Which LLM for which task: benchmark scores and API prices for 400+ models. Free, no key.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Two models side by side: score on every category board where both were measured, prices, context. Names are matched loosely: 'claude opus', 'gpt-5' or a slug all work.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http llmbenchmark https://api.llmbenchmark.ai/mcp
Two models side by side: score on every category board where both were measured, prices, context. Names are matched loosely: 'claude opus', 'gpt-5' or a slug all work.
| Argument | Type | Description |
|---|---|---|
| model_a* | string | |
| model_b* | string |
{
"type": "object",
"title": "compare_modelsArguments",
"required": [
"model_a",
"model_b"
],
"properties": {
"model_a": {
"type": "string",
"title": "Model A"
},
"model_b": {
"type": "string",
"title": "Model B"
}
}
}The top models on one category's board. category is one of overall, coding, agentic, reasoning, math, knowledge, design (see list_categories). limit is 1 to 50. overall is the LLMBenchmark Index: a weighted mean of the Vibe Coding Index, the agentic, reasoning, math and knowledge indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| category | string |
{
"type": "object",
"title": "get_leaderboardArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 10
},
"category": {
"type": "string",
"title": "Category",
"default": "overall"
}
}
}One model: maker, release date, prices, context, open weights, and its score and rank on every category board. Name or slug.
| Argument | Type | Description |
|---|---|---|
| model* | string |
{
"type": "object",
"title": "get_modelArguments",
"required": [
"model"
],
"properties": {
"model": {
"type": "string",
"title": "Model"
}
}
}API prices (USD per million tokens), cheapest output price first: the maker's own price when it serves the model on OpenRouter, else the median of providers (price_basis says which), plus the cheapest provider. Filter by model name and/or maker; limit is 1 to 100.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| maker | any | |
| model | any |
{
"type": "object",
"title": "get_pricesArguments",
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20
},
"maker": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Maker",
"default": null
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model",
"default": null
}
}
}The categories recommend_model and get_leaderboard know, the benchmark board behind each, and the task keywords that select it.
No arguments.
{
"type": "object",
"title": "list_categoriesArguments",
"properties": {}
}Which model should I use for this task? Maps the task text to a category (coding, agentic, reasoning, math, knowledge, web design, or overall when nothing matches) by a fixed keyword map, filters by output price per million tokens, context length and open weights, and ranks by that category's benchmark board. Deterministic, no LLM call. Returns top_k models with scores, rank, prices, context, page URLs and a one-line reason. overall is the LLMBenchmark Index: a weighted mean of the Vibe Coding Index, the agentic, reasoning, math and knowledge indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.
| Argument | Type | Description |
|---|---|---|
| task* | string | |
| top_k | integer | |
| open_weights_only | boolean | |
| min_context_tokens | any | |
| max_output_price_per_m | any |
{
"type": "object",
"title": "recommend_modelArguments",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"title": "Task"
},
"top_k": {
"type": "integer",
"title": "Top K",
"default": 3
},
"open_weights_only": {
"type": "boolean",
"title": "Open Weights Only",
"default": false
},
"min_context_tokens": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Min Context Tokens",
"default": null
},
"max_output_price_per_m": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Max Output Price Per M",
"default": null
}
}
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 19, 2026.
No readOnlyHint / destructiveHint annotations, so clients can't tell a read from a write without asking.
Fix: Add annotations to each tool, e.g. { readOnlyHint: true } for tools that only read.