode \u7684\u5e74\u7d42\u7e3d\u8cc7\u7522\u5e73\u5747\u503c\u8a08\u7b97 asset multiplier\uff0c\u540c\u6642\u63d0\u4f9b\u6a19\u6e96\u5dee\u3001CSE\u207a\u3001BadSpend%\u3001\u56de\u64a4\u3001\u6bcf\u6b21\u5de5\u5177\u547c\u53eb\u5e36\u4f86\u7684\u6536\u5165\u3001\u53ef\u63a7\u9000\u8ca8\u6bd4\u4f8b\u3001AnchorRatio\u3001\u5de5\u5177\u547c\u53eb\u6b21\u6578\u53ca\u7834\u7522\u6b21\u6578\u7b49\u6307\u6a19\u3002GPT-5.6 Sol\uff08max\uff09\u5e73\u5747\u8cc7\u7522\u9054 \u00a51,431,425\uff0c\u7d04\u70ba\u672c\u91d1 14.3 \u500d\uff1b\u6700\u4f73 open-weight \u6a21\u578b Qwen3.8-Max-Preview \u70ba \u00a5416,252\uff0c\u7d04 4.2 \u500d\uff0c18 \u500b\u6a21\u578b\u4e4b\u9593\u76f8\u5dee 1,264 \u500d\uff0c90 \u6b21\u904b\u884c\u6709 10 \u6b21\u7834\u7522\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>\u6e2c\u8a66\u5834\u666f\u6db5\u84cb\u6700\u591a\u7d04 4,000 \u500b\u56de\u5408\uff0c\u9069\u5408\u7814\u7a76\u9577\u671f\u8a18\u61b6\u3001\u898f\u5283\u548c\u5de5\u5177\u4f7f\u7528\u3002<\/li><li>\u56fa\u5b9a\u9700\u6c42\u8207\u8ac7\u5224\u6a5f\u5236\u4ee4\u6a21\u578b\u5dee\u7570\u8f03\u5bb9\u6613\u6b78\u56e0\uff0c\u4f46\u672a\u5fc5\u4ee3\u8868\u771f\u5be6\u5e02\u5834\u7684\u96a8\u6a5f\u6027\u3002<\/li><li>\u6a21\u578b\u6392\u540d\u540c\u6642\u5448\u73fe\u76c8\u5229\u80fd\u529b\u3001\u98a8\u96aa\u63a7\u5236\u3001\u6d6a\u8cbb\u958b\u652f\u53ca\u8cc7\u91d1\u58d3\u529b\u3002<\/li><li>\u9805\u76ee\u8cc7\u6599\u63d0\u5230 Python 3.10+\uff0c\u4f46\u63d0\u4f9b\u5167\u5bb9\u6c92\u6709\u5217\u51fa\u5b8c\u6574\u5b89\u88dd\u3001\u57f7\u884c\u6216\u4e0b\u8f09\u6d41\u7a0b\u3002<\/li><\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u7814\u7a76\u4ee3\u7406\u4eba\u53ef\u9760\u6027\u3001\u5546\u696d\u6c7a\u7b56\u3001\u9577\u671f\u898f\u5283\u6216\u591a\u6b65\u9a5f\u5de5\u5177\u8abf\u7528\u7684\u5718\u968a\uff0c\u6703\u8f03\u5bb9\u6613\u5f9e\u9019\u5957\u56fa\u5b9a\u4e16\u754c\u53d6\u5f97\u53ef\u91cd\u8907\u6bd4\u8f03\u7684\u7d50\u679c\uff1b\u7db2\u5e97\u7d93\u71df\u8005\u5247\u53ef\u628a\u5b83\u7406\u89e3\u6210\u58d3\u529b\u6e2c\u8a66\uff0c\u800c\u4e0d\u662f\u76f4\u63a5\u9810\u6e2c\u771f\u5be6\u92b7\u552e\u984d\u3002\u5b83\u540c\u6642\u6bd4\u8f03 proprietary \u8207 open-weight \u6a21\u578b\uff0c\u4f46\u8cc7\u6599\u672a\u4ea4\u4ee3\u5404\u6a21\u578b\u7684\u63d0\u793a\u8a5e\u3001\u5de5\u5177\u7b56\u7565\u6216\u6210\u672c\uff0c\u56e0\u6b64\u8cc7\u7522\u6392\u540d\u4e0d\u61c9\u55ae\u7368\u8996\u70ba\u6574\u9ad4\u80fd\u529b\u7d50\u8ad6\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/ecbench.github.io\/\" rel=\"noopener noreferrer\"><strong>\u9805\u76ee\u4e3b\u9801<\/strong><\/a> \u00b7 <a href=\"https:\/\/github.com\/QwenLM\/E-CommerceBench\" rel=\"noopener noreferrer\"><strong>GitHub<\/strong><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u4ee3\u7406\u4eba\u8981\u7531\u5341\u842c\u5143\u8d77\u6b65\uff0c\u7d93\u71df\u6700\u591a\u56db\u9593\u7db2\u5e97\u4e26\u61c9\u4ed8\u4f9b\u61c9\u5546\u3001\u5eab\u5b58\u8207\u9000\u8ca8\uff0c\u6700\u5f8c\u4ee5\u5168\u5e74\u8cc7\u7522\u589e\u9577\u5206\u9ad8\u4f4e\u3002<\/p>\n","protected":false},"author":8,"featured_media":11824,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"wpai_generated_summary":"","footnotes":""},"categories":[133,185,178,140,147,153,116,152,191,199],"tags":[],"class_list":["post-11825","post","type-post","status-publish","format-standard","hentry","category-133","category-qwen","category-google","category-gemini","category-deepseek","category-openai","category-agentic","category-python","category-anthropic","category-dataset-"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11825","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=11825"}],"version-history":[{"count":1,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11825\/revisions"}],"predecessor-version":[{"id":11827,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/11825\/revisions\/11827"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/11824"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=11825"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=11825"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=11825"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}