{"ok":true,"site":{"host":"benchlm.ai","url":"https://benchlm.ai/","type":"live","category":"AI & Agents","desc":"LLM leaderboard and benchmark site comparing hundreds of AI models, with ranked scores, source evidence, API pricing, context windows, runtime and head-to-head pages.","tools":[{"name":"search_benchlm","kind":"answer","impl":"imperative","description":"Search BenchLM for AI models, benchmarks, rankings, comparisons, tools, providers, and blog posts. Use this before navigating when the exact BenchLM page is unknown.","title":"Search BenchLM","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"The model, benchmark, provider, comparison, tool, ranking, or topic to search for."},"limit":{"type":"number","description":"Maximum number of results to return. Defaults to 8."}},"required":["query"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"open_benchlm_page","kind":"act","impl":"imperative","description":"Navigate the current BenchLM tab to the best matching page for a model, benchmark, provider, ranking, comparison, blog post, or tool query.","title":"Open BenchLM Page","annotations":{"readOnlyHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"A natural language page request, exact title, model name, benchmark name, provider name, or BenchLM path."},"type":{"type":"string","enum":["any","model","benchmark","best-page","provider","comparison","blog","tool"],"description":"Optional result type to prefer when resolving the page."}},"required":["query"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"open_model_profile","kind":"act","impl":"imperative","description":"Navigate to the BenchLM profile page for a specific AI model by model name, alias, or slug.","title":"Open Model Profile","annotations":{"readOnlyHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"model":{"type":"string","description":"The model name, alias, or slug. Examples: GPT-5.5, Claude Opus 4.7, Gemini 3 Pro."}},"required":["model"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"get_model_details","kind":"answer","impl":"imperative","description":"Return BenchLM metadata for one AI model, including provider, score, source type, context window, reasoning mode, pricing, speed, and category scores.","title":"Get Model Details","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"model":{"type":"string","description":"The model name, alias, or slug. Examples: GPT-5.5, Claude Opus 4.7, Gemini 3 Pro."}},"required":["model"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"find_best_models","kind":"answer","impl":"imperative","description":"Return top BenchLM-ranked AI models for a use case such as coding, reasoning, tool use, web research, computer use, long context, document AI, image understanding, factuality, open source, or value.","title":"Find Best Models","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"useCase":{"type":"string","description":"The use case or leaderboard to optimize for. Examples: coding, long context, tool use, web research, open source, value."},"limit":{"type":"number","description":"Maximum number of models to return. Defaults to 5."},"openWeight":{"type":"boolean","description":"If true, only return open-weight models."},"maxOutputPrice":{"type":"number","description":"Optional maximum output price per 1M tokens."},"minContextTokens":{"type":"number","description":"Optional minimum context window in tokens."},"reasoning":{"type":"boolean","description":"Optional. true returns reasoning models only; false returns non-reasoning models only."}},"required":["useCase"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"recommend_llm","kind":"act","impl":"imperative","description":"Recommend AI models using BenchLM selector logic for a user use case, budget, context-window need, open-weight preference, and speed/quality preference.","title":"Recommend LLM","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"useCase":{"type":"string","enum":["coding","agents","multimodal","writing","analysis","math","general","long-context","tool-use","web-research","computer-use","document-ai","image-understanding","frontend-app-dev","factuality"],"description":"Primary model use case."},"task":{"type":"string","enum":["emails","marketing","fiction","roleplay","studying","research","reasoning","math","legal","medical","image-understanding","charts","pdfs","spreadsheets","data-analysis","extraction","presentations","coding","debugging","frontend","local-code","agents","rag","support","translation","language-learning","voice","transcription","images","video","general"],"description":"Optional exact task; overrides the broad use case."},"audience":{"type":"string","enum":["everyday","builders"],"description":"Assistant-plan guidance or API/local-model guidance."},"budget":{"type":"string","enum":["free","low","mid","unlimited"],"description":"For builders, low means at most $5 and mid at most $20 for 1M input + 200k output tokens. free requests open-weight/local candidates, not free hosting."},"context":{"type":"string","enum":["standard","large","huge"],"description":"Context requirement. large means 200K+ tokens; huge means 1M+ tokens."},"openWeight":{"type":"string","enum":["yes","no","either"],"description":"Whether the user needs an open-weight model."},"speed":{"type":"string","enum":["critical","balanced","quality"],"description":"Preference for speed versus best quality."},"limit":{"type":"number","description":"Maximum number of recommendations to return. Defaults to 5."}},"required":["useCase"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"compare_ai_models","kind":"act","impl":"imperative","description":"Return a BenchLM side-by-side comparison summary for two AI models, then open the comparison page in the current tab. Use this when a user wants benchmark, pricing, context window, or capability tradeoffs between models.","title":"Compare AI Models","annotations":{"readOnlyHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"modelA":{"type":"string","description":"First model name, alias, or slug."},"modelB":{"type":"string","description":"Second model name, alias, or slug."}},"required":["modelA","modelB"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"lookup_benchmark_results","kind":"answer","impl":"imperative","description":"Return the BenchLM leaderboard for a specific benchmark, such as SWE-bench Verified, LiveCodeBench, MMLU, GPQA, BFCL, BrowseComp, OSWorld, or AIME.","title":"Lookup Benchmark Results","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"benchmark":{"type":"string","description":"Benchmark name, full name, or slug."},"limit":{"type":"number","description":"Maximum number of model results to return. Defaults to 10."},"includeUnverified":{"type":"boolean","description":"If true, include non-displayable or unverified benchmark rows. Defaults to false."}},"required":["benchmark"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"estimate_ai_cost","kind":"answer","impl":"imperative","description":"Estimate monthly, daily, and yearly AI model cost for real workloads such as blog posts, website pages, docs articles, PRDs/specs, or shipped product features.","title":"Estimate AI Cost","annotations":{"readOnlyHint":true,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"workload":{"type":"string","enum":["blog-posts","website-pages","docs-articles","prds-specs","features-shipped"],"description":"Workload preset to estimate."},"unitsPerMonth":{"type":"number","description":"Number of workload units per month, such as posts, pages, articles, specs, or features."},"wordsPerUnit":{"type":"number","description":"Approximate final words per unit. Ignored for features-shipped."},"revisionRounds":{"type":"number","description":"Number of drafting/revision passes per unit."},"complexity":{"type":"string","enum":["small","medium","large"],"description":"Feature complexity. Used for features-shipped."},"modelNames":{"type":"array","items":{"type":"string"},"description":"Optional model names to price. Defaults to BenchLM cost-calculator defaults."}},"required":["workload"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"},{"name":"subscribe_to_benchlm_updates","kind":"transact","impl":"imperative","description":"Subscribe an email address to weekly BenchLM benchmark, ranking, and pricing updates. This tool always asks the user to confirm before submitting.","title":"Subscribe to BenchLM Updates","annotations":{"readOnlyHint":false,"untrustedContentHint":false},"inputSchema":{"type":"object","properties":{"email":{"type":"string","description":"Email address to subscribe."}},"required":["email"]},"hasHandler":true,"hasExecute":true,"__source":"spec","executable":true,"handlerField":"execute"}],"apiSurface":"spec","favicon":"/favicons/benchlm.ai.png","toolCount":10}}