{"schemaVersion":"1.0","name":"AI Benchmark Index","slug":"ai-benchmark-index","website":"https://aibenchmarkindex.com","category":"ai","description":"AI Benchmark Index lists AI and large language model benchmarks. Compare them by task, data licence, scoring method, access and reported results.","capabilities":["llmsTxt documentation","llmsFullTxt documentation"],"aiResources":{"llmsTxt":{"type":"llmsTxt","url":"https://aibenchmarkindex.com/llms.txt","status":"verified","available":true,"httpStatus":200,"checkedAt":"2026-11-10T22:27:32.962Z","lastSuccessfulAt":"2026-11-10T22:27:32.962Z","contentType":"text/plain; charset=utf-8","contentSize":6878,"estimatedTokens":1720,"tokenMethod":"UTF-16 characters / 4 (approximation)","contentHash":"7f0c1257e2da6d251f8d4e6f0ff8112eed975e136f60703674cc2cd1eff204aa","internalLinks":46,"externalLinks":0,"document":{"h1Count":1,"firstBlockIsH1":true,"title":"AI Benchmark Index","usefulTitle":true,"headingCount":12,"uniqueHeadingCount":12,"hasSections":true,"orderedHeadings":true,"sectionWithContent":true,"fileListLinks":43,"summaryPresent":true,"contextPresent":true,"validLinks":46,"invalidLinks":0,"duplicateLinks":0,"descriptiveLinks":46,"annotatedLinks":42},"linkHealth":{"eligibleCount":46,"selectedCount":5,"sampledCount":5,"working":5,"broken":0,"unknown":0,"checkedAt":"2026-11-10T22:27:34.619Z","sourceHash":"7f0c1257e2da6d251f8d4e6f0ff8112eed975e136f60703674cc2cd1eff204aa","method":"deterministic sample, at most 5 URLs, at most 2 concurrent hosts, 15s budget","results":[{"url":"https://aibenchmarkindex.com/academy/choose-and-run-an-ai-benchmark.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/tools.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/.well-known/agent-card.json","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/commerce.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/browser.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"}]},"headings":["AI Benchmark Index","Regions","Benchmarks by city","Categories","Free tools","Products","Academy","Guides","About this site","Data sources","API","Optional"],"warnings":[],"summary":"Documentation sections: AI Benchmark Index; Regions; Benchmarks by city; Categories; Free tools; Products.","summarySourceHash":"7f0c1257e2da6d251f8d4e6f0ff8112eed975e136f60703674cc2cd1eff204aa","processingVersion":"2.0","method":"markdown-ast-analysis"},"llmsFullTxt":{"type":"llmsFullTxt","url":"https://aibenchmarkindex.com/llms-full.txt","status":"verified","available":true,"httpStatus":200,"checkedAt":"2026-11-10T22:27:33.748Z","lastSuccessfulAt":"2026-11-10T22:27:33.748Z","contentType":"text/plain; charset=utf-8","contentSize":109287,"estimatedTokens":27320,"tokenMethod":"UTF-16 characters / 4 (approximation)","contentHash":"329d88edd04645cfafb725dbad23bd8bcafaf4dea18b499e6e9ad59ddc6c1673","internalLinks":281,"externalLinks":263,"document":{"h1Count":1,"firstBlockIsH1":true,"title":"AI Benchmark Index","usefulTitle":true,"headingCount":276,"uniqueHeadingCount":276,"hasSections":true,"orderedHeadings":true,"sectionWithContent":true,"fileListLinks":281,"summaryPresent":true,"contextPresent":true,"validLinks":551,"invalidLinks":0,"duplicateLinks":7,"descriptiveLinks":281,"annotatedLinks":11},"headings":["AI Benchmark Index","Online, Global, United States","ActivityNet-QA","AdvBench","AgentBench","AgentDojo","AGIEval","AI2 Reasoning Challenge","AI2-THOR","AI2D","ALFWorld","AlpacaEval"],"warnings":["7 duplicate documentation links"],"summary":"Documentation sections: AI Benchmark Index; Online, Global, United States; ActivityNet-QA; AdvBench; AgentBench; AgentDojo.","summarySourceHash":"329d88edd04645cfafb725dbad23bd8bcafaf4dea18b499e6e9ad59ddc6c1673","processingVersion":"2.0","method":"markdown-ast-analysis"},"webmcp":null},"readiness":{"score":100,"version":"2.0","confidence":"high","components":[{"name":"availability","weight":25,"assessedWeight":25,"points":25,"rules":[{"id":"current_access","label":"Current usable primary file","weight":25,"observation":"Current llms.txt retrieval succeeded (HTTP 200); usable text verified.","points":25}],"explanation":"Current usable primary file: 25/25."},{"name":"structure","weight":25,"assessedWeight":25,"points":25,"rules":[{"id":"title","label":"One project H1 at the beginning","weight":10,"observation":"1 H1 heading(s); starts with H1: yes.","points":10},{"id":"sections","label":"Coherent content sections","weight":5,"observation":"H2 with content: yes; no heading-level jumps: yes.","points":5},{"id":"file_lists","label":"Documentation links organized in lists","weight":5,"observation":"43 valid link occurrence(s) inside Markdown lists.","points":5},{"id":"heading_uniqueness","label":"Non-repeated headings","weight":5,"observation":"12 unique heading(s) out of 12; code examples are excluded.","points":5}],"explanation":"One project H1 at the beginning: 10/10. Coherent content sections: 5/5. Documentation links organized in lists: 5/5. Non-repeated headings: 5/5."},{"name":"links","weight":25,"assessedWeight":25,"points":24.78,"rules":[{"id":"link_syntax","label":"Resolvable HTTP(S) link syntax","weight":5,"observation":"46 valid URL occurrence(s), 0 malformed, unsupported or unresolved.","points":5},{"id":"link_uniqueness","label":"Unique documentation destinations","weight":5,"observation":"46 unique destination(s) from 46 valid occurrence(s).","points":5},{"id":"link_labels","label":"Descriptive link labels","weight":2.5,"observation":"46 of 46 unique links have non-placeholder labels. This is a text heuristic, not a semantic guarantee.","points":2.5},{"id":"link_notes","label":"Context beside file links","weight":2.5,"observation":"42 of 46 unique links have notes beside a Markdown list link.","points":2.28},{"id":"link_health","label":"Sampled destination accessibility","weight":10,"observation":"5 of 46 destinations sampled: 5 working, 0 confirmed 404/410, 0 unknown. Only working and confirmed-broken results enter this fraction.","points":10}],"explanation":"Resolvable HTTP(S) link syntax: 5/5. Unique documentation destinations: 5/5. Descriptive link labels: 2.5/2.5. Context beside file links: 2.28/2.5. Sampled destination accessibility: 10/10."},{"name":"confidence","weight":15,"assessedWeight":15,"points":15,"rules":[{"id":"verification_age","label":"Age of last successful verification","weight":10,"observation":"Last success: 2026-11-10T22:27:32.962Z. Full points through day 8 (7-day schedule plus 1-day grace), 60% through day 30, 20% thereafter or for an unknown date.","points":10},{"id":"latest_success","label":"Latest primary check succeeded","weight":5,"observation":"Latest primary verification succeeded.","points":5}],"explanation":"Age of last successful verification: 10/10. Latest primary check succeeded: 5/5."},{"name":"metadata","weight":10,"assessedWeight":10,"points":10,"rules":[{"id":"summary","label":"Useful summary blockquote","weight":5,"observation":"A blockquote before the first H2 with at least 20 non-whitespace characters and no placeholder-only text.","points":5},{"id":"context","label":"Useful introductory context","weight":5,"observation":"An introductory paragraph before the first H2 with at least 20 non-whitespace characters and no placeholder-only text. Listing form fields do not earn these points.","points":5}],"explanation":"Useful summary blockquote: 5/5. Useful introductory context: 5/5."}],"earnedPoints":99.78,"assessedWeight":100,"availableWeight":100,"provisional":false,"calculatedAt":"2026-11-10T22:27:39.601Z","lastVerifiedAt":"2026-11-10T22:27:32.962Z","evidence":{"sourceUrl":"https://aibenchmarkindex.com/llms.txt","contentHash":"7f0c1257e2da6d251f8d4e6f0ff8112eed975e136f60703674cc2cd1eff204aa","processingVersion":"2.0","retrievedAt":"2026-11-10T22:27:32.962Z"},"linkSampling":{"eligibleCount":46,"selectedCount":5,"sampledCount":5,"working":5,"broken":0,"unknown":0,"checkedAt":"2026-11-10T22:27:34.619Z","sourceHash":"7f0c1257e2da6d251f8d4e6f0ff8112eed975e136f60703674cc2cd1eff204aa","method":"deterministic sample, at most 5 URLs, at most 2 concurrent hosts, 15s budget","results":[{"url":"https://aibenchmarkindex.com/academy/choose-and-run-an-ai-benchmark.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/tools.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/.well-known/agent-card.json","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/commerce.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"},{"url":"https://aibenchmarkindex.com/category/browser.md","httpStatus":200,"checkedAt":"2026-11-10T22:27:34.619Z","attempted":true,"status":"working","reason":"http_success"}]},"warnings":["This measures observable documentation, not model rankings or citation probability.","H1 is the only required section in the llms.txt proposal. Other checks are LLMSList quality preferences; missing optional sections do not make usable text invalid.","Destination accessibility covers a sample of 5 out of 46 unique links, not the entire website."]},"updatedAt":"2026-11-10T22:27:39.602Z"}