Tool tree
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.
Implementation
gradeNot graded
gradeNot graded
search_benchlmAnswer
Search BenchLM for AI models, benchmarks, rankings, comparisons, tools, providers, and blog posts. Use this before navigating when the exact BenchLM page is unknown.
View tool JSON
{
"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.",
"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"
]
}
}open_benchlm_pageAction
Navigate the current BenchLM tab to the best matching page for a model, benchmark, provider, ranking, comparison, blog post, or tool query.
View tool JSON
{
"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.",
"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"
]
}
}open_model_profileAction
Navigate to the BenchLM profile page for a specific AI model by model name, alias, or slug.
View tool JSON
{
"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.",
"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"
]
}
}get_model_detailsAnswer
Return BenchLM metadata for one AI model, including provider, score, source type, context window, reasoning mode, pricing, speed, and category scores.
View tool JSON
{
"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.",
"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"
]
}
}find_best_modelsAnswer
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.
View tool JSON
{
"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.",
"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"
]
}
}recommend_llmAction
Recommend AI models using BenchLM selector logic for a user use case, budget, context-window need, open-weight preference, and speed/quality preference.
View tool JSON
{
"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.",
"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"
]
}
}compare_ai_modelsAction
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.
View tool JSON
{
"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.",
"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"
]
}
}lookup_benchmark_resultsAnswer
Return the BenchLM leaderboard for a specific benchmark, such as SWE-bench Verified, LiveCodeBench, MMLU, GPQA, BFCL, BrowseComp, OSWorld, or AIME.
View tool JSON
{
"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.",
"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"
]
}
}estimate_ai_costAnswer
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.
View tool JSON
{
"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.",
"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"
]
}
}subscribe_to_benchlm_updatesSensitive Action
Subscribe an email address to weekly BenchLM benchmark, ranking, and pricing updates. This tool always asks the user to confirm before submitting.
View tool JSON
{
"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.",
"inputSchema": {
"type": "object",
"properties": {
"email": {
"type": "string",
"description": "Email address to subscribe."
}
},
"required": [
"email"
]
}
}