Skip to content
Eden Engine

Top AI Model Leaderboard Overview

omnial/get-leaderboard-overview

Returns the default community AI-model leaderboard overview: the ten top-ranked models, each with its current rank plus a best/worst rank confidence range, an Elo-style rating with its own confidence bounds, head-to-head vote count, publishing organization, license, and (where published) per-second generation pricing. Takes no input.

activeper callv1
Provider
Web & Business Data Network
Category
model-benchmarks
Provider price
$0.1365 per call
Latency p50 / p95
— / —
Success rate
—
Verified
—

Provider list price; Omnial MCP charges provider cost plus a platform markup on top.

Contract

input_schema.json
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
output_schema.json
{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "properties": {
        "entries": {
          "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": "The model's license, e.g. 'Proprietary' (nine of ten rows observed) or a named community license (one row: 'minimax-h3-community-license-agreement')."
              },
              "modelKey": {
                "type": "string",
                "description": "The provider's internal identifier for this model version."
              },
              "modelUrl": {
                "type": "null",
                "description": "Always null in the shaped output. The raw field is a URL to the model's own announcement/product page (a census-recorded URL leaf); it is stripped rather than passed through, per this build's rule that a URL leaf carries strip: true or is omitted."
              },
              "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 on every row of the real call -- not always present."
              },
              "contextLength": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "Maximum context window in tokens. Observed null on every row of the real call -- not always present."
              },
              "pricePerImage": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per generated image, for image-output models. Only null was observed on the real call -- unconfirmed for a call that may populate it."
              },
              "pricePerSecond": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per second of generated media, for video/audio-output models. Observed populated (e.g. 0.05) on four of the ten rows of the real call and null on the rest -- not always present."
              },
              "modelDisplayName": {
                "type": "string",
                "description": "The model's public display name, e.g. 'gemini-omni-flash'."
              },
              "modelOrganization": {
                "type": "string",
                "description": "The organization that publishes this model, e.g. 'Google'."
              },
              "inputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million input tokens. Observed null on every row of the real call (a video-generation leaderboard) -- not always present."
              },
              "outputPricePerMillion": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD per million output tokens. Observed null alongside a null inputPricePerMillion on every row -- not always present."
              }
            },
            "additionalProperties": false
          },
          "description": "The ten top-ranked models, in leaderboard rank order -- populated on the single real capture (never observed empty)."
        },
        "metadata": {
          "type": "object",
          "description": "Leaderboard-page metadata. An empty object {} on the observed call; the shape a populated value would take is unconfirmed.",
          "additionalProperties": true
        }
      },
      "additionalProperties": false
    },
    "status": {
      "type": "string",
      "description": "'success' on the single real call observed."
    }
  },
  "description": "The leaderboard overview, as returned at routing.responseResultPath ($.output).",
  "additionalProperties": false
}

Pricing

Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.

Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.

ChargeRate
Per call
Flat, regardless of what comes back
$0.1365
Cost basis
Not recorded

This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.

Updated
Sep 30, 2026