# Open LLM Leaderboard v2 Model Search

> Open LLM Leaderboard v2 Model Search is a paid API for AI agents from api.companyrecords-api.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-24).

Searches the archived Hugging Face Open LLM Leaderboard v2 (4,576 models) by name and returns benchmark scores, parameter count, license, and hub metadata sorted by average score.

## Facts

- Endpoint: GET https://api.companyrecords-api.workers.dev/api/b2b/openllm-leaderboard?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-24
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/open-llm-leaderboard-v2-model-search-072fa382
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EixbnxedX6uu2kVUh8rIq

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability open-llm-leaderboard-v2-model-search-072fa382
```

Example prompt: Search the Open LLM Leaderboard for all Mistral models and show me their average score, MATH Lvl 5, GPQA, and parameter count — return up to 10 results sorted best first.

## When to prefer this

Use this endpoint when you need to look up benchmark performance data for one or more open-source LLMs by name from the Hugging Face Open LLM Leaderboard v2. It's ideal for comparing models on IFEval, BBH, MATH Lvl 5, GPQA, MUSR, or MMLU-PRO, or for retrieving metadata like parameter count, license, and community likes. Prefer this over general web search when you need structured, comparable numeric benchmark data across multiple models in a single call.

## Known failure modes

- Query string shorter than 2 or longer than 60 characters returns a validation error
- No models matching the query returns an empty results array
- Limit parameter outside 1–20 range may be rejected or clamped
- Stale data: leaderboard frozen since March 2025, so newer models not present
- Payment failure (x402) if USDC balance is insufficient

## How this service works

Pay-per-call company registry, government, legal and B2B data tools for AI agents, from official registers and public sources. Payment: x402, USDC on Base, Solana, Arc, Polygon, Arbitrum, Monad, World Chain, Optimism, Avalanche, Celo or Stellar, or RLUSD/XRP on the XRP Ledger. No signup, no API key; a failed call is not charged.

## Output

Returns a JSON object with the search query, source URL, total match count, rows scanned, leaderboard freeze date, and an array of matching models sorted by average score descending. Each model entry includes: model name, Hugging Face URL, average score, IFEval, BBH, MATH Lvl 5, GPQA, MUSR, MMLU-PRO scores, parameter count in billions, hub likes, and license string.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "q"
     ],
     "properties": {
      "q": {
       "type": "string",
       "description": "Model name part, 2 to 60 characters"
      },
      "limit": {
       "type": "string",
       "description": "Rows to return, 1 to 20 (default 10)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "query": "Yi-1.5",
  "source": "https://huggingface.co/datasets/open-llm-leaderboard/contents",
  "matches": 18,
  "results": [
   {
    "bbh": 44.26,
    "url": "https://huggingface.co/01-ai/Yi-1.5-34B-Chat",
    "gpqa": 15.32,
    "musr": 13.06,
    "model": "01-ai/Yi-1.5-34B-Chat",
    "ifeval": 60.67,
    "license": "apache-2.0",
    "mmluPro": 39.12,
    "hubLikes": 268,
    "mathLvl5": 27.72,
    "averageScore": 33.36,
    "parametersBillions": 34.39
   },
   {
    "bbh": 36.95,
    "url": "https://huggingface.co/01-ai/Yi-1.5-9B-Chat",
    "gpqa": 11.3,
    "musr": 12.84,
    "model": "01-ai/Yi-1.5-9B-Chat",
    "ifeval": 60.46,
    "license": "apache-2.0",
    "mmluPro": 33.06,
    "hubLikes": 141,
    "mathLvl5": 22.58,
    "averageScore": 29.53,
    "parametersBillions": 8.83
   }
  ],
  "checkedAt": "2026-10-23T09:37:40.668Z",
  "rowsScanned": 4576,
  "rowsInDataset": 4576,
  "leaderboardFrozenSince": "2025-03-20"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/open-llm-leaderboard-v2-model-search-072fa382/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.companyrecords-api.workers.dev](https://www.zero.xyz/host/api.companyrecords-api.workers.dev/llms.txt)