{"id":27381,"date":"2025-03-03T00:24:02","date_gmt":"2025-03-02T16:24:02","guid":{"rendered":"https:\/\/www.aisharenet.com\/?p=27381"},"modified":"2025-07-17T03:07:45","modified_gmt":"2025-07-16T19:07:45","slug":"agent-leaderboard","status":"publish","type":"post","link":"https:\/\/www.kdjingpai.com\/de\/agent-leaderboard\/","title":{"rendered":"Agent Leaderboard\uff1aAI Agent \u6027\u80fd\u8bc4\u4f30\u6392\u884c\u699c"},"content":{"rendered":"<p>Agent Leaderboard \u662f\u7531 Galileo AI \u5728 Hugging Face \u5e73\u53f0\u4e0a\u63a8\u51fa\u7684\u4e00\u4e2a\u4e13\u6ce8\u4e8e AI \u4ee3\u7406\u6027\u80fd\u8bc4\u4f30\u7684\u5728\u7ebf\u5de5\u5177\u3002\u5b83\u901a\u8fc7\u7efc\u5408\u591a\u4e2a\u6743\u5a01\u6570\u636e\u96c6\uff08\u5982 BFCL\u3001\u03c4-bench\u3001xLAM \u548c ToolACE\uff09\uff0c\u5bf9 17 \u79cd\u9886\u5148\u7684\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08LLM\uff09\u8fdb\u884c\u6d4b\u8bd5\uff0c\u6db5\u76d6\u4ece\u7b80\u5355 API \u8c03\u7528\u5230\u590d\u6742\u591a\u5de5\u5177\u4ea4\u4e92\u7684\u573a\u666f\u3002\u7f51\u7ad9\u65e8\u5728\u56de\u7b54\u201cAI \u4ee3\u7406\u5728\u771f\u5b9e\u4e1a\u52a1\u573a\u666f\u4e2d\u7684\u8868\u73b0\u5982\u4f55\u201d\uff0c\u5e2e\u52a9\u5f00\u53d1\u8005\u548c\u4f01\u4e1a\u9009\u62e9\u9002\u5408\u81ea\u8eab\u9700\u6c42\u7684\u6a21\u578b\u3002\u6392\u884c\u699c\u6bcf\u6708\u66f4\u65b0\uff0c\u652f\u6301\u67e5\u770b\u6a21\u578b\u6392\u540d\u3001\u5f97\u5206\u3001\u6210\u672c\u7b49\u4fe1\u606f\uff0c\u9002\u7528\u4e8e\u9700\u8981\u6784\u5efa\u9ad8\u6548 AI \u4ee3\u7406\u7cfb\u7edf\u7684\u56e2\u961f\u3002\u65e0\u8bba\u662f\u5f00\u6e90\u6a21\u578b\u8fd8\u662f\u79c1\u6709\u6a21\u578b\uff0c\u7528\u6237\u90fd\u80fd\u5728\u8fd9\u91cc\u76f4\u89c2\u5bf9\u6bd4\u5176\u6027\u80fd\u3002\u67e5\u770b\u5206\u6790\u62a5\u544a\uff1a<a href=\"https:\/\/www.kdjingpai.com\/hugging-face-tuichu\/\">Hugging Face \u63a8\u51fa Agent \u667a\u80fd\u4f53\u6392\u884c\u699c\uff1a \u8c01\u662f\u5de5\u5177\u8c03\u7528\u9886\u57df\u7684\u9886\u5bfc\u8005\uff1f<\/a><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-27382\" title=\"Agent Leaderboard\uff1aAI Agent \u6027\u80fd\u8bc4\u4f30\u6392\u884c\u699c-1\" src=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/03\/9b26bad92799527.png\" alt=\"Agent Leaderboard\uff1aAI Agent \u6027\u80fd\u8bc4\u4f30\u6392\u884c\u699c-1\" width=\"1320\" height=\"567\" srcset=\"https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/03\/9b26bad92799527.png 1320w, https:\/\/www.kdjingpai.com\/wp-content\/uploads\/2025\/03\/9b26bad92799527-768x330.png 768w\" sizes=\"auto, (max-width: 1320px) 100vw, 1320px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2>\u529f\u80fd\u5217\u8868<\/h2>\n<ul>\n<li><strong>\u6a21\u578b\u6027\u80fd\u6392\u540d<\/strong>: \u663e\u793a 17 \u79cd\u4e3b\u6d41 LLM \u7684\u6392\u540d\uff0c\u5982 Gemini-2.0 Flash\u3001GPT-4o \u7b49\uff0c\u57fa\u4e8e\u5de5\u5177\u9009\u62e9\u8d28\u91cf\uff08TSQ\uff09\u8bc4\u5206\u3002<\/li>\n<li><strong>\u591a\u7ef4\u5ea6\u8bc4\u4f30\u6570\u636e<\/strong>: \u63d0\u4f9b\u8de8\u9886\u57df\u6d4b\u8bd5\u7ed3\u679c\uff0c\u8986\u76d6\u6570\u5b66\u3001\u96f6\u552e\u3001\u822a\u7a7a\u3001API \u4ea4\u4e92\u7b49 390 \u591a\u4e2a\u573a\u666f\u3002<\/li>\n<li><strong>\u6210\u672c\u4e0e\u6548\u7387\u5bf9\u6bd4<\/strong>: \u5c55\u793a\u6bcf\u79cd\u6a21\u578b\u7684\u6bcf\u767e\u4e07 <a href=\"https:\/\/www.kdjingpai.com\/de\/tokenization\/\">token<\/a> \u6210\u672c\uff08\u5982 Gemini-2.0 Flash $0.15 vs GPT-4o $2.5\uff09\uff0c\u4fbf\u4e8e\u6027\u4ef7\u6bd4\u5206\u6790\u3002<\/li>\n<li><strong>\u7b5b\u9009\u4e0e\u67e5\u770b\u5de5\u5177<\/strong>: \u652f\u6301\u6309\u4f9b\u5e94\u5546\u3001\u5f00\u6e90\/\u79c1\u6709\u72b6\u6001\u3001\u5f97\u5206\u7b49\u6761\u4ef6\u7b5b\u9009\u6a21\u578b\uff0c\u5feb\u901f\u5b9a\u4f4d\u6240\u9700\u4fe1\u606f\u3002<\/li>\n<li><strong>\u6570\u636e\u96c6\u5f00\u6e90\u8bbf\u95ee<\/strong>: \u63d0\u4f9b\u6d4b\u8bd5\u6570\u636e\u96c6\u4e0b\u8f7d\u94fe\u63a5\uff0c\u65b9\u4fbf\u5f00\u53d1\u8005\u7814\u7a76\u548c\u9a8c\u8bc1\u3002<\/li>\n<li><strong>\u52a8\u6001\u66f4\u65b0\u673a\u5236<\/strong>: \u6bcf\u6708\u66f4\u65b0\u6392\u884c\u699c\uff0c\u540c\u6b65\u6700\u65b0\u6a21\u578b\u53d1\u5e03\u548c\u6027\u80fd\u6570\u636e\u3002<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2>\u4f7f\u7528\u5e2e\u52a9<\/h2>\n<h3>\u5982\u4f55\u8bbf\u95ee\u4e0e\u4f7f\u7528<\/h3>\n<p>Agent Leaderboard \u662f\u4e00\u4e2a\u65e0\u9700\u5b89\u88c5\u7684\u5728\u7ebf\u5de5\u5177\uff0c\u7528\u6237\u53ea\u9700\u6253\u5f00\u6d4f\u89c8\u5668\uff0c\u8bbf\u95ee\u00a0<code>https:\/\/huggingface.co\/spaces\/galileo-ai\/agent-leaderboard<\/code>\u00a0\u5373\u53ef\u4f7f\u7528\u3002\u9875\u9762\u52a0\u8f7d\u540e\uff0c\u6620\u5165\u773c\u5e18\u7684\u662f\u4e00\u4e2a\u76f4\u89c2\u7684\u6392\u884c\u699c\u8868\u683c\uff0c\u65e0\u9700\u6ce8\u518c\u6216\u767b\u5f55\u5373\u53ef\u6d4f\u89c8\u6240\u6709\u516c\u5f00\u6570\u636e\u3002\u5982\u679c\u9700\u8981\u66f4\u6df1\u5165\u53c2\u4e0e\uff08\u5982\u4e0b\u8f7d\u6570\u636e\u96c6\u6216\u63d0\u51fa\u5efa\u8bae\uff09\uff0c\u53ef\u4ee5\u6ce8\u518c Hugging Face \u8d26\u6237\u3002<\/p>\n<h4>\u64cd\u4f5c\u6d41\u7a0b<\/h4>\n<ol>\n<li><strong>\u6d4f\u89c8\u6392\u884c\u699c<\/strong>\n<ul>\n<li>\u6253\u5f00\u7f51\u9875\u540e\uff0c\u9996\u9875\u9ed8\u8ba4\u5c55\u793a\u5f53\u524d\u6392\u540d\u524d 17 \u7684 LLM \u6a21\u578b\u3002<\/li>\n<li>\u8868\u683c\u5217\u5305\u62ec\u201c\u6392\u540d\uff08Rank\uff09\u201d\u3001\u201c\u6a21\u578b\u540d\u79f0\uff08Model\uff09\u201d\u3001\u201c\u4f9b\u5e94\u5546\uff08Vendor\uff09\u201d\u3001\u201c\u5f97\u5206\uff08Score\uff09\u201d\u3001\u201c\u6210\u672c\uff08Cost\uff09\u201d\u548c\u201c\u7c7b\u578b\uff08\u5f00\u6e90\/\u79c1\u6709\uff09\u201d\u3002<\/li>\n<li>\u793a\u4f8b\uff1a\u6392\u540d\u7b2c\u4e00\u7684 Gemini-2.0 Flash\uff0c\u5f97\u5206 0.9+\uff0c\u6210\u672c $0.15\/\u767e\u4e07 token\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u7b5b\u9009\u4e0e\u5bf9\u6bd4\u6a21\u578b<\/strong>\n<ul>\n<li>\u70b9\u51fb\u8868\u683c\u4e0a\u65b9\u7684\u7b5b\u9009\u6846\uff0c\u53ef\u4ee5\u9009\u62e9\u201c\u4f9b\u5e94\u5546\u201d\uff08\u5982 Google\u3001OpenAI\uff09\u3001\u201c\u7c7b\u578b\u201d\uff08\u5f00\u6e90\u6216\u79c1\u6709\uff09\u6216\u201c\u5f97\u5206\u533a\u95f4\u201d\u3002<\/li>\n<li>\u4f8b\u5982\uff0c\u8f93\u5165\u201cOpenAI\u201d\u540e\uff0c\u9875\u9762\u4f1a\u8fc7\u6ee4\u51fa GPT-4o\u3001o1 \u7b49\u6a21\u578b\uff0c\u65b9\u4fbf\u5bf9\u6bd4\u5176\u6027\u80fd\u3002<\/li>\n<li>\u82e5\u60f3\u67e5\u770b\u6210\u672c\u6548\u76ca\uff0c\u53ef\u6309\u201cCost\u201d\u5217\u6392\u5e8f\uff0c\u627e\u5230\u4ef7\u683c\u6700\u4f4e\u7684\u9009\u9879\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u67e5\u770b\u8be6\u7ec6\u8bc4\u4f30\u6570\u636e<\/strong>\n<ul>\n<li>\u70b9\u51fb\u4efb\u4e00\u6a21\u578b\u540d\u79f0\uff08\u5982 Gemini-1.5-Pro\uff09\uff0c\u4f1a\u5f39\u51fa\u5177\u4f53\u6027\u80fd\u62a5\u544a\u3002<\/li>\n<li>\u62a5\u544a\u5305\u62ec\u6a21\u578b\u5728\u4e0d\u540c\u6570\u636e\u96c6\u4e0a\u7684\u8868\u73b0\uff0c\u4f8b\u5982\u5728 \u03c4-bench \u7684\u96f6\u552e\u573a\u666f\u5f97\u5206\u3001\u5728 ToolACE \u7684 API \u4ea4\u4e92\u5f97\u5206\u7b49\u3002<\/li>\n<li>\u6570\u636e\u4ee5\u56fe\u8868\u5f62\u5f0f\u5c55\u793a\uff0c\u76f4\u89c2\u5448\u73b0\u6a21\u578b\u5728\u591a\u5de5\u5177\u4efb\u52a1\u6216\u957f\u4e0a\u4e0b\u6587\u573a\u666f\u4e2d\u7684\u5f3a\u5f31\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u4e0b\u8f7d\u5f00\u6e90\u6570\u636e\u96c6<\/strong>\n<ul>\n<li>\u9875\u9762\u5e95\u90e8\u6709\u201cDataset\u201d\u94fe\u63a5\uff0c\u70b9\u51fb\u8df3\u8f6c\u81f3\u00a0<code>https:\/\/huggingface.co\/datasets\/galileo-ai\/agent-leaderboard<\/code>\u3002<\/li>\n<li>\u7528\u6237\u53ef\u4e0b\u8f7d\u5b8c\u6574\u6d4b\u8bd5\u6570\u636e\u96c6\uff08\u5982 BFCL \u7684\u6570\u5b66\u9898\u5e93\u3001xLAM \u7684\u8de8\u9886\u57df\u6570\u636e\uff09\uff0c\u7528\u4e8e\u672c\u5730\u5206\u6790\u6216\u4e8c\u6b21\u5f00\u53d1\u3002<\/li>\n<li>\u4e0b\u8f7d\u524d\u9700\u767b\u5f55 Hugging Face \u8d26\u6237\uff0c\u82e5\u65e0\u8d26\u6237\uff0c\u53ef\u70b9\u51fb\u9875\u9762\u53f3\u4e0a\u89d2\u201cSign Up\u201d\u6ce8\u518c\uff0c\u8fc7\u7a0b\u7b80\u5355\uff0c\u4ec5\u9700\u90ae\u7bb1\u9a8c\u8bc1\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u83b7\u53d6\u66f4\u65b0\u52a8\u6001<\/strong>\n<ul>\n<li>\u6392\u884c\u699c\u627f\u8bfa\u6bcf\u6708\u66f4\u65b0\uff0c\u5173\u6ce8 Galileo AI \u7684\u5b98\u65b9\u535a\u5ba2\uff08\u94fe\u63a5\u5728\u9875\u9762\u5e95\u90e8\uff09\u53ef\u83b7\u53d6\u6700\u65b0\u6a21\u578b\u52a0\u5165\u901a\u77e5\u3002<\/li>\n<li>\u4f8b\u5982\uff0c\u8fd1\u671f\u7528\u6237\u5728\u793e\u533a\u8bf7\u6c42\u52a0\u5165 <a href=\"https:\/\/www.kdjingpai.com\/de\/claudeanquanfubai\/\">Claude<\/a> 3.7 Sonnet \u548c <a href=\"https:\/\/www.kdjingpai.com\/de\/grok\/\">Grok<\/a> 3\uff0c\u5b98\u65b9\u56de\u590d\u5c06\u5728 API \u53ef\u7528\u540e\u6dfb\u52a0\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n<h4>\u7279\u8272\u529f\u80fd\u64cd\u4f5c\u8be6\u89e3<\/h4>\n<ul>\n<li><strong>\u5de5\u5177\u9009\u62e9\u8d28\u91cf\uff08TSQ\uff09\u8bc4\u5206\u89e3\u8bfb<\/strong>\n<ul>\n<li>TSQ \u662f Agent Leaderboard \u7684\u6838\u5fc3\u8bc4\u4f30\u6307\u6807\uff0c\u8861\u91cf\u6a21\u578b\u5728\u5de5\u5177\u4f7f\u7528\u4e2d\u7684\u51c6\u786e\u6027\u3002<\/li>\n<li>\u64cd\u4f5c\u793a\u4f8b\uff1a\u9009\u62e9 GPT-4o\uff0c\u67e5\u770b\u5176 TSQ \u5f97\u5206 0.9\uff0c\u7ec6\u9879\u663e\u793a\u5b83\u5728\u591a\u5de5\u5177\u534f\u540c\u4efb\u52a1\u4e2d\u8868\u73b0\u4f18\u5f02\uff0c\u4f46\u5728\u957f\u4e0a\u4e0b\u6587\u573a\u666f\u7a0d\u5f31\u3002<\/li>\n<li>\u4f7f\u7528\u5efa\u8bae\uff1a\u5982\u679c\u4f60\u7684\u9879\u76ee\u6d89\u53ca\u590d\u6742\u5de5\u4f5c\u6d41\uff0c\u9009\u62e9 TSQ \u9ad8\u4e8e 0.85 \u7684\u6a21\u578b\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u591a\u9886\u57df\u6d4b\u8bd5\u7ed3\u679c\u5206\u6790<\/strong>\n<ul>\n<li>\u70b9\u51fb\u201cEvaluation Details\u201d\uff0c\u53ef\u67e5\u770b\u6a21\u578b\u5728 14 \u4e2a\u57fa\u51c6\u6d4b\u8bd5\u4e2d\u7684\u8868\u73b0\u3002<\/li>\n<li>\u793a\u4f8b\uff1aGemini-2.0 Flash \u5728 BFCL\uff08\u6570\u5b66\u4e0e\u6559\u80b2\uff09\u5f97\u5206 0.92\uff0c\u5728 ToolACE\uff08API \u4ea4\u4e92\uff09\u5f97\u5206 0.89\u3002<\/li>\n<li>\u4f7f\u7528\u573a\u666f\uff1a\u9700\u8981\u5904\u7406\u822a\u7a7a\u6570\u636e\u7684\u56e2\u961f\u53ef\u53c2\u8003 \u03c4-bench \u7ed3\u679c\uff0c\u6311\u9009\u64c5\u957f\u8be5\u9886\u57df\u7684\u6a21\u578b\u3002<\/li>\n<\/ul>\n<\/li>\n<li><strong>\u6210\u672c\u4f18\u5316\u51b3\u7b56<\/strong>\n<ul>\n<li>\u5728\u8868\u683c\u201cCost\u201d\u5217\u67e5\u770b\u6bcf\u767e\u4e07 token \u7684\u8f93\u5165\/\u8f93\u51fa\u4ef7\u683c\u3002<\/li>\n<li>\u64cd\u4f5c\u793a\u4f8b\uff1a\u7b5b\u9009\u201cCost &lt; $1\u201d\uff0c\u7ed3\u679c\u663e\u793a Mistral-small-2501\uff08$0.5\/\u767e\u4e07 token\uff09\uff0c\u9002\u5408\u9884\u7b97\u6709\u9650\u7684\u9879\u76ee\u3002<\/li>\n<li>\u5c0f\u8d34\u58eb\uff1a\u7ed3\u5408\u5f97\u5206\u548c\u6210\u672c\uff0c\u5e73\u8861\u6027\u80fd\u4e0e\u5f00\u652f\u3002<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h4>\u6ce8\u610f\u4e8b\u9879<\/h4>\n<ul>\n<li><strong>\u6570\u636e\u66f4\u65b0\u65f6\u95f4<\/strong>: \u5f53\u524d\u6570\u636e\u622a\u81f3 2025 \u5e74 2 \u6708\uff0c\u5efa\u8bae\u5b9a\u671f\u8bbf\u95ee\u4ee5\u83b7\u53d6\u6700\u65b0\u6392\u540d\u3002<\/li>\n<li><strong>\u793e\u533a\u53cd\u9988<\/strong>: \u82e5\u9700\u65b0\u6a21\u578b\uff08\u5982 Grok 3\uff09\uff0c\u53ef\u5728 Hugging Face \u9875\u9762\u7559\u8a00\uff0c\u5b98\u65b9\u4f1a\u6839\u636e API \u53ef\u7528\u6027\u54cd\u5e94\u3002<\/li>\n<li><strong>\u6280\u672f\u8981\u6c42<\/strong>: \u7f51\u9875\u5bf9\u7f51\u7edc\u8981\u6c42\u4f4e\uff0c\u4f46\u4e0b\u8f7d\u6570\u636e\u96c6\u9700\u7a33\u5b9a\u8fde\u63a5\uff0c\u5efa\u8bae\u4f7f\u7528\u684c\u9762\u7aef\u64cd\u4f5c\u3002<\/li>\n<\/ul>\n<p>\u901a\u8fc7\u4ee5\u4e0a\u6b65\u9aa4\uff0c\u7528\u6237\u53ef\u4ee5\u5feb\u901f\u4e0a\u624b Agent Leaderboard\uff0c\u65e0\u8bba\u662f\u5bfb\u627e\u9ad8\u6027\u80fd\u6a21\u578b\uff0c\u8fd8\u662f\u7814\u7a76 AI \u4ee3\u7406\u7684\u6280\u672f\u7ec6\u8282\uff0c\u8fd9\u4e2a\u5de5\u5177\u90fd\u80fd\u63d0\u4f9b\u5b9e\u7528\u652f\u6301\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Agent Leaderboard \u662f\u7531 Galileo AI \u5728 Hugging Face \u5e73\u53f0\u4e0a\u63a8\u51fa\u7684\u4e00\u4e2a\u4e13\u6ce8\u4e8e AI \u4ee3\u7406\u6027\u80fd\u8bc4\u4f30\u7684\u5728\u7ebf\u5de5\u5177\u3002\u5b83\u901a\u8fc7\u7efc\u5408\u591a\u4e2a\u6743\u5a01\u6570\u636e\u96c6\uff08\u5982 BFCL\u3001\u03c4-bench\u3001xLAM \u548c ToolACE\uff09\uff0c\u5bf9 &#8230;<\/p>\n","protected":false},"author":1,"featured_media":31260,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[20],"tags":[208],"class_list":["post-27381","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tool","tag-aikaifangfuwu"],"_links":{"self":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/27381","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/comments?post=27381"}],"version-history":[{"count":0,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/posts\/27381\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media\/31260"}],"wp:attachment":[{"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/media?parent=27381"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/categories?post=27381"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.kdjingpai.com\/de\/wp-json\/wp\/v2\/tags?post=27381"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}