Read the LMArena text-model leaderboard

Ask for Text Arena rankings without supplying a writing task or model name. Compare the returned model names, positions, scores and vote counts to choose candidates for writing, chat or other text tests.

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-text-leaderboard-lmarena to read Text Arena rankings. Reuse a working Toolmu connection, or follow https://toolmu.com/SKILL.md to connect. Check current availability, requirements and the Credits ceiling, then execute within my authorization and budget. No writing task, model name or extra named input is required; handle the request internally without asking for technical fields or empty objects, and do not invent model, prompt, category, filtering, count or pagination controls. Apply any ordinary display-count preference only after retrieval. Present actual model names, source ranks, scores, votes and relevant organization labels or links in source order, retaining actual source identities internally and keeping variants separate. Preserve original ranking-range labels and values, including reversed or equal values, without assigning confidence. Keep blank labels, missing model details, release information and prices as returned; do not fill them from names or URLs. Genuine zero prices do not prove free access, and units, currency and current terms need separate confirmation. Do not invent a separate complete model catalog, background information or update timestamps absent from the response. Reading rankings does not run a model or generate an answer, establish full coverage or verify suitability and license rights for my task. Bracketed optional example text is replaced by my own content.

Task:
Show the LMArena text-model rankings with the model names, ranks, scores and vote counts returned. Explain missing information and what to check before separately testing a model for writing or chat.

Paste into your connected AI's conversation.

Connection guide

Up to 0.12 credits / call

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

LMArena

Read the LMArena text-model leaderboard

You receive

Text Arena model rankings with names, organizations, reference links, positions, scores and vote counts. Additional model information is included only when returned; missing information and genuine zero prices remain distinct.

Start with your task

Show the LMArena text-model rankings with the model names, ranks, scores and vote counts returned. Explain missing information and what to check before separately testing a model for writing or chat.

What to know

This reads rankings without running a model or generating an answer. It does not establish performance on every text task, a complete available-model catalogue or the current source update time. Preserve the original rank bounds even when their numeric order is reversed; rating confidence, context units, price conditions and license rights require separate checking.

Inputs & outputs

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

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Optional query container`queryParams`	`object`	Optional	Open optional object with no documented named controls or defaults. The captured successful text-leaderboard request used {}; no model, prompt, category, pagination or top-N parameter is defined.

View raw JSON

{
  "type": "object",
  "required": [],
  "properties": {
    "queryParams": {
      "type": "object",
      "properties": {},
      "additionalProperties": true
    }
  },
  "additionalProperties": false
}

Result schema

No fixed output contract is available. Field types reflect saved result evidence; individual responses can differ.

Result schema
Field / Path	Type	Meaning
Text Arena ranked records`result.data.entries`	`array`	Model records for the text leaderboard. The saved response contains 413, without a separate initialModels catalogue or metadata; count and completeness are not future guarantees.
Model configuration key`result.data.entries[].modelKey`	`string`	Source identifier that distinguishes a record and its configuration. Keep it beside the display name rather than merging similarly named versions.
Source display name`result.data.entries[].modelDisplayName`	`string`	Human-readable name reported for this model. It does not establish current availability or explain a configuration label on its own.
Reported model organization`result.data.entries[].modelOrganization`	`string`	Organization text is blank in 50 saved records. Retain those blanks as unknown instead of assigning an organization from names or links.
Source model reference`result.data.entries[].modelUrl`	`string`	Link attached to the record for separate checking. Its presence does not verify the page, service access, price or license conditions.
Text-leaderboard position`result.data.entries[].rank`	`number`	Position supplied for this returned collection. It is a source comparison value, not a guaranteed ordering for every writing or chat task.
Source text-model rating`result.data.entries[].rating`	`number`	Reported numeric rating accompanied by bounds and votes. Calculation and scale are not defined here; do not translate it into answer accuracy.
Source vote count`result.data.entries[].votes`	`number`	Count reported for this record. Voter identities, date range and counting rules are not provided, so it is not a verified number of distinct people.
rankLower reported endpoint`result.data.entries[].rankLower`	`number`	Keep the original named value. It exceeds rankUpper in 412 saved records and equals it in one; no confidence interpretation or silent swap is justified.
rankUpper reported endpoint`result.data.entries[].rankUpper`	`number`	Other source rank endpoint, paired with rankLower under its original name. Preserve numeric order instead of reformatting an assumed statistical interval.
Lower source rating endpoint`result.data.entries[].ratingLower`	`number`	Reported rating-bound value. Keep it with ratingUpper without claiming a confidence level or statistical significance.
Upper source rating endpoint`result.data.entries[].ratingUpper`	`number`	Companion rating endpoint for this model. Its presence does not explain the evaluation method or prove performance on an unrelated task.
Reported context-length value`result.data.entries[].contextLength`	`number \| null`	Numeric in 277 saved records and null in 136. Units and effective input/output limits are unspecified; do not assume tokens or replace null with zero.
Source input-price value`result.data.entries[].inputPricePerMillion`	`number \| null`	Source per-million label with 315 numeric and 98 null values; two numbers are literal zero. Currency and billing conditions are unknown, and this is separate from Toolmu call cost.
Source output-price value`result.data.entries[].outputPricePerMillion`	`number \| null`	Reported per-million output-price label: 315 numbers, including two zeros, and 98 nulls. Confirm priced quantity, currency and current model terms before calculating a quote.
Reported release label`result.data.entries[].releaseType`	`string \| null`	Saved values include three pre_release, one co_release and 409 nulls. Preserve the labels; meanings, dates and current release status are not documented here.
Reported license text`result.data.entries[].license`	`string`	Source-supplied label rather than full legal terms. Verify permissions for the intended model use separately before relying on it.

Additional notes

Read Text Arena rankings with no required input. The optional query settings do not define named model, prompt, category, pagination or top-N controls. Retrieve the records first, then select the models and fields needed for your comparison; the request does not submit a text task to those models.

The saved response contains 413 records in result.data.entries. It contains neither a separate initialModels catalogue nor background metadata or a source-update timestamp. Treat the count as one observation, not a fixed future size or evidence that every available model is included. Keep model keys alongside display names to distinguish configurations.

Read ratings and votes with their source bounds. In the saved records, 412 rankLower values exceed rankUpper and one pair is equal; preserve all original labels and values. Context is missing for 136 records and each model-price field is missing for 98. Each price field also has two reported zeros, which do not establish free service. Confirm the relevant model documentation and test your task before using the shortlist.

Questions about this tool.

Inputs, results and details to know before running it.

Get connected

Complete coverage is not established. Read the ranking records actually returned; they are not proof of a separate complete model directory or a promise that every model version will appear.

Read the LMArena text-model leaderboard

Read the LMArena text-model leaderboard

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Ask for text-model rankings

Compare the model names and scores

Try candidates on your own text tasks

Questions about this tool.

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Ask for text-model rankings

Compare the model names and scores

Try candidates on your own text tasks

Questions about this tool.

Does this include every available text model?

Does a high rating guarantee a good answer for my task?

Can zero model prices be budgeted as free service?