SiteCheck Company Records

Open LLM Leaderboard v2: finds open-source language models

b2b_openllm_leaderboard

Read-only

Open LLM Leaderboard v2 (Hugging Face, archived March 2025): finds open-source language models by name across all 4,576 leaderboard rows and returns average score, IFEval, BBH, MATH Lvl 5, GPQA, MUSR and MMLU-PRO scores, parameter count, likes, license and hub URL, best average first. Related tools on this server, for a different need: b2b_hyperliquid_leaderboard when you need Hyperliquid public trader leaderboard: top accounts ranked; b2b_pgatour_leaderboard when you need PGA Tour current and upcoming events from ESPN's public. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "q": "<q>"
    },
    "name": "b2b_openllm_leaderboard"
  }
}

Input Schema

Name	Required	Description	Default
`q`	Yes	Model name part, 2 to 60 characters
`limit`	No	Rows to return, 1 to 20 (default 10)

Output Schema

Name	Required	Description	Default
`query`	No
`source`	No
`matches`	No
`results`	No
`checkedAt`	No
`rowsScanned`	No
`rowsInDataset`	No
`leaderboardFrozenSince`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only and open-world access, yet the description still adds real value: a frozen 4,576-row dataset, deterministic 'best average first' ordering, and an explicit pricing model ($0.002 USDC via x402, failed calls uncharged). It stops short of saying how ties or zero-match searches behave.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded, followed by return fields, ordering, sibling routing, and pricing in a logical sequence. The sibling-routing sentences are slightly bulky relative to how rarely they matter, but nothing is truly wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return fields needn't be re-listed, but the description redundantly enumerates them anyway. It supplies the crucial recency caveat (archived March 2025) and cost model that structured fields cannot convey; only edge cases like empty results are unaddressed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with ranges for q and limit, so the schema does the heavy lifting. The description only reinforces that q matches on model name and that results are sorted by average score; it adds no syntax, case-sensitivity, or fallback details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('finds open-source language models by name') plus the exact data source and scope ('Open LLM Leaderboard v2, Hugging Face, archived March 2025'). An agent can immediately tell this apart from the other *leaderboard tools, which cover traders and golf events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes away from the two sibling tools with 'for a different need' clauses, and the 'archived March 2025' note implicitly tells the agent when the data is not current. It does not state an explicit when-not-to-use case (e.g., for live/newer models), which keeps it short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Company Records tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?