Top AI Models by Category | LMArena Rankings

Describe the models you want to compare, such as writing or text chat. Your assistant confirms the source ranking category and requests its leading models, with an optional maximum count.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use Toolmu get-top-models-by-category-lmarena to request leading models for my ordinary purpose or Arena leaderboard page link. Reuse a working Toolmu connection, or follow https://toolmu.com/SKILL.md to connect. Check current requirements, availability and the cumulative Credits ceiling, then execute within my authorization and budget. The overall text category for writing and text conversation is confirmed by the actual Arena text-board page and a successful exact category request; use that real source category reference internally, explaining that it is the broad text ranking, not a writing-only task evaluation. For any other purpose or page, establish its currently accepted category from actual supplier documentation, returned category metadata or a separately authorized bounded witness; another website path alone does not prove this Tool accepts it. Parse confirmed links with a URL parser rather than guessing a reference from names. If the category is unresolved, offer readable confirmed choices or ask for an ordinary relevant leaderboard page link; never ask me for a technical category identifier, silently substitute the text category or invent acceptance. Include the documented optional maximum only when I supply an ordinary model count, converting its representation internally without guessing defaults or valid ranges. Present only returned records in their source ranking order, with actual count and missing details; include names, scores, links and time context only when supplied. A maximum is not an exact count, and a rank does not establish suitability for my workload. This does not run models or generate content. Bracketed example text is replaced by my own content.

Task:
Find leading LMArena models in the category for [what you want to do, such as writing or text chat]. Request at most [maximum number of models, such as five] models. Confirm the category first, then show only returned records and explain their limits.

Paste into your connected AI's conversation.

Connection guide

Up to 0.012 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

LMArena

Top AI Models by Category | LMArena Rankings

Describe the models you want to compare, such as writing or text chat. Your assistant confirms the source ranking category and requests its leading models, with an optional maximum count.

You receive

A ranked list from the source category confirmed for your request. Your assistant organizes only the records actually returned, keeping their source order, actual count and any missing information clear.

Start with your task

Find leading LMArena models in the category for [what you want to do, such as writing or text chat]. Request at most [maximum number of models, such as five] models. Confirm the category first, then show only returned records and explain their limits.

What to know

Your assistant must confirm a supported source category before requesting it. A maximum count does not guarantee that many results. The rankings do not establish the best model for your task, run a model or generate content.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Category query`queryParams`	`object`	Required	Required object containing the category value and, optionally, an integer limit. Additional query properties are not accepted by the published input schema. Required fields `category`
Maximum requested model count`queryParams.limit`	`integer`	Optional	Optional integer specifying the maximum number of top models to request. No default, minimum or maximum bound is published. It is not a guarantee of an exact result count.
Leaderboard category identifier`queryParams.category`	`string`	Required	Required string identifying the leaderboard category to query. No accepted-value list is published; confirm the exact identifier before calling. A free string type does not establish support for every arbitrary value.

View raw JSON

{
  "type": "object",
  "required": [
    "queryParams"
  ],
  "properties": {
    "queryParams": {
      "type": "object",
      "required": [
        "category"
      ],
      "properties": {
        "limit": {
          "type": "integer",
          "description": "Maximum number of top models to return."
        },
        "category": {
          "type": "string",
          "description": "Leaderboard category to query."
        }
      },
      "additionalProperties": false
    }
  },
  "additionalProperties": false
}

Result schema

Output fields have not been documented yet.

Additional notes

Describe what you want to explore, such as writing or text conversation, or share an ordinary Arena category leaderboard page link. Your assistant confirms the supported category before requesting it. Writing and text conversation use the broad text ranking; a different purpose needs its category checked first.

Treat the first entries as candidates for closer investigation within that comparison setting. A leading position in one category does not establish a universal winner or transfer to a different workload. After reviewing the returned list, test suitable candidates on your own requirements before making an adoption decision.

Keep the returned order and distinguish the lookup from your later interpretation. When the response supplies source or time context, include it; when it does not, leave that context unknown. A later lookup may return a different list, so do not assign an invented update date or present an earlier ranking as newly retrieved.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Describe the purpose or provide its ordinary Arena leaderboard page link. Writing or text chat can use the confirmed broad text ranking; other directions need their category checked first. Your assistant asks readable follow-up questions when needed.

Top AI Models by Category | LMArena Rankings

Top AI Models by Category | LMArena Rankings

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the models you want to explore

Confirm the readable category and count

Read the actual ranked list

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Describe the models you want to explore

Confirm the readable category and count

Read the actual ranked list

Questions about this tool.

What should I provide?

Will I always get as many models as requested?

Does the first model identify the best choice for my task?