Best AI Coding Models + Top Text Model Snapshot (LMArena Leaderboard)

omnial/get-best-coding-models

One call returns the full LMArena Code Arena leaderboard -- every model's rank, Elo-style rating with its confidence range, vote count, publishing organization, license, per-million-token pricing, context length, and release status -- alongside a snapshot of the top 10 models on the separate Text Arena leaderboard, for comparing code-focused models against general-purpose leaders.

activeper callv2

Price

Up to $0.0137 per call; you pay what the call used

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.00.

Data source

LMArena

Data from LMArena.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

For developers: the calls your assistant makes

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/get-best-coding-models" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/get-best-coding-models" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/get-best-coding-models", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/get-best-coding-models", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0137

Updated: Oct 27, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "properties": {
        "code_leaderboard": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "rank": {
                "type": "number",
                "description": "The model's current leaderboard position."
              },
              "votes": {
                "type": "number",
                "description": "Number of head-to-head votes backing this rating."
              },
              "rating": {
                "type": "number",
                "description": "Elo-style leaderboard rating."
              },
              "license": {
                "type": "string",
                "description": "e.g. 'Proprietary', 'MIT', 'Apache 2.0'."
              },
              "modelKey": {
                "type": "string",
                "description": "The provider's internal identifier for this model version."
              },
              "modelUrl": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "The model publisher's own announcement/product page URL. Observed null on some rows in the real call; withheld from this tool's response, listed here only so this schema covers every key the raw leaderboard row actually carries."
              },
              "rankLower": {
                "type": "number",
                "description": "Worst-case rank within the statistical confidence interval."
              },
              "rankUpper": {
                "type": "number",
                "description": "Best-case rank within the statistical confidence interval."
              },
              "ratingLower": {
                "type": "number",
                "description": "Lower bound of the rating's confidence interval."
              },
              "ratingUpper": {
                "type": "number",
                "description": "Upper bound of the rating's confidence interval."
              },
              "releaseType": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "e.g. 'co_release', 'pre_release' for a model still in preview. Observed null for a generally-available model -- not always present."
              },
              "contextLength": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "Maximum context window in tokens. Observed null for some models -- not always present."
              },
              "pricePerImage": {
                "type": "null",
                "description": "Always null on the real call observed -- this endpoint's two leaderboards (code, text) never carry image-output pricing."
              },
              "pricePerSecond": {
                "type": "null",
                "description": "Always null on the real call observed -- this endpoint's two leaderboards (code, text) never carry video/audio-output pricing."
              },
              "modelDisplayName": {
                "type": "string",
                "description": "The model's public display name, e.g. 'claude-opus-5-max'."
              },
              "modelOrganization": {
                "type": "string",
                "description": "The organization that publishes this model, e.g. 'OpenAI'."
              },
              "inputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million input tokens. Observed null for models with no published per-token API pricing -- not always present."
              },
              "outputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million output tokens. Observed null alongside a null inputPricePerMillion on the same models -- not always present."
              }
            },
            "additionalProperties": false
          },
          "description": "Every model on the Code Arena leaderboard, in rank order. 128 entries on the real call observed; cardinality is not confirmed fixed at 128 going forward."
        },
        "text_leaderboard_snapshot": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "rank": {
                "type": "number",
                "description": "The model's current leaderboard position."
              },
              "votes": {
                "type": "number",
                "description": "Number of head-to-head votes backing this rating."
              },
              "rating": {
                "type": "number",
                "description": "Elo-style leaderboard rating."
              },
              "license": {
                "type": "string",
                "description": "e.g. 'Proprietary', 'MIT'."
              },
              "modelKey": {
                "type": "string",
                "description": "The provider's internal identifier for this model version."
              },
              "modelUrl": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "The model publisher's own announcement/product page URL. Observed null on some rows in the real call; withheld from this tool's response, listed here only so this schema covers every key the raw leaderboard row actually carries."
              },
              "rankLower": {
                "type": "number",
                "description": "Worst-case rank within the statistical confidence interval."
              },
              "rankUpper": {
                "type": "number",
                "description": "Best-case rank within the statistical confidence interval."
              },
              "ratingLower": {
                "type": "number",
                "description": "Lower bound of the rating's confidence interval."
              },
              "ratingUpper": {
                "type": "number",
                "description": "Upper bound of the rating's confidence interval."
              },
              "releaseType": {
                "type": [
                  "string",
                  "null"
                ],
                "description": "e.g. 'pre_release' for a model still in preview. Observed null for a generally-available model -- not always present."
              },
              "contextLength": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "Maximum context window in tokens. Observed null for at least one model in this top-10 slice -- not always present."
              },
              "pricePerImage": {
                "type": "null",
                "description": "Always null on the real call observed -- this endpoint's two leaderboards (code, text) never carry image-output pricing."
              },
              "pricePerSecond": {
                "type": "null",
                "description": "Always null on the real call observed -- this endpoint's two leaderboards (code, text) never carry video/audio-output pricing."
              },
              "modelDisplayName": {
                "type": "string",
                "description": "The model's public display name, e.g. 'claude-fable-5'."
              },
              "modelOrganization": {
                "type": "string",
                "description": "The organization that publishes this model, e.g. 'Anthropic'."
              },
              "inputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million input tokens. Not observed null in this top-10 slice, but typed nullable to match the identical field on code_leaderboard."
              },
              "outputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million output tokens. Not observed null in this top-10 slice, but typed nullable to match the identical field on code_leaderboard."
              }
            },
            "additionalProperties": false
          },
          "description": "The top 10 models on the separate Text Arena leaderboard, in rank order, for comparison against the code-focused leaderboard above. Exactly 10 entries on the real call observed. Same per-entry shape as code_leaderboard."
        }
      },
      "additionalProperties": false
    },
    "status": {
      "type": "string",
      "description": "'success' on the real call observed."
    }
  },
  "description": "The leaderboard snapshot.",
  "additionalProperties": false
}